add example_dataset in training scripts (#1358)

* add example_dataset in training scripts

* fix example datasets

.gitignore

@@ -2,6 +2,7 @@
 /models
 /scripts
 /diffusers
+/.vscode
 *.pkl
 *.safetensors
 *.pth

diffsynth/core/gradient/gradient_checkpoint.py

@@ -1,12 +1,32 @@
 import torch
 
 
+try:
+    import deepspeed
+    _HAS_DEEPSPEED = True
+except ModuleNotFoundError:
+    _HAS_DEEPSPEED = False
+
+
 def create_custom_forward(module):
     def custom_forward(*inputs, **kwargs):
         return module(*inputs, **kwargs)
     return custom_forward
 
 
+def create_custom_forward_use_reentrant(module):
+    def custom_forward(*inputs):
+        return module(*inputs)
+    return custom_forward
+
+
+def judge_args_requires_grad(*args):
+    for arg in args:
+        if isinstance(arg, torch.Tensor) and arg.requires_grad:
+            return True
+    return False
+
+
 def gradient_checkpoint_forward(
     model,
     use_gradient_checkpointing,
@@ -14,6 +34,17 @@ def gradient_checkpoint_forward(
     *args,
     **kwargs,
 ):
+    if use_gradient_checkpointing and _HAS_DEEPSPEED and deepspeed.checkpointing.is_configured():
+        all_args = args + tuple(kwargs.values())
+        if not judge_args_requires_grad(*all_args):
+            # get the first grad_enabled tensor from un_checkpointed forward
+            model_output = model(*args, **kwargs)
+        else:
+            model_output = deepspeed.checkpointing.checkpoint(
+                create_custom_forward_use_reentrant(model),
+                *all_args,
+            )
+        return model_output
     if use_gradient_checkpointing_offload:
         with torch.autograd.graph.save_on_cpu():
             model_output = torch.utils.checkpoint.checkpoint(

diffsynth/diffusion/runner.py

@@ -29,7 +29,7 @@ def launch_training_task(
     dataloader = torch.utils.data.DataLoader(dataset, shuffle=True, collate_fn=lambda x: x[0], num_workers=num_workers)
     model.to(device=accelerator.device)
     model, optimizer, dataloader, scheduler = accelerator.prepare(model, optimizer, dataloader, scheduler)
-    
+    initialize_deepspeed_gradient_checkpointing(accelerator)
     for epoch_id in range(num_epochs):
         for data in tqdm(dataloader):
             with accelerator.accumulate(model):
@@ -70,3 +70,19 @@ def launch_data_process_task(
                 save_path = os.path.join(model_logger.output_path, str(accelerator.process_index), f"{data_id}.pth")
                 data = model(data)
                 torch.save(data, save_path)
+
+
+def initialize_deepspeed_gradient_checkpointing(accelerator: Accelerator):
+    if getattr(accelerator.state, "deepspeed_plugin", None) is not None:
+        ds_config = accelerator.state.deepspeed_plugin.deepspeed_config
+        if "activation_checkpointing" in ds_config:
+            import deepspeed
+            act_config = ds_config["activation_checkpointing"]
+            deepspeed.checkpointing.configure(
+                mpu_=None, 
+                partition_activations=act_config.get("partition_activations", False),
+                checkpoint_in_cpu=act_config.get("cpu_checkpointing", False),
+                contiguous_checkpointing=act_config.get("contiguous_memory_optimization", False)
+            )
+        else:
+            print("Do not find activation_checkpointing config in deepspeed config, skip initializing deepspeed gradient checkpointing.")

docs/en/Model_Details/Anima.md

@@ -133,7 +133,7 @@ Anima models are trained through [`examples/anima/model_training/train.py`](http
 We provide a sample image dataset for testing:
 
 ```shell
-modelscope download --dataset DiffSynth-Studio/example_image_dataset --local_dir ./data/example_image_dataset
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --local_dir ./data/diffsynth_example_dataset
 ```
 
 For training script details, refer to [Model Training](../Pipeline_Usage/Model_Training.md). For advanced training techniques, see [Training Framework Documentation](https://github.com/modelscope/DiffSynth-Studio/tree/main/docs/zh/Training/).

docs/en/Model_Details/FLUX.md

@@ -195,7 +195,7 @@ FLUX series models are uniformly trained through [`examples/flux/model_training/
 We have built a sample image dataset for your testing. You can download this dataset with the following command:
 
 ```shell
-modelscope download --dataset DiffSynth-Studio/example_image_dataset --local_dir ./data/example_image_dataset
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --local_dir ./data/diffsynth_example_dataset
 ```
 
 We have written recommended training scripts for each model, please refer to the table in the "Model Overview" section above. For how to write model training scripts, please refer to [Model Training](../Pipeline_Usage/Model_Training.md); for more advanced training algorithms, please refer to [Training Framework Detailed Explanation](https://github.com/modelscope/DiffSynth-Studio/tree/main/docs/en/Training/).

docs/en/Model_Details/FLUX2.md

@@ -145,7 +145,7 @@ FLUX.2 series models are uniformly trained through [`examples/flux2/model_traini
 We have built a sample image dataset for your testing. You can download this dataset with the following command:
 
 ```shell
-modelscope download --dataset DiffSynth-Studio/example_image_dataset --local_dir ./data/example_image_dataset
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --local_dir ./data/diffsynth_example_dataset
 ```
 
 We have written recommended training scripts for each model, please refer to the table in the "Model Overview" section above. For how to write model training scripts, please refer to [Model Training](../Pipeline_Usage/Model_Training.md); for more advanced training algorithms, please refer to [Training Framework Detailed Explanation](https://github.com/modelscope/DiffSynth-Studio/tree/main/docs/en/Training/).

docs/en/Model_Details/LTX-2.md

@@ -217,7 +217,7 @@ LTX-2 series models are uniformly trained through [`examples/ltx2/model_training
 We have built a sample video dataset for your testing. You can download this dataset with the following command:
 
 ```shell
-modelscope download --dataset DiffSynth-Studio/example_video_dataset --local_dir ./data/example_video_dataset
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --local_dir ./data/diffsynth_example_dataset
 ```
 
 We have written recommended training scripts for each model, please refer to the table in the "Model Overview" section above. For how to write model training scripts, please refer to [Model Training](../Pipeline_Usage/Model_Training.md); for more advanced training algorithms, please refer to [Training Framework Detailed Explanation](https://github.com/modelscope/DiffSynth-Studio/tree/main/docs/en/Training/).

docs/en/Model_Details/Qwen-Image.md

@@ -199,7 +199,7 @@ Qwen-Image series models are uniformly trained through [`examples/qwen_image/mod
 We have built a sample image dataset for your testing. You can download this dataset with the following command:
 
 ```shell
-modelscope download --dataset DiffSynth-Studio/example_image_dataset --local_dir ./data/example_image_dataset
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --local_dir ./data/diffsynth_example_dataset
 ```
 
 We have written recommended training scripts for each model, please refer to the table in the "Model Overview" section above. For how to write model training scripts, please refer to [Model Training](../Pipeline_Usage/Model_Training.md); for more advanced training algorithms, please refer to [Training Framework Detailed Explanation](https://github.com/modelscope/DiffSynth-Studio/tree/main/docs/en/Training/).

docs/en/Model_Details/Wan.md

@@ -253,7 +253,7 @@ Wan series models are uniformly trained through [`examples/wanvideo/model_traini
 We have built a sample video dataset for your testing. You can download this dataset with the following command:
 
 ```shell
-modelscope download --dataset DiffSynth-Studio/example_video_dataset --local_dir ./data/example_video_dataset
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --local_dir ./data/diffsynth_example_dataset
 ```
 
 We have written recommended training scripts for each model, please refer to the table in the "Model Overview" section above. For how to write model training scripts, please refer to [Model Training](../Pipeline_Usage/Model_Training.md); for more advanced training algorithms, please refer to [Training Framework Detailed Explanation](https://github.com/modelscope/DiffSynth-Studio/tree/main/docs/en/Training/).

docs/en/Model_Details/Z-Image.md

@@ -134,7 +134,7 @@ Z-Image series models are uniformly trained through [`examples/z_image/model_tra
 We have built a sample image dataset for your testing. You can download this dataset with the following command:
 
 ```shell
-modelscope download --dataset DiffSynth-Studio/example_image_dataset --local_dir ./data/example_image_dataset
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --local_dir ./data/diffsynth_example_dataset
 ```
 
 We have written recommended training scripts for each model, please refer to the table in the "Model Overview" section above. For how to write model training scripts, please refer to [Model Training](../Pipeline_Usage/Model_Training.md); for more advanced training algorithms, please refer to [Training Framework Detailed Explanation](https://github.com/modelscope/DiffSynth-Studio/tree/main/docs/en/Training/).

docs/en/Pipeline_Usage/Model_Training.md

@@ -69,25 +69,11 @@ We have built sample datasets for your testing. To understand how the universal
 
 <details>
 
-<summary>Sample Image Dataset</summary>
+<summary>Sample Dataset</summary>
 
 > ```shell
-> modelscope download --dataset DiffSynth-Studio/example_image_dataset --local_dir ./data/example_image_dataset
+> modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --local_dir ./data/diffsynth_example_dataset
 > ```
-> 
-> Applicable to training of image generation models such as Qwen-Image and FLUX.
-
-</details>
-
-<details>
-
-<summary>Sample Video Dataset</summary>
-
-> ```shell
-> modelscope download --dataset DiffSynth-Studio/example_video_dataset --local_dir ./data/example_video_dataset
-> ```
-> 
-> Applicable to training of video generation models such as Wan.
 
 </details>
 
@@ -123,7 +109,6 @@ Similar to [model loading during inference](../Pipeline_Usage/Model_Inference.md
 
 <details>
 
-<details>
 
 <summary>Load models from local file paths</summary>
 
@@ -244,4 +229,119 @@ accelerate launch --config_file examples/qwen_image/model_training/full/accelera
 * The training framework does not support batch size > 1. The reasons are complex. See [Q&A: Why doesn't the training framework support batch size > 1?](../QA.md#why-doesnt-the-training-framework-support-batch-size--1)
 * Some models contain redundant parameters. For example, the text encoding part of the last layer of Qwen-Image's DiT part. When training these models, `--find_unused_parameters` needs to be set to avoid errors in multi-GPU training. For compatibility with community models, we do not intend to remove these redundant parameters.
 * The loss function value of Diffusion models has little relationship with actual effects. Therefore, we do not record loss function values during training. We recommend setting `--num_epochs` to a sufficiently large value, testing while training, and manually closing the training program after the effect converges.
-* `--use_gradient_checkpointing` is usually enabled unless GPU VRAM is sufficient; `--use_gradient_checkpointing_offload` is enabled as needed. See [`diffsynth.core.gradient`](../API_Reference/core/gradient.md) for details.
+* `--use_gradient_checkpointing` is usually enabled unless GPU VRAM is sufficient; `--use_gradient_checkpointing_offload` is enabled as needed. See [`diffsynth.core.gradient`](../API_Reference/core/gradient.md) for details.
+
+## Low VRAM Training
+
+If you want to complete LoRA model training on GPU with low vram, you can combine [Two-Stage Split Training](../Training/Split_Training.md) with `deepspeed_zero3_offload` training. First, split the preprocessing steps into the first stage and store the computed results onto the hard disk. Second, read these results from the disk and train the denoising model. By using `deepspeed_zero3_offload`, the training parameters and optimizer states are offloaded to the CPU or disk. We provide examples for some models, primarily by specifying the `deepspeed` configuration via `--config_file`.
+
+Please note that the `deepspeed_zero3_offload` mode is incompatible with PyTorch's native gradient checkpointing mechanism. To address this, we have adapted the `checkpointing` interface of `deepspeed`. Users need to fill the `activation_checkpointing` field in the `deepspeed` configuration to enable gradient checkpointing.
+
+Below is the script for low VRAM model training for the Qwen-Image model:
+
+```shell
+accelerate launch examples/qwen_image/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --max_pixels 1048576 \
+  --dataset_repeat 1 \
+  --model_id_with_origin_paths "Qwen/Qwen-Image:text_encoder/model*.safetensors,Qwen/Qwen-Image:vae/diffusion_pytorch_model.safetensors" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Qwen-Image_lora-splited-cache" \
+  --lora_base_model "dit" \
+  --lora_target_modules "to_q,to_k,to_v,add_q_proj,add_k_proj,add_v_proj,to_out.0,to_add_out,img_mlp.net.2,img_mod.1,txt_mlp.net.2,txt_mod.1" \
+  --lora_rank 32 \
+  --task "sft:data_process" \
+  --use_gradient_checkpointing \
+  --dataset_num_workers 8 \
+  --find_unused_parameters
+
+accelerate launch --config_file examples/qwen_image/model_training/special/low_vram_training/deepspeed_zero3_cpuoffload.yaml examples/qwen_image/model_training/train.py \
+  --dataset_base_path "./models/train/Qwen-Image_lora-splited-cache" \
+  --max_pixels 1048576 \
+  --dataset_repeat 50 \
+  --model_id_with_origin_paths "Qwen/Qwen-Image:transformer/diffusion_pytorch_model*.safetensors" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Qwen-Image_lora" \
+  --lora_base_model "dit" \
+  --lora_target_modules "to_q,to_k,to_v,add_q_proj,add_k_proj,add_v_proj,to_out.0,to_add_out,img_mlp.net.2,img_mod.1,txt_mlp.net.2,txt_mod.1" \
+  --lora_rank 32 \
+  --task "sft:train" \
+  --use_gradient_checkpointing \
+  --dataset_num_workers 8 \
+  --find_unused_parameters \
+  --initialize_model_on_cpu
+```
+
+The configurations for `accelerate` and `deepspeed` are as follows:
+
+```yaml
+compute_environment: LOCAL_MACHINE
+debug: true
+deepspeed_config:
+  deepspeed_config_file: examples/qwen_image/model_training/special/low_vram_training/ds_z3_cpuoffload.json
+  zero3_init_flag: true
+distributed_type: DEEPSPEED
+downcast_bf16: 'no'
+enable_cpu_affinity: false
+machine_rank: 0
+main_training_function: main
+num_machines: 1
+num_processes: 1
+rdzv_backend: static
+same_network: true
+tpu_env: []
+tpu_use_cluster: false
+tpu_use_sudo: false
+use_cpu: false
+```
+
+```json
+{
+    "fp16": {
+        "enabled": "auto",
+        "loss_scale": 0,
+        "loss_scale_window": 1000,
+        "initial_scale_power": 16,
+        "hysteresis": 2,
+        "min_loss_scale": 1
+    },
+    "bf16": {
+        "enabled": "auto"
+    },
+    "zero_optimization": {
+        "stage": 3,
+        "offload_optimizer": {
+            "device": "cpu",
+            "pin_memory": true
+        },
+        "offload_param": {
+            "device": "cpu",
+            "pin_memory": true
+        },
+        "overlap_comm": false,
+        "contiguous_gradients": true,
+        "sub_group_size": 1e9,
+        "reduce_bucket_size": 5e7,
+        "stage3_prefetch_bucket_size": 5e7,
+        "stage3_param_persistence_threshold": 1e5,
+        "stage3_max_live_parameters": 1e8,
+        "stage3_max_reuse_distance": 1e8,
+        "stage3_gather_16bit_weights_on_model_save": true
+    },
+    "activation_checkpointing": {
+        "partition_activations": false,
+        "cpu_checkpointing": false,
+        "contiguous_memory_optimization": false
+    },
+    "gradient_accumulation_steps": "auto",
+    "gradient_clipping": "auto",
+    "train_batch_size": "auto",
+    "train_micro_batch_size_per_gpu": "auto",
+    "wall_clock_breakdown": false
+}
+```

docs/en/Training/Direct_Distill.md

@@ -77,7 +77,7 @@ distill_qwen/image.jpg,"精致肖像，水下少女，蓝裙飘逸，发丝轻
 This sample dataset can be downloaded directly:
 
 ```shell
-modelscope download --dataset DiffSynth-Studio/example_image_dataset --local_dir ./data/example_image_dataset
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --local_dir ./data/diffsynth_example_dataset
 ```
 
 Then start LoRA distillation accelerated training:

docs/zh/Model_Details/Anima.md

@@ -133,7 +133,7 @@ Anima 系列模型统一通过 [`examples/anima/model_training/train.py`](https:
 我们构建了一个样例图像数据集，以方便您进行测试，通过以下命令可以下载这个数据集：
 
 ```shell
-modelscope download --dataset DiffSynth-Studio/example_image_dataset --local_dir ./data/example_image_dataset
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --local_dir ./data/diffsynth_example_dataset
 ```
 
 我们为每个模型编写了推荐的训练脚本，请参考前文"模型总览"中的表格。关于如何编写模型训练脚本，请参考[模型训练](../Pipeline_Usage/Model_Training.md)；更多高阶训练算法，请参考[训练框架详解](https://github.com/modelscope/DiffSynth-Studio/tree/main/docs/zh/Training/)。

docs/zh/Model_Details/FLUX.md

@@ -195,7 +195,7 @@ FLUX 系列模型统一通过 [`examples/flux/model_training/train.py`](https://
 我们构建了一个样例图像数据集，以方便您进行测试，通过以下命令可以下载这个数据集：
 
 ```shell
-modelscope download --dataset DiffSynth-Studio/example_image_dataset --local_dir ./data/example_image_dataset
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --local_dir ./data/diffsynth_example_dataset
 ```
 
 我们为每个模型编写了推荐的训练脚本，请参考前文"模型总览"中的表格。关于如何编写模型训练脚本，请参考[模型训练](../Pipeline_Usage/Model_Training.md)；更多高阶训练算法，请参考[训练框架详解](https://github.com/modelscope/DiffSynth-Studio/tree/main/docs/zh/Training/)。

docs/zh/Model_Details/FLUX2.md

@@ -145,7 +145,7 @@ FLUX.2 系列模型统一通过 [`examples/flux2/model_training/train.py`](https
 我们构建了一个样例图像数据集，以方便您进行测试，通过以下命令可以下载这个数据集：
 
 ```shell
-modelscope download --dataset DiffSynth-Studio/example_image_dataset --local_dir ./data/example_image_dataset
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --local_dir ./data/diffsynth_example_dataset
 ```
 
 我们为每个模型编写了推荐的训练脚本，请参考前文"模型总览"中的表格。关于如何编写模型训练脚本，请参考[模型训练](../Pipeline_Usage/Model_Training.md)；更多高阶训练算法，请参考[训练框架详解](https://github.com/modelscope/DiffSynth-Studio/tree/main/docs/zh/Training/)。

docs/zh/Model_Details/LTX-2.md

@@ -217,7 +217,7 @@ LTX-2 系列模型统一通过 [`examples/ltx2/model_training/train.py`](https:/
 我们构建了一个样例视频数据集，以方便您进行测试，通过以下命令可以下载这个数据集：
 
 ```shell
-modelscope download --dataset DiffSynth-Studio/example_video_dataset --local_dir ./data/example_video_dataset
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --local_dir ./data/diffsynth_example_dataset
 ```
 
 我们为每个模型编写了推荐的训练脚本，请参考前文"模型总览"中的表格。关于如何编写模型训练脚本，请参考[模型训练](../Pipeline_Usage/Model_Training.md)；更多高阶训练算法，请参考[训练框架详解](https://github.com/modelscope/DiffSynth-Studio/tree/main/docs/zh/Training/)。

docs/zh/Model_Details/Qwen-Image.md

@@ -199,7 +199,7 @@ Qwen-Image 系列模型统一通过 [`examples/qwen_image/model_training/train.p
 我们构建了一个样例图像数据集，以方便您进行测试，通过以下命令可以下载这个数据集：
 
 ```shell
-modelscope download --dataset DiffSynth-Studio/example_image_dataset --local_dir ./data/example_image_dataset
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --local_dir ./data/diffsynth_example_dataset
 ```
 
 我们为每个模型编写了推荐的训练脚本，请参考前文“模型总览”中的表格。关于如何编写模型训练脚本，请参考[模型训练](../Pipeline_Usage/Model_Training.md)；更多高阶训练算法，请参考[训练框架详解](https://github.com/modelscope/DiffSynth-Studio/tree/main/docs/zh/Training/)。

docs/zh/Model_Details/Wan.md

@@ -254,7 +254,7 @@ Wan 系列模型统一通过 [`examples/wanvideo/model_training/train.py`](https
 我们构建了一个样例视频数据集，以方便您进行测试，通过以下命令可以下载这个数据集：
 
 ```shell
-modelscope download --dataset DiffSynth-Studio/example_video_dataset --local_dir ./data/example_video_dataset
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --local_dir ./data/diffsynth_example_dataset
 ```
 
 我们为每个模型编写了推荐的训练脚本，请参考前文"模型总览"中的表格。关于如何编写模型训练脚本，请参考[模型训练](../Pipeline_Usage/Model_Training.md)；更多高阶训练算法，请参考[训练框架详解](https://github.com/modelscope/DiffSynth-Studio/tree/main/docs/zh/Training/)。

docs/zh/Model_Details/Z-Image.md

@@ -134,7 +134,7 @@ Z-Image 系列模型统一通过 [`examples/z_image/model_training/train.py`](ht
 我们构建了一个样例图像数据集，以方便您进行测试，通过以下命令可以下载这个数据集：
 
 ```shell
-modelscope download --dataset DiffSynth-Studio/example_image_dataset --local_dir ./data/example_image_dataset
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --local_dir ./data/diffsynth_example_dataset
 ```
 
 我们为每个模型编写了推荐的训练脚本，请参考前文"模型总览"中的表格。关于如何编写模型训练脚本，请参考[模型训练](../Pipeline_Usage/Model_Training.md)；更多高阶训练算法，请参考[训练框架详解](https://github.com/modelscope/DiffSynth-Studio/tree/main/docs/zh/Training/)。

docs/zh/Pipeline_Usage/Model_Training.md

@@ -69,28 +69,16 @@ image_2.jpg,"a cat"
 
 <details>
 
-<summary>样例图像数据集</summary>
+<summary>样例数据集</summary>
 
 > ```shell
-> modelscope download --dataset DiffSynth-Studio/example_image_dataset --local_dir ./data/example_image_dataset
+> modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --local_dir ./data/diffsynth_example_dataset
 > ```
 > 
 > 适用于 Qwen-Image、FLUX 等图像生成模型的训练。
 
 </details>
 
-<details>
-
-<summary>样例视频数据集</summary>
-
-> ```shell
-> modelscope download --dataset DiffSynth-Studio/example_video_dataset --local_dir ./data/example_video_dataset
-> ```
-> 
-> 适用于 Wan 等视频生成模型的训练。
-
-</details>
-
 ## 加载模型
 
 类似于[推理时的模型加载](../Pipeline_Usage/Model_Inference.md#加载模型)，我们支持多种方式配置模型路径，两种方式是可以混用的。
@@ -243,3 +231,116 @@ accelerate launch --config_file examples/qwen_image/model_training/full/accelera
 * 少数模型包含冗余参数，例如 Qwen-Image 的 DiT 部分最后一层的文本编码部分，在训练这些模型时，需设置 `--find_unused_parameters` 避免在多 GPU 训练中报错。出于对开源社区模型兼容性的考虑，我们不打算删除这些冗余参数。
 * Diffusion 模型的损失函数值与实际效果的关系不大，因此我们在训练过程中不会记录损失函数值。我们建议把 `--num_epochs` 设置为足够大的数值，边训边测，直至效果收敛后手动关闭训练程序。
 * `--use_gradient_checkpointing` 通常是开启的，除非 GPU 显存足够；`--use_gradient_checkpointing_offload` 则按需开启，详见 [`diffsynth.core.gradient`](../API_Reference/core/gradient.md)。
+
+## 低显存训练
+如果想在低显存显卡上完成 LoRA 模型训练，可以同时采用 [两阶段拆分训练](../Training/Split_Training.md) 和 `deepspeed_zero3_offload` 训练。 首先，将前处理过程拆分到第一阶段，将计算结果存储到硬盘中。其次，在第二阶段从硬盘中读取这些结果并进行去噪模型的训练，训练通过采用 `deepspeed_zero3_offload`，将训练参数和优化器状态 offload 到 cpu 或者 disk 上。我们为部分模型提供了样例，主要是通过 `--config_file` 指定 `deepspeed` 配置。
+
+需要注意的是，`deepspeed_zero3_offload` 模式与 `pytorch` 原生的梯度检查点机制不兼容，我们为此对 `deepspeed` 的`checkpointing` 接口做了适配。用户需要在 `deepspeed` 配置中填写 `activation_checkpointing` 字段以启用梯度检查点。
+
+以下为 Qwen-Image 模型的低显存模型训练脚本：
+```shell
+accelerate launch examples/qwen_image/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --max_pixels 1048576 \
+  --dataset_repeat 1 \
+  --model_id_with_origin_paths "Qwen/Qwen-Image:text_encoder/model*.safetensors,Qwen/Qwen-Image:vae/diffusion_pytorch_model.safetensors" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Qwen-Image_lora-splited-cache" \
+  --lora_base_model "dit" \
+  --lora_target_modules "to_q,to_k,to_v,add_q_proj,add_k_proj,add_v_proj,to_out.0,to_add_out,img_mlp.net.2,img_mod.1,txt_mlp.net.2,txt_mod.1" \
+  --lora_rank 32 \
+  --task "sft:data_process" \
+  --use_gradient_checkpointing \
+  --dataset_num_workers 8 \
+  --find_unused_parameters
+
+accelerate launch --config_file examples/qwen_image/model_training/special/low_vram_training/deepspeed_zero3_cpuoffload.yaml examples/qwen_image/model_training/train.py \
+  --dataset_base_path "./models/train/Qwen-Image_lora-splited-cache" \
+  --max_pixels 1048576 \
+  --dataset_repeat 50 \
+  --model_id_with_origin_paths "Qwen/Qwen-Image:transformer/diffusion_pytorch_model*.safetensors" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Qwen-Image_lora" \
+  --lora_base_model "dit" \
+  --lora_target_modules "to_q,to_k,to_v,add_q_proj,add_k_proj,add_v_proj,to_out.0,to_add_out,img_mlp.net.2,img_mod.1,txt_mlp.net.2,txt_mod.1" \
+  --lora_rank 32 \
+  --task "sft:train" \
+  --use_gradient_checkpointing \
+  --dataset_num_workers 8 \
+  --find_unused_parameters \
+  --initialize_model_on_cpu
+```
+
+其中，`accelerate` 和 `deepspeed` 的配置文件如下：
+
+```yaml
+compute_environment: LOCAL_MACHINE
+debug: true
+deepspeed_config:
+  deepspeed_config_file: examples/qwen_image/model_training/special/low_vram_training/ds_z3_cpuoffload.json
+  zero3_init_flag: true
+distributed_type: DEEPSPEED
+downcast_bf16: 'no'
+enable_cpu_affinity: false
+machine_rank: 0
+main_training_function: main
+num_machines: 1
+num_processes: 1
+rdzv_backend: static
+same_network: true
+tpu_env: []
+tpu_use_cluster: false
+tpu_use_sudo: false
+use_cpu: false
+```
+
+```json
+{
+    "fp16": {
+        "enabled": "auto",
+        "loss_scale": 0,
+        "loss_scale_window": 1000,
+        "initial_scale_power": 16,
+        "hysteresis": 2,
+        "min_loss_scale": 1
+    },
+    "bf16": {
+        "enabled": "auto"
+    },
+    "zero_optimization": {
+        "stage": 3,
+        "offload_optimizer": {
+            "device": "cpu",
+            "pin_memory": true
+        },
+        "offload_param": {
+            "device": "cpu",
+            "pin_memory": true
+        },
+        "overlap_comm": false,
+        "contiguous_gradients": true,
+        "sub_group_size": 1e9,
+        "reduce_bucket_size": 5e7,
+        "stage3_prefetch_bucket_size": 5e7,
+        "stage3_param_persistence_threshold": 1e5,
+        "stage3_max_live_parameters": 1e8,
+        "stage3_max_reuse_distance": 1e8,
+        "stage3_gather_16bit_weights_on_model_save": true
+    },
+    "activation_checkpointing": {
+        "partition_activations": false,
+        "cpu_checkpointing": false,
+        "contiguous_memory_optimization": false
+    },
+    "gradient_accumulation_steps": "auto",
+    "gradient_clipping": "auto",
+    "train_batch_size": "auto",
+    "train_micro_batch_size_per_gpu": "auto",
+    "wall_clock_breakdown": false
+}
+```

docs/zh/Training/Direct_Distill.md

@@ -77,7 +77,7 @@ distill_qwen/image.jpg,"精致肖像，水下少女，蓝裙飘逸，发丝轻
 这个样例数据集可以直接下载：
 
 ```shell
-modelscope download --dataset DiffSynth-Studio/example_image_dataset --local_dir ./data/example_image_dataset
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --local_dir ./data/diffsynth_example_dataset
 ```
 
 然后开始 LoRA 蒸馏加速训练：

examples/anima/model_training/full/anima-preview.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "anima/anima-preview/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/anima/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/anima/anima-preview \
-  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/anima/anima-preview/metadata.csv \
   --max_pixels 1048576 \
   --dataset_repeat 50 \
   --model_id_with_origin_paths "circlestone-labs/Anima:split_files/diffusion_models/anima-preview.safetensors,circlestone-labs/Anima:split_files/text_encoders/qwen_3_06b_base.safetensors,circlestone-labs/Anima:split_files/vae/qwen_image_vae.safetensors" \
@@ -11,4 +13,4 @@ accelerate launch examples/anima/model_training/train.py \
   --remove_prefix_in_ckpt "pipe.dit." \
   --output_path "./models/train/anima-preview_full" \
   --trainable_models "dit" \
-  --use_gradient_checkpointing
+  --use_gradient_checkpointing

examples/anima/model_training/lora/anima-preview.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "anima/anima-preview/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/anima/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/anima/anima-preview \
-  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/anima/anima-preview/metadata.csv \
   --max_pixels 1048576 \
   --dataset_repeat 50 \
   --model_id_with_origin_paths "circlestone-labs/Anima:split_files/diffusion_models/anima-preview.safetensors,circlestone-labs/Anima:split_files/text_encoders/qwen_3_06b_base.safetensors,circlestone-labs/Anima:split_files/vae/qwen_image_vae.safetensors" \
@@ -13,4 +15,4 @@ accelerate launch examples/anima/model_training/train.py \
   --lora_base_model "dit" \
   --lora_target_modules "" \
   --lora_rank 32 \
-  --use_gradient_checkpointing
+  --use_gradient_checkpointing

examples/flux/model_training/full/FLEX.2-preview.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux/FLEX.2-preview/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch --config_file examples/flux/model_training/full/accelerate_config.yaml examples/flux/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux/FLEX.2-preview \
-  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux/FLEX.2-preview/metadata.csv \
   --max_pixels 1048576 \
   --dataset_repeat 200 \
   --model_id_with_origin_paths "ostris/Flex.2-preview:Flex.2-preview.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors" \

examples/flux/model_training/full/FLUX.1-Kontext-dev.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux/FLUX.1-Kontext-dev/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch --config_file examples/flux/model_training/full/accelerate_config.yaml examples/flux/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux/FLUX.1-Kontext-dev \
-  --dataset_metadata_path data/example_image_dataset/metadata_kontext.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux/FLUX.1-Kontext-dev/metadata.csv \
   --data_file_keys "image,kontext_images" \
   --max_pixels 1048576 \
   --dataset_repeat 400 \

examples/flux/model_training/full/FLUX.1-Krea-dev.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux/FLUX.1-Krea-dev/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch --config_file examples/flux/model_training/full/accelerate_config.yaml examples/flux/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux/FLUX.1-Krea-dev \
-  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux/FLUX.1-Krea-dev/metadata.csv \
   --max_pixels 1048576 \
   --dataset_repeat 400 \
   --model_id_with_origin_paths "black-forest-labs/FLUX.1-Krea-dev:flux1-krea-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors" \

examples/flux/model_training/full/FLUX.1-dev-AttriCtrl.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux/FLUX.1-dev-AttriCtrl/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/flux/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux/FLUX.1-dev-AttriCtrl \
-  --dataset_metadata_path data/example_image_dataset/metadata_attrictrl.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux/FLUX.1-dev-AttriCtrl/metadata.csv \
   --data_file_keys "image" \
   --max_pixels 1048576 \
   --dataset_repeat 100 \

examples/flux/model_training/full/FLUX.1-dev-Controlnet-Inpainting-Beta.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux/FLUX.1-dev-Controlnet-Inpainting-Beta/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch --config_file examples/flux/model_training/full/accelerate_config.yaml examples/flux/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux/FLUX.1-dev-Controlnet-Inpainting-Beta \
-  --dataset_metadata_path data/example_image_dataset/metadata_controlnet_inpaint.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux/FLUX.1-dev-Controlnet-Inpainting-Beta/metadata.csv \
   --data_file_keys "image,controlnet_image,controlnet_inpaint_mask" \
   --max_pixels 1048576 \
   --dataset_repeat 400 \

examples/flux/model_training/full/FLUX.1-dev-Controlnet-Union-alpha.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux/FLUX.1-dev-Controlnet-Union-alpha/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch --config_file examples/flux/model_training/full/accelerate_config.yaml examples/flux/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux/FLUX.1-dev-Controlnet-Union-alpha \
-  --dataset_metadata_path data/example_image_dataset/metadata_controlnet_canny.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux/FLUX.1-dev-Controlnet-Union-alpha/metadata.csv \
   --data_file_keys "image,controlnet_image" \
   --max_pixels 1048576 \
   --dataset_repeat 400 \

examples/flux/model_training/full/FLUX.1-dev-Controlnet-Upscaler.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux/FLUX.1-dev-Controlnet-Upscaler/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch --config_file examples/flux/model_training/full/accelerate_config.yaml examples/flux/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux/FLUX.1-dev-Controlnet-Upscaler \
-  --dataset_metadata_path data/example_image_dataset/metadata_controlnet_upscale.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux/FLUX.1-dev-Controlnet-Upscaler/metadata.csv \
   --data_file_keys "image,controlnet_image" \
   --max_pixels 1048576 \
   --dataset_repeat 400 \

examples/flux/model_training/full/FLUX.1-dev-IP-Adapter.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux/FLUX.1-dev-IP-Adapter/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/flux/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux/FLUX.1-dev-IP-Adapter \
-  --dataset_metadata_path data/example_image_dataset/metadata_ipadapter.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux/FLUX.1-dev-IP-Adapter/metadata.csv \
   --data_file_keys "image,ipadapter_images" \
   --max_pixels 1048576 \
   --dataset_repeat 100 \

examples/flux/model_training/full/FLUX.1-dev-InfiniteYou.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux/FLUX.1-dev-InfiniteYou/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch --config_file examples/flux/model_training/full/accelerate_config.yaml examples/flux/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux/FLUX.1-dev-InfiniteYou \
-  --dataset_metadata_path data/example_image_dataset/metadata_infiniteyou.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux/FLUX.1-dev-InfiniteYou/metadata.csv \
   --data_file_keys "image,controlnet_image,infinityou_id_image" \
   --max_pixels 1048576 \
   --dataset_repeat 400 \

examples/flux/model_training/full/FLUX.1-dev-LoRA-Encoder.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux/FLUX.1-dev-LoRA-Encoder/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/flux/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux/FLUX.1-dev-LoRA-Encoder \
-  --dataset_metadata_path data/example_image_dataset/metadata_lora_encoder.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux/FLUX.1-dev-LoRA-Encoder/metadata.csv \
   --data_file_keys "image" \
   --max_pixels 1048576 \
   --dataset_repeat 100 \

examples/flux/model_training/full/FLUX.1-dev.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux/FLUX.1-dev/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch --config_file examples/flux/model_training/full/accelerate_config.yaml examples/flux/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux/FLUX.1-dev \
-  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux/FLUX.1-dev/metadata.csv \
   --max_pixels 1048576 \
   --dataset_repeat 400 \
   --model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors" \

examples/flux/model_training/full/Nexus-Gen.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux/Nexus-Gen/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch --config_file examples/flux/model_training/full/accelerate_config_zero2offload.yaml examples/flux/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux/Nexus-Gen \
-  --dataset_metadata_path data/example_image_dataset/metadata_nexusgen_edit.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux/Nexus-Gen/metadata.csv \
   --data_file_keys "image,nexus_gen_reference_image" \
   --max_pixels 262144 \
   --dataset_repeat 400 \

examples/flux/model_training/full/Step1X-Edit.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux/Step1X-Edit/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch --config_file examples/flux/model_training/full/accelerate_config.yaml examples/flux/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux/Step1X-Edit \
-  --dataset_metadata_path data/example_image_dataset/metadata_step1x.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux/Step1X-Edit/metadata.csv \
   --data_file_keys "image,step1x_reference_image" \
   --max_pixels 1048576 \
   --dataset_repeat 400 \

examples/flux/model_training/lora/FLEX.2-preview.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux/FLEX.2-preview/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/flux/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux/FLEX.2-preview \
-  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux/FLEX.2-preview/metadata.csv \
   --max_pixels 1048576 \
   --dataset_repeat 50 \
   --model_id_with_origin_paths "ostris/Flex.2-preview:Flex.2-preview.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors" \

examples/flux/model_training/lora/FLUX.1-Kontext-dev.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux/FLUX.1-Kontext-dev/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/flux/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux/FLUX.1-Kontext-dev \
-  --dataset_metadata_path data/example_image_dataset/metadata_kontext.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux/FLUX.1-Kontext-dev/metadata.csv \
   --data_file_keys "image,kontext_images" \
   --max_pixels 1048576 \
   --dataset_repeat 400 \

examples/flux/model_training/lora/FLUX.1-Krea-dev.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux/FLUX.1-Krea-dev/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/flux/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux/FLUX.1-Krea-dev \
-  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux/FLUX.1-Krea-dev/metadata.csv \
   --max_pixels 1048576 \
   --dataset_repeat 50 \
   --model_id_with_origin_paths "black-forest-labs/FLUX.1-Krea-dev:flux1-krea-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors" \

examples/flux/model_training/lora/FLUX.1-dev-AttriCtrl.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux/FLUX.1-dev-AttriCtrl/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/flux/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux/FLUX.1-dev-AttriCtrl \
-  --dataset_metadata_path data/example_image_dataset/metadata_attrictrl.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux/FLUX.1-dev-AttriCtrl/metadata.csv \
   --data_file_keys "image" \
   --max_pixels 1048576 \
   --dataset_repeat 100 \

examples/flux/model_training/lora/FLUX.1-dev-Controlnet-Inpainting-Beta.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux/FLUX.1-dev-Controlnet-Inpainting-Beta/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/flux/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux/FLUX.1-dev-Controlnet-Inpainting-Beta \
-  --dataset_metadata_path data/example_image_dataset/metadata_controlnet_inpaint.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux/FLUX.1-dev-Controlnet-Inpainting-Beta/metadata.csv \
   --data_file_keys "image,controlnet_image,controlnet_inpaint_mask" \
   --max_pixels 1048576 \
   --dataset_repeat 100 \

examples/flux/model_training/lora/FLUX.1-dev-Controlnet-Union-alpha.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux/FLUX.1-dev-Controlnet-Union-alpha/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/flux/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux/FLUX.1-dev-Controlnet-Union-alpha \
-  --dataset_metadata_path data/example_image_dataset/metadata_controlnet_canny.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux/FLUX.1-dev-Controlnet-Union-alpha/metadata.csv \
   --data_file_keys "image,controlnet_image" \
   --max_pixels 1048576 \
   --dataset_repeat 100 \

examples/flux/model_training/lora/FLUX.1-dev-Controlnet-Upscaler.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux/FLUX.1-dev-Controlnet-Upscaler/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/flux/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux/FLUX.1-dev-Controlnet-Upscaler \
-  --dataset_metadata_path data/example_image_dataset/metadata_controlnet_upscale.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux/FLUX.1-dev-Controlnet-Upscaler/metadata.csv \
   --data_file_keys "image,controlnet_image" \
   --max_pixels 1048576 \
   --dataset_repeat 100 \

examples/flux/model_training/lora/FLUX.1-dev-EliGen.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux/FLUX.1-dev-EliGen/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/flux/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux/FLUX.1-dev-EliGen \
-  --dataset_metadata_path data/example_image_dataset/metadata_eligen.json \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux/FLUX.1-dev-EliGen/metadata.json \
   --data_file_keys "image,eligen_entity_masks" \
   --max_pixels 1048576 \
   --dataset_repeat 50 \

examples/flux/model_training/lora/FLUX.1-dev-IP-Adapter.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux/FLUX.1-dev-IP-Adapter/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/flux/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux/FLUX.1-dev-IP-Adapter \
-  --dataset_metadata_path data/example_image_dataset/metadata_ipadapter.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux/FLUX.1-dev-IP-Adapter/metadata.csv \
   --data_file_keys "image,ipadapter_images" \
   --max_pixels 1048576 \
   --dataset_repeat 50 \

examples/flux/model_training/lora/FLUX.1-dev-InfiniteYou.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux/FLUX.1-dev-InfiniteYou/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/flux/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux/FLUX.1-dev-InfiniteYou \
-  --dataset_metadata_path data/example_image_dataset/metadata_infiniteyou.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux/FLUX.1-dev-InfiniteYou/metadata.csv \
   --data_file_keys "image,controlnet_image,infinityou_id_image" \
   --max_pixels 1048576 \
   --dataset_repeat 100 \

examples/flux/model_training/lora/FLUX.1-dev.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux/FLUX.1-dev/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/flux/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux/FLUX.1-dev \
-  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux/FLUX.1-dev/metadata.csv \
   --max_pixels 1048576 \
   --dataset_repeat 50 \
   --model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors" \

examples/flux/model_training/lora/Nexus-Gen.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux/Nexus-Gen/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/flux/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux/Nexus-Gen \
-  --dataset_metadata_path data/example_image_dataset/metadata_nexusgen_edit.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux/Nexus-Gen/metadata.csv \
   --data_file_keys "image,nexus_gen_reference_image" \
   --max_pixels 1048576 \
   --dataset_repeat 400 \

examples/flux/model_training/lora/Step1X-Edit.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux/Step1X-Edit/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/flux/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux/Step1X-Edit \
-  --dataset_metadata_path data/example_image_dataset/metadata_step1x.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux/Step1X-Edit/metadata.csv \
   --data_file_keys "image,step1x_reference_image" \
   --max_pixels 1048576 \
   --dataset_repeat 50 \

examples/flux/model_training/special/npu_training/FLUX.1-Kontext-dev-NPU.sh

@@ -1,9 +1,11 @@
 export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
 export CPU_AFFINITY_CONF=1
 
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux/FLUX.1-Kontext-dev/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch --config_file examples/flux/model_training/full/accelerate_config_zero2offload.yaml examples/flux/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux/FLUX.1-Kontext-dev \
-  --dataset_metadata_path data/example_image_dataset/metadata_kontext.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux/FLUX.1-Kontext-dev/metadata.csv \
   --data_file_keys "image,kontext_images" \
   --max_pixels 1048576 \
   --dataset_repeat 400 \

examples/flux/model_training/special/npu_training/FLUX.1-dev-NPU.sh

@@ -1,9 +1,11 @@
 export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
 export CPU_AFFINITY_CONF=1
 
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux/FLUX.1-dev/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch --config_file examples/flux/model_training/full/accelerate_config_zero2offload.yaml examples/flux/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux/FLUX.1-dev \
-  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux/FLUX.1-dev/metadata.csv \
   --max_pixels 1048576 \
   --dataset_repeat 400 \
   --model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors" \

examples/flux2/model_training/full/FLUX.2-klein-4B.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux2/FLUX.2-klein-4B/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/flux2/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-4B \
-  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-4B/metadata.csv \
   --max_pixels 1048576 \
   --dataset_repeat 50 \
   --model_id_with_origin_paths "black-forest-labs/FLUX.2-klein-4B:text_encoder/*.safetensors,black-forest-labs/FLUX.2-klein-4B:transformer/*.safetensors,black-forest-labs/FLUX.2-klein-4B:vae/diffusion_pytorch_model.safetensors" \
@@ -13,9 +15,12 @@ accelerate launch examples/flux2/model_training/train.py \
   --use_gradient_checkpointing
 
 # Edit
+
+# modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Edit-2511/*" --local_dir ./data/diffsynth_example_dataset
+
 # accelerate launch examples/flux2/model_training/train.py \
-#   --dataset_base_path data/example_image_dataset \
+#   --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511 \
-#   --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \
+#   --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511/metadata.json \
 #   --data_file_keys "image,edit_image" \
 #   --extra_inputs "edit_image" \
 #   --max_pixels 1048576 \

examples/flux2/model_training/full/FLUX.2-klein-9B.sh

@@ -1,7 +1,9 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux2/FLUX.2-klein-9B/*" --local_dir ./data/diffsynth_example_dataset
+
 # This script is tested on 8*A100
 accelerate launch --config_file examples/flux2/model_training/full/accelerate_config.yaml examples/flux2/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-9B \
-  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-9B/metadata.csv \
   --max_pixels 1048576 \
   --dataset_repeat 50 \
   --model_id_with_origin_paths "black-forest-labs/FLUX.2-klein-9B:text_encoder/*.safetensors,black-forest-labs/FLUX.2-klein-9B:transformer/*.safetensors,black-forest-labs/FLUX.2-klein-9B:vae/diffusion_pytorch_model.safetensors" \
@@ -14,9 +16,12 @@ accelerate launch --config_file examples/flux2/model_training/full/accelerate_co
   --use_gradient_checkpointing
 
 # Edit
+
+# modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Edit-2511/*" --local_dir ./data/diffsynth_example_dataset
+
 # accelerate launch --config_file examples/flux2/model_training/full/accelerate_config.yaml examples/flux2/model_training/train.py \
-#   --dataset_base_path data/example_image_dataset \
+#   --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511 \
-#   --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \
+#   --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511/metadata.json \
 #   --data_file_keys "image,edit_image" \
 #   --extra_inputs "edit_image" \
 #   --max_pixels 1048576 \

examples/flux2/model_training/full/FLUX.2-klein-base-4B.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux2/FLUX.2-klein-base-4B/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/flux2/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-base-4B \
-  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-base-4B/metadata.csv \
   --max_pixels 1048576 \
   --dataset_repeat 50 \
   --model_id_with_origin_paths "black-forest-labs/FLUX.2-klein-4B:text_encoder/*.safetensors,black-forest-labs/FLUX.2-klein-base-4B:transformer/*.safetensors,black-forest-labs/FLUX.2-klein-4B:vae/diffusion_pytorch_model.safetensors" \
@@ -13,9 +15,12 @@ accelerate launch examples/flux2/model_training/train.py \
   --use_gradient_checkpointing
 
 # Edit
+
+# modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Edit-2511/*" --local_dir ./data/diffsynth_example_dataset
+
 # accelerate launch examples/flux2/model_training/train.py \
-#   --dataset_base_path data/example_image_dataset \
+#   --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511 \
-#   --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \
+#   --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511/metadata.json \
 #   --data_file_keys "image,edit_image" \
 #   --extra_inputs "edit_image" \
 #   --max_pixels 1048576 \
@@ -27,4 +32,4 @@ accelerate launch examples/flux2/model_training/train.py \
 #   --remove_prefix_in_ckpt "pipe.dit." \
 #   --output_path "./models/train/FLUX.2-klein-base-4B_full" \
 #   --trainable_models "dit" \
-#   --use_gradient_checkpointing
+#   --use_gradient_checkpointing

examples/flux2/model_training/full/FLUX.2-klein-base-9B.sh

@@ -1,7 +1,9 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux2/FLUX.2-klein-base-9B/*" --local_dir ./data/diffsynth_example_dataset
+
 # This script is tested on 8*A100
 accelerate launch --config_file examples/flux2/model_training/full/accelerate_config.yaml examples/flux2/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-base-9B \
-  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-base-9B/metadata.csv \
   --max_pixels 1048576 \
   --dataset_repeat 50 \
   --model_id_with_origin_paths "black-forest-labs/FLUX.2-klein-9B:text_encoder/*.safetensors,black-forest-labs/FLUX.2-klein-base-9B:transformer/*.safetensors,black-forest-labs/FLUX.2-klein-9B:vae/diffusion_pytorch_model.safetensors" \
@@ -14,9 +16,12 @@ accelerate launch --config_file examples/flux2/model_training/full/accelerate_co
   --use_gradient_checkpointing
 
 # Edit
+
+# modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Edit-2511/*" --local_dir ./data/diffsynth_example_dataset
+
 # accelerate launch --config_file examples/flux2/model_training/full/accelerate_config.yaml examples/flux2/model_training/train.py \
-#   --dataset_base_path data/example_image_dataset \
+#   --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511 \
-#   --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \
+#   --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511/metadata.json \
 #   --data_file_keys "image,edit_image" \
 #   --extra_inputs "edit_image" \
 #   --max_pixels 1048576 \

examples/flux2/model_training/lora/FLUX.2-dev.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux2/FLUX.2-dev/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/flux2/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux2/FLUX.2-dev \
-  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux2/FLUX.2-dev/metadata.csv \
   --max_pixels 1048576 \
   --dataset_repeat 1 \
   --model_id_with_origin_paths "black-forest-labs/FLUX.2-dev:text_encoder/*.safetensors,black-forest-labs/FLUX.2-dev:vae/diffusion_pytorch_model.safetensors" \

examples/flux2/model_training/lora/FLUX.2-klein-4B.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux2/FLUX.2-klein-4B/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/flux2/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-4B \
-  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-4B/metadata.csv \
   --max_pixels 1048576 \
   --dataset_repeat 50 \
   --model_id_with_origin_paths "black-forest-labs/FLUX.2-klein-4B:text_encoder/*.safetensors,black-forest-labs/FLUX.2-klein-4B:transformer/*.safetensors,black-forest-labs/FLUX.2-klein-4B:vae/diffusion_pytorch_model.safetensors" \
@@ -15,9 +17,12 @@ accelerate launch examples/flux2/model_training/train.py \
   --use_gradient_checkpointing
 
 # Edit
+
+# modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Edit-2511/*" --local_dir ./data/diffsynth_example_dataset
+
 # accelerate launch examples/flux2/model_training/train.py \
-#   --dataset_base_path data/example_image_dataset \
+#   --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511 \
-#   --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \
+#   --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511/metadata.json \
 #   --data_file_keys "image,edit_image" \
 #   --extra_inputs "edit_image" \
 #   --max_pixels 1048576 \

examples/flux2/model_training/lora/FLUX.2-klein-9B.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux2/FLUX.2-klein-9B/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/flux2/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-9B \
-  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-9B/metadata.csv \
   --max_pixels 1048576 \
   --dataset_repeat 50 \
   --model_id_with_origin_paths "black-forest-labs/FLUX.2-klein-9B:text_encoder/*.safetensors,black-forest-labs/FLUX.2-klein-9B:transformer/*.safetensors,black-forest-labs/FLUX.2-klein-9B:vae/diffusion_pytorch_model.safetensors" \
@@ -15,9 +17,12 @@ accelerate launch examples/flux2/model_training/train.py \
   --use_gradient_checkpointing
 
 # Edit
+
+# modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Edit-2511/*" --local_dir ./data/diffsynth_example_dataset
+
 # accelerate launch examples/flux2/model_training/train.py \
-#   --dataset_base_path data/example_image_dataset \
+#   --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511 \
-#   --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \
+#   --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511/metadata.json \
 #   --data_file_keys "image,edit_image" \
 #   --extra_inputs "edit_image" \
 #   --max_pixels 1048576 \

examples/flux2/model_training/lora/FLUX.2-klein-base-4B.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux2/FLUX.2-klein-base-4B/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/flux2/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-base-4B \
-  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-base-4B/metadata.csv \
   --max_pixels 1048576 \
   --dataset_repeat 50 \
   --model_id_with_origin_paths "black-forest-labs/FLUX.2-klein-4B:text_encoder/*.safetensors,black-forest-labs/FLUX.2-klein-base-4B:transformer/*.safetensors,black-forest-labs/FLUX.2-klein-4B:vae/diffusion_pytorch_model.safetensors" \
@@ -15,9 +17,12 @@ accelerate launch examples/flux2/model_training/train.py \
   --use_gradient_checkpointing
 
 # Edit
+
+# modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Edit-2511/*" --local_dir ./data/diffsynth_example_dataset
+
 # accelerate launch examples/flux2/model_training/train.py \
-#   --dataset_base_path data/example_image_dataset \
+#   --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511 \
-#   --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \
+#   --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511/metadata.json \
 #   --data_file_keys "image,edit_image" \
 #   --extra_inputs "edit_image" \
 #   --max_pixels 1048576 \

examples/flux2/model_training/lora/FLUX.2-klein-base-9B.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux2/FLUX.2-klein-base-9B/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/flux2/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-base-9B \
-  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-base-9B/metadata.csv \
   --max_pixels 1048576 \
   --dataset_repeat 50 \
   --model_id_with_origin_paths "black-forest-labs/FLUX.2-klein-9B:text_encoder/*.safetensors,black-forest-labs/FLUX.2-klein-base-9B:transformer/*.safetensors,black-forest-labs/FLUX.2-klein-9B:vae/diffusion_pytorch_model.safetensors" \
@@ -15,9 +17,12 @@ accelerate launch examples/flux2/model_training/train.py \
   --use_gradient_checkpointing
 
 # Edit
+
+# modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Edit-2511/*" --local_dir ./data/diffsynth_example_dataset
+
 # accelerate launch examples/flux2/model_training/train.py \
-#   --dataset_base_path data/example_image_dataset \
+#   --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511 \
-#   --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \
+#   --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511/metadata.json \
 #   --data_file_keys "image,edit_image" \
 #   --extra_inputs "edit_image" \
 #   --max_pixels 1048576 \
@@ -31,4 +36,4 @@ accelerate launch examples/flux2/model_training/train.py \
 #   --lora_base_model "dit" \
 #   --lora_target_modules "to_q,to_k,to_v,to_out.0,add_q_proj,add_k_proj,add_v_proj,to_add_out,linear_in,linear_out,to_qkv_mlp_proj,single_transformer_blocks.0.attn.to_out,single_transformer_blocks.1.attn.to_out,single_transformer_blocks.2.attn.to_out,single_transformer_blocks.3.attn.to_out,single_transformer_blocks.4.attn.to_out,single_transformer_blocks.5.attn.to_out,single_transformer_blocks.6.attn.to_out,single_transformer_blocks.7.attn.to_out,single_transformer_blocks.8.attn.to_out,single_transformer_blocks.9.attn.to_out,single_transformer_blocks.10.attn.to_out,single_transformer_blocks.11.attn.to_out,single_transformer_blocks.12.attn.to_out,single_transformer_blocks.13.attn.to_out,single_transformer_blocks.14.attn.to_out,single_transformer_blocks.15.attn.to_out,single_transformer_blocks.16.attn.to_out,single_transformer_blocks.17.attn.to_out,single_transformer_blocks.18.attn.to_out,single_transformer_blocks.19.attn.to_out,single_transformer_blocks.20.attn.to_out,single_transformer_blocks.21.attn.to_out,single_transformer_blocks.22.attn.to_out,single_transformer_blocks.23.attn.to_out" \
 #   --lora_rank 32 \
-#   --use_gradient_checkpointing
+#   --use_gradient_checkpointing

examples/flux2/model_training/special/npu_training/FLUX.2-dev-Lora-NPU.sh

@@ -1,9 +1,11 @@
 export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
 export CPU_AFFINITY_CONF=1
 
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux2/FLUX.2-dev/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/flux2/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux2/FLUX.2-dev \
-  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux2/FLUX.2-dev/metadata.csv \
   --max_pixels 1048576 \
   --dataset_repeat 1 \
   --model_id_with_origin_paths "black-forest-labs/FLUX.2-dev:text_encoder/*.safetensors,black-forest-labs/FLUX.2-dev:vae/diffusion_pytorch_model.safetensors" \

examples/flux2/model_training/special/npu_training/FLUX.2-klein-9B-NPU.sh

@@ -2,9 +2,11 @@
 export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
 export CPU_AFFINITY_CONF=1
 
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux2/FLUX.2-klein-9B/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch --config_file examples/flux2/model_training/full/accelerate_config.yaml examples/flux2/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-9B \
-  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-9B/metadata.csv \
   --max_pixels 1048576 \
   --dataset_repeat 50 \
   --model_id_with_origin_paths "black-forest-labs/FLUX.2-klein-9B:text_encoder/*.safetensors,black-forest-labs/FLUX.2-klein-9B:transformer/*.safetensors,black-forest-labs/FLUX.2-klein-9B:vae/diffusion_pytorch_model.safetensors" \
@@ -17,9 +19,12 @@ accelerate launch --config_file examples/flux2/model_training/full/accelerate_co
   --use_gradient_checkpointing
 
 # Edit
+
+# modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Edit-2511/*" --local_dir ./data/diffsynth_example_dataset
+
 # accelerate launch --config_file examples/flux2/model_training/full/accelerate_config.yaml examples/flux2/model_training/train.py \
-#   --dataset_base_path data/example_image_dataset \
+#   --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511 \
-#   --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \
+#   --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511/metadata.json \
 #   --data_file_keys "image,edit_image" \
 #   --extra_inputs "edit_image" \
 #   --max_pixels 1048576 \

examples/ltx2/model_training/full/LTX-2-T2AV-splited.sh

@@ -1,7 +1,9 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "ltx2/LTX-2-T2AV-splited/*" --local_dir ./data/diffsynth_example_dataset
+
 # Splited Training
 accelerate launch examples/ltx2/model_training/train.py \
-  --dataset_base_path data/example_video_dataset/ltx2 \
+  --dataset_base_path data/diffsynth_example_dataset/ltx2/LTX-2-T2AV-splited \
-  --dataset_metadata_path data/example_video_dataset/ltx2_t2av.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/ltx2/LTX-2-T2AV-splited/metadata.csv \
   --data_file_keys "video,input_audio" \
   --extra_inputs "input_audio" \
   --height 512 \

examples/ltx2/model_training/full/LTX-2.3-I2AV-splited.sh

@@ -1,7 +1,9 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "ltx2/LTX-2.3-I2AV-splited/*" --local_dir ./data/diffsynth_example_dataset
+
 # Splited Training
 accelerate launch examples/ltx2/model_training/train.py \
-  --dataset_base_path data/example_video_dataset/ltx2 \
+  --dataset_base_path data/diffsynth_example_dataset/ltx2/LTX-2.3-I2AV-splited \
-  --dataset_metadata_path data/example_video_dataset/ltx2_t2av.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/ltx2/LTX-2.3-I2AV-splited/metadata.csv \
   --data_file_keys "video,input_audio" \
   --extra_inputs "input_audio,input_image" \
   --height 512 \

examples/ltx2/model_training/full/LTX-2.3-T2AV-splited.sh

@@ -1,7 +1,9 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "ltx2/LTX-2.3-T2AV-splited/*" --local_dir ./data/diffsynth_example_dataset
+
 # Splited Training
 accelerate launch examples/ltx2/model_training/train.py \
-  --dataset_base_path data/example_video_dataset/ltx2 \
+  --dataset_base_path data/diffsynth_example_dataset/ltx2/LTX-2.3-T2AV-splited \
-  --dataset_metadata_path data/example_video_dataset/ltx2_t2av.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/ltx2/LTX-2.3-T2AV-splited/metadata.csv \
   --data_file_keys "video,input_audio" \
   --extra_inputs "input_audio" \
   --height 512 \

examples/ltx2/model_training/lora/LTX-2-T2AV-IC-LoRA-splited.sh

@@ -1,7 +1,9 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "ltx2/LTX-2-T2AV-IC-LoRA-splited/*" --local_dir ./data/diffsynth_example_dataset
+
 # Splited Training
 accelerate launch examples/ltx2/model_training/train.py \
-  --dataset_base_path data/example_video_dataset/ltx2 \
+  --dataset_base_path data/diffsynth_example_dataset/ltx2/LTX-2-T2AV-IC-LoRA-splited \
-  --dataset_metadata_path data/example_video_dataset/ltx2_t2av_iclora.json \
+  --dataset_metadata_path data/diffsynth_example_dataset/ltx2/LTX-2-T2AV-IC-LoRA-splited/metadata.json \
   --data_file_keys "video,input_audio,in_context_videos" \
   --extra_inputs "input_audio,in_context_videos,in_context_downsample_factor,frame_rate" \
   --height 512 \

examples/ltx2/model_training/lora/LTX-2-T2AV-noaudio.sh

@@ -1,7 +1,9 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "ltx2/LTX-2-T2AV-noaudio/*" --local_dir ./data/diffsynth_example_dataset
+
 # single stage training
 # accelerate launch examples/ltx2/model_training/train.py \
-#   --dataset_base_path data/example_video_dataset/ltx2 \
+#   --dataset_base_path data/diffsynth_example_dataset/ltx2/LTX-2-T2AV-noaudio \
-#   --dataset_metadata_path data/example_video_dataset/ltx2_t2v.csv \
+#   --dataset_metadata_path data/diffsynth_example_dataset/ltx2/LTX-2-T2AV-noaudio/metadata.csv \
 #   --height 256 \
 #   --width 384 \
 #   --num_frames 25\
@@ -20,8 +22,8 @@
 
 # Splited Training
 accelerate launch examples/ltx2/model_training/train.py \
-  --dataset_base_path data/example_video_dataset/ltx2 \
+  --dataset_base_path data/diffsynth_example_dataset/ltx2/LTX-2-T2AV-noaudio \
-  --dataset_metadata_path data/example_video_dataset/ltx2_t2av.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/ltx2/LTX-2-T2AV-noaudio/metadata.csv \
   --height 512 \
   --width 768 \
   --num_frames 121\

examples/ltx2/model_training/lora/LTX-2-T2AV-splited.sh

@@ -1,7 +1,9 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "ltx2/LTX-2-T2AV-splited/*" --local_dir ./data/diffsynth_example_dataset
+
 # Single Stage Training not recommended for T2AV due to the large memory consumption. Please use the Splited Training instead.
 # accelerate launch examples/ltx2/model_training/train.py \
-#   --dataset_base_path data/example_video_dataset/ltx2 \
+#   --dataset_base_path data/diffsynth_example_dataset/ltx2/LTX-2-T2AV-splited \
-#   --dataset_metadata_path data/example_video_dataset/ltx2_t2av.csv \
+#   --dataset_metadata_path data/diffsynth_example_dataset/ltx2/LTX-2-T2AV-splited/metadata.csv \
 #   --data_file_keys "video,input_audio" \
 #   --extra_inputs "input_audio" \
 #   --height 256 \
@@ -21,8 +23,8 @@
 
 # Splited Training
 accelerate launch examples/ltx2/model_training/train.py \
-  --dataset_base_path data/example_video_dataset/ltx2 \
+  --dataset_base_path data/diffsynth_example_dataset/ltx2/LTX-2-T2AV-splited \
-  --dataset_metadata_path data/example_video_dataset/ltx2_t2av.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/ltx2/LTX-2-T2AV-splited/metadata.csv \
   --data_file_keys "video,input_audio" \
   --extra_inputs "input_audio" \
   --height 512 \

examples/ltx2/model_training/lora/LTX-2.3-I2AV-splited.sh

@@ -1,7 +1,9 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "ltx2/LTX-2.3-I2AV-splited/*" --local_dir ./data/diffsynth_example_dataset
+
 # Splited Training
 accelerate launch examples/ltx2/model_training/train.py \
-  --dataset_base_path data/example_video_dataset/ltx2 \
+  --dataset_base_path data/diffsynth_example_dataset/ltx2/LTX-2.3-I2AV-splited \
-  --dataset_metadata_path data/example_video_dataset/ltx2_t2av.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/ltx2/LTX-2.3-I2AV-splited/metadata.csv \
   --data_file_keys "video,input_audio" \
   --extra_inputs "input_audio,input_image" \
   --height 512 \

examples/ltx2/model_training/lora/LTX-2.3-T2AV-IC-LoRA-splited.sh

@@ -1,7 +1,9 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "ltx2/LTX-2.3-T2AV-IC-LoRA-splited/*" --local_dir ./data/diffsynth_example_dataset
+
 # Splited Training
 accelerate launch examples/ltx2/model_training/train.py \
-  --dataset_base_path data/example_video_dataset/ltx2 \
+  --dataset_base_path data/diffsynth_example_dataset/ltx2/LTX-2.3-T2AV-IC-LoRA-splited \
-  --dataset_metadata_path data/example_video_dataset/ltx2_t2av_iclora.json \
+  --dataset_metadata_path data/diffsynth_example_dataset/ltx2/LTX-2.3-T2AV-IC-LoRA-splited/metadata.json \
   --data_file_keys "video,input_audio,in_context_videos" \
   --extra_inputs "input_audio,in_context_videos,in_context_downsample_factor,frame_rate" \
   --height 512 \

examples/ltx2/model_training/lora/LTX-2.3-T2AV-splited.sh

@@ -1,7 +1,9 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "ltx2/LTX-2.3-T2AV-splited/*" --local_dir ./data/diffsynth_example_dataset
+
 # Splited Training
 accelerate launch examples/ltx2/model_training/train.py \
-  --dataset_base_path data/example_video_dataset/ltx2 \
+  --dataset_base_path data/diffsynth_example_dataset/ltx2/LTX-2.3-T2AV-splited \
-  --dataset_metadata_path data/example_video_dataset/ltx2_t2av.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/ltx2/LTX-2.3-T2AV-splited/metadata.csv \
   --data_file_keys "video,input_audio" \
   --extra_inputs "input_audio" \
   --height 512 \

examples/mova/model_training/full/MOVA-360P-I2AV.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "mova/MOVA-360P-I2AV/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch --config_file examples/wanvideo/model_training/full/accelerate_config_14B.yaml examples/mova/model_training/train.py \
-  --dataset_base_path data/example_video_dataset/ltx2 \
+  --dataset_base_path data/diffsynth_example_dataset/mova/MOVA-360P-I2AV \
-  --dataset_metadata_path data/example_video_dataset/ltx2_t2av.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/mova/MOVA-360P-I2AV/metadata.csv \
   --data_file_keys "video,input_audio" \
   --extra_inputs "input_audio,input_image" \
   --height 352 \
@@ -19,8 +21,8 @@ accelerate launch --config_file examples/wanvideo/model_training/full/accelerate
 # boundary corresponds to timesteps [900, 1000]
 
 accelerate launch --config_file examples/wanvideo/model_training/full/accelerate_config_14B.yaml examples/mova/model_training/train.py \
-  --dataset_base_path data/example_video_dataset/ltx2 \
+  --dataset_base_path data/diffsynth_example_dataset/mova/MOVA-360P-I2AV \
-  --dataset_metadata_path data/example_video_dataset/ltx2_t2av.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/mova/MOVA-360P-I2AV/metadata.csv \
   --data_file_keys "video,input_audio" \
   --extra_inputs "input_audio,input_image" \
   --height 352 \
@@ -36,4 +38,4 @@ accelerate launch --config_file examples/wanvideo/model_training/full/accelerate
   --max_timestep_boundary 1 \
   --min_timestep_boundary 0.358 \
   --use_gradient_checkpointing
-# boundary corresponds to timesteps [0, 900)
+# boundary corresponds to timesteps [0, 900)

examples/mova/model_training/full/MOVA-720P-I2AV.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "mova/MOVA-720P-I2AV/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch --config_file examples/wanvideo/model_training/full/accelerate_config_14B.yaml examples/mova/model_training/train.py \
-  --dataset_base_path data/example_video_dataset/ltx2 \
+  --dataset_base_path data/diffsynth_example_dataset/mova/MOVA-720P-I2AV \
-  --dataset_metadata_path data/example_video_dataset/ltx2_t2av.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/mova/MOVA-720P-I2AV/metadata.csv \
   --data_file_keys "video,input_audio" \
   --extra_inputs "input_audio,input_image" \
   --height 720 \
@@ -19,8 +21,8 @@ accelerate launch --config_file examples/wanvideo/model_training/full/accelerate
 # boundary corresponds to timesteps [900, 1000]
 
 accelerate launch --config_file examples/wanvideo/model_training/full/accelerate_config_14B.yaml examples/mova/model_training/train.py \
-  --dataset_base_path data/example_video_dataset/ltx2 \
+  --dataset_base_path data/diffsynth_example_dataset/mova/MOVA-720P-I2AV \
-  --dataset_metadata_path data/example_video_dataset/ltx2_t2av.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/mova/MOVA-720P-I2AV/metadata.csv \
   --data_file_keys "video,input_audio" \
   --extra_inputs "input_audio,input_image" \
   --height 720 \
@@ -36,4 +38,4 @@ accelerate launch --config_file examples/wanvideo/model_training/full/accelerate
   --max_timestep_boundary 1 \
   --min_timestep_boundary 0.358 \
   --use_gradient_checkpointing
-# boundary corresponds to timesteps [0, 900)
+# boundary corresponds to timesteps [0, 900)

examples/mova/model_training/lora/MOVA-360P-I2AV.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "mova/MOVA-360P-I2AV/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/mova/model_training/train.py \
-  --dataset_base_path data/example_video_dataset/ltx2 \
+  --dataset_base_path data/diffsynth_example_dataset/mova/MOVA-360P-I2AV \
-  --dataset_metadata_path data/example_video_dataset/ltx2_t2av.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/mova/MOVA-360P-I2AV/metadata.csv \
   --data_file_keys "video,input_audio" \
   --extra_inputs "input_audio,input_image" \
   --height 352 \
@@ -20,24 +22,24 @@ accelerate launch examples/mova/model_training/train.py \
   --use_gradient_checkpointing
 # boundary corresponds to timesteps [900, 1000]
 
-# accelerate launch examples/mova/model_training/train.py \
+accelerate launch examples/mova/model_training/train.py \
-#   --dataset_base_path data/example_video_dataset/ltx2 \
+  --dataset_base_path data/diffsynth_example_dataset/mova/MOVA-360P-I2AV \
-#   --dataset_metadata_path data/example_video_dataset/ltx2_t2av.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/mova/MOVA-360P-I2AV/metadata.csv \
-#   --data_file_keys "video,input_audio" \
+  --data_file_keys "video,input_audio" \
-#   --extra_inputs "input_audio,input_image" \
+  --extra_inputs "input_audio,input_image" \
-#   --height 352 \
+  --height 352 \
-#   --width 640 \
+  --width 640 \
-#   --num_frames 121 \
+  --num_frames 121 \
-#   --dataset_repeat 100 \
+  --dataset_repeat 100 \
-#   --model_id_with_origin_paths "openmoss/MOVA-360p:video_dit_2/diffusion_pytorch_model-*.safetensors,openmoss/MOVA-360p:audio_dit/diffusion_pytorch_model.safetensors,openmoss/MOVA-360p:dual_tower_bridge/diffusion_pytorch_model.safetensors,openmoss/MOVA-720p:audio_vae/diffusion_pytorch_model.safetensors,DiffSynth-Studio/Wan-Series-Converted-Safetensors:Wan2.1_VAE.safetensors,DiffSynth-Studio/Wan-Series-Converted-Safetensors:models_t5_umt5-xxl-enc-bf16.safetensors" \
+  --model_id_with_origin_paths "openmoss/MOVA-360p:video_dit_2/diffusion_pytorch_model-*.safetensors,openmoss/MOVA-360p:audio_dit/diffusion_pytorch_model.safetensors,openmoss/MOVA-360p:dual_tower_bridge/diffusion_pytorch_model.safetensors,openmoss/MOVA-720p:audio_vae/diffusion_pytorch_model.safetensors,DiffSynth-Studio/Wan-Series-Converted-Safetensors:Wan2.1_VAE.safetensors,DiffSynth-Studio/Wan-Series-Converted-Safetensors:models_t5_umt5-xxl-enc-bf16.safetensors" \
-#   --learning_rate 1e-4 \
+  --learning_rate 1e-4 \
-#   --num_epochs 5 \
+  --num_epochs 5 \
-#   --remove_prefix_in_ckpt "pipe.video_dit." \
+  --remove_prefix_in_ckpt "pipe.video_dit." \
-#   --output_path "./models/train/MOVA-360p-I2AV_low_noise_lora" \
+  --output_path "./models/train/MOVA-360p-I2AV_low_noise_lora" \
-#   --lora_base_model "video_dit" \
+  --lora_base_model "video_dit" \
-#   --lora_target_modules "q,k,v,o,ffn.0,ffn.2" \
+  --lora_target_modules "q,k,v,o,ffn.0,ffn.2" \
-#   --lora_rank 32 \
+  --lora_rank 32 \
-#   --max_timestep_boundary 1 \
+  --max_timestep_boundary 1 \
-#   --min_timestep_boundary 0.358 \
+  --min_timestep_boundary 0.358 \
-#   --use_gradient_checkpointing
+  --use_gradient_checkpointing
-# boundary corresponds to timesteps [0, 900)
+# boundary corresponds to timesteps [0, 900)

examples/mova/model_training/lora/MOVA-720P-I2AV.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "mova/MOVA-720P-I2AV/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/mova/model_training/train.py \
-  --dataset_base_path data/example_video_dataset/ltx2 \
+  --dataset_base_path data/diffsynth_example_dataset/mova/MOVA-720P-I2AV \
-  --dataset_metadata_path data/example_video_dataset/ltx2_t2av.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/mova/MOVA-720P-I2AV/metadata.csv \
   --data_file_keys "video,input_audio" \
   --extra_inputs "input_audio,input_image" \
   --height 720 \
@@ -21,8 +23,8 @@ accelerate launch examples/mova/model_training/train.py \
 # boundary corresponds to timesteps [900, 1000]
 
 accelerate launch examples/mova/model_training/train.py \
-  --dataset_base_path data/example_video_dataset/ltx2 \
+  --dataset_base_path data/diffsynth_example_dataset/mova/MOVA-720P-I2AV \
-  --dataset_metadata_path data/example_video_dataset/ltx2_t2av.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/mova/MOVA-720P-I2AV/metadata.csv \
   --data_file_keys "video,input_audio" \
   --extra_inputs "input_audio,input_image" \
   --height 720 \
@@ -40,4 +42,4 @@ accelerate launch examples/mova/model_training/train.py \
   --max_timestep_boundary 1 \
   --min_timestep_boundary 0.358 \
   --use_gradient_checkpointing
-# boundary corresponds to timesteps [0, 900)
+# boundary corresponds to timesteps [0, 900)

examples/mova/model_training/train.py

@@ -148,11 +148,11 @@ if __name__ == "__main__":
         max_pixels=args.max_pixels,
         height=args.height,
         width=args.width,
-        height_division_factor=model.pipe.height_division_factor,
+        height_division_factor=16,
-        width_division_factor=model.pipe.width_division_factor,
+        width_division_factor=16,
         num_frames=args.num_frames,
-        time_division_factor=model.pipe.time_division_factor,
+        time_division_factor=4,
-        time_division_remainder=model.pipe.time_division_remainder,
+        time_division_remainder=1,
         frame_rate=args.frame_rate,
         fix_frame_rate=True,
     )
@@ -166,8 +166,8 @@ if __name__ == "__main__":
             "input_audio":
                 ToAbsolutePath(args.dataset_base_path) >> LoadAudioWithTorchaudio(
                     num_frames=args.num_frames,
-                    time_division_factor=model.pipe.time_division_factor,
+                    time_division_factor=4,
-                    time_division_remainder=model.pipe.time_division_remainder,
+                    time_division_remainder=1,
                     frame_rate=args.frame_rate,
                 ),
             "in_context_videos":

examples/qwen_image/model_training/full/FireRed-Image-Edit-1.0.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/FireRed-Image-Edit-1.0/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch --config_file examples/qwen_image/model_training/full/accelerate_config_zero2offload.yaml examples/qwen_image/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/qwen_image/FireRed-Image-Edit-1.0 \
-  --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \
+  --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/FireRed-Image-Edit-1.0/metadata.json \
   --data_file_keys "image,edit_image" \
   --extra_inputs "edit_image" \
   --max_pixels 1048576 \

examples/qwen_image/model_training/full/FireRed-Image-Edit-1.1.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/FireRed-Image-Edit-1.1/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch --config_file examples/qwen_image/model_training/full/accelerate_config_zero2offload.yaml examples/qwen_image/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/qwen_image/FireRed-Image-Edit-1.1 \
-  --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \
+  --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/FireRed-Image-Edit-1.1/metadata.json \
   --data_file_keys "image,edit_image" \
   --extra_inputs "edit_image" \
   --max_pixels 1048576 \

examples/qwen_image/model_training/full/Qwen-Image-2512.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-2512/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch --config_file examples/qwen_image/model_training/full/accelerate_config_zero2offload.yaml examples/qwen_image/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-2512 \
-  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-2512/metadata.csv \
   --max_pixels 1048576 \
   --dataset_repeat 50 \
   --model_id_with_origin_paths "Qwen/Qwen-Image-2512:transformer/diffusion_pytorch_model*.safetensors,Qwen/Qwen-Image:text_encoder/model*.safetensors,Qwen/Qwen-Image:vae/diffusion_pytorch_model.safetensors" \

examples/qwen_image/model_training/full/Qwen-Image-Blockwise-ControlNet-Canny.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Blockwise-ControlNet-Canny/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/qwen_image/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Blockwise-ControlNet-Canny \
-  --dataset_metadata_path data/example_image_dataset/metadata_blockwise_controlnet_canny.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Blockwise-ControlNet-Canny/metadata.csv \
   --data_file_keys "image,blockwise_controlnet_image" \
   --max_pixels 1048576 \
   --dataset_repeat 400 \
@@ -21,8 +23,8 @@ accelerate launch examples/qwen_image/model_training/train.py \
 # python examples/qwen_image/model_training/scripts/Qwen-Image-Blockwise-ControlNet-Initialize.py
 
 # accelerate launch examples/qwen_image/model_training/train.py \
-#   --dataset_base_path data/example_image_dataset \
+#   --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Blockwise-ControlNet-Canny \
-#   --dataset_metadata_path data/example_image_dataset/metadata_blockwise_controlnet_canny.csv \
+#   --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Blockwise-ControlNet-Canny/metadata.csv \
 #   --data_file_keys "image,blockwise_controlnet_image" \
 #   --max_pixels 1048576 \
 #   --dataset_repeat 50 \
@@ -35,4 +37,4 @@ accelerate launch examples/qwen_image/model_training/train.py \
 #   --trainable_models "blockwise_controlnet" \
 #   --extra_inputs "blockwise_controlnet_image" \
 #   --use_gradient_checkpointing \
-#   --find_unused_parameters
+#   --find_unused_parameters

examples/qwen_image/model_training/full/Qwen-Image-Blockwise-ControlNet-Depth.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Blockwise-ControlNet-Depth/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/qwen_image/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Blockwise-ControlNet-Depth \
-  --dataset_metadata_path data/example_image_dataset/metadata_blockwise_controlnet_depth.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Blockwise-ControlNet-Depth/metadata.csv \
   --data_file_keys "image,blockwise_controlnet_image" \
   --max_pixels 1048576 \
   --dataset_repeat 400 \
@@ -21,8 +23,8 @@ accelerate launch examples/qwen_image/model_training/train.py \
 # python examples/qwen_image/model_training/scripts/Qwen-Image-Blockwise-ControlNet-Initialize.py
 
 # accelerate launch examples/qwen_image/model_training/train.py \
-#   --dataset_base_path data/example_image_dataset \
+#   --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Blockwise-ControlNet-Depth \
-#   --dataset_metadata_path data/example_image_dataset/metadata_blockwise_controlnet_depth.csv \
+#   --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Blockwise-ControlNet-Depth/metadata.csv \
 #   --data_file_keys "image,blockwise_controlnet_image" \
 #   --max_pixels 1048576 \
 #   --dataset_repeat 50 \
@@ -35,4 +37,4 @@ accelerate launch examples/qwen_image/model_training/train.py \
 #   --trainable_models "blockwise_controlnet" \
 #   --extra_inputs "blockwise_controlnet_image" \
 #   --use_gradient_checkpointing \
-#   --find_unused_parameters
+#   --find_unused_parameters

examples/qwen_image/model_training/full/Qwen-Image-Blockwise-ControlNet-Inpaint.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Blockwise-ControlNet-Inpaint/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch --config_file examples/qwen_image/model_training/full/accelerate_config.yaml examples/qwen_image/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Blockwise-ControlNet-Inpaint \
-  --dataset_metadata_path data/example_image_dataset/metadata_blockwise_controlnet_inpaint.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Blockwise-ControlNet-Inpaint/metadata.csv \
   --data_file_keys "image,blockwise_controlnet_image,blockwise_controlnet_inpaint_mask" \
   --max_pixels 1048576 \
   --dataset_repeat 400 \
@@ -21,8 +23,8 @@ accelerate launch --config_file examples/qwen_image/model_training/full/accelera
 # python examples/qwen_image/model_training/scripts/Qwen-Image-Blockwise-ControlNet-Inpaint-Initialize.py
 
 # accelerate launch --config_file examples/qwen_image/model_training/full/accelerate_config.yaml examples/qwen_image/model_training/train.py \
-#   --dataset_base_path data/example_image_dataset \
+#   --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Blockwise-ControlNet-Inpaint \
-#   --dataset_metadata_path data/example_image_dataset/metadata_blockwise_controlnet_inpaint.csv \
+#   --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Blockwise-ControlNet-Inpaint/metadata.csv \
 #   --data_file_keys "image,blockwise_controlnet_image,blockwise_controlnet_inpaint_mask" \
 #   --max_pixels 1048576 \
 #   --dataset_repeat 50 \

examples/qwen_image/model_training/full/Qwen-Image-Distill-Full.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Distill-Full/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch --config_file examples/qwen_image/model_training/full/accelerate_config_zero2offload.yaml examples/qwen_image/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Distill-Full \
-  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Distill-Full/metadata.csv \
   --max_pixels 1048576 \
   --dataset_repeat 50 \
   --model_id_with_origin_paths "DiffSynth-Studio/Qwen-Image-Distill-Full:diffusion_pytorch_model*.safetensors,Qwen/Qwen-Image:text_encoder/model*.safetensors,Qwen/Qwen-Image:vae/diffusion_pytorch_model.safetensors" \

examples/qwen_image/model_training/full/Qwen-Image-Edit-2509.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Edit-2509/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch --config_file examples/qwen_image/model_training/full/accelerate_config_zero2offload.yaml examples/qwen_image/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2509 \
-  --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \
+  --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2509/metadata.json \
   --data_file_keys "image,edit_image" \
   --extra_inputs "edit_image" \
   --max_pixels 1048576 \

examples/qwen_image/model_training/full/Qwen-Image-Edit-2511.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Edit-2511/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch --config_file examples/qwen_image/model_training/full/accelerate_config_zero2offload.yaml examples/qwen_image/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511 \
-  --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \
+  --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511/metadata.json \
   --data_file_keys "image,edit_image" \
   --extra_inputs "edit_image" \
   --max_pixels 1048576 \

examples/qwen_image/model_training/full/Qwen-Image-Edit.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Edit/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch --config_file examples/qwen_image/model_training/full/accelerate_config_zero2offload.yaml examples/qwen_image/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit \
-  --dataset_metadata_path data/example_image_dataset/metadata_edit.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit/metadata.csv \
   --data_file_keys "image,edit_image" \
   --extra_inputs "edit_image" \
   --max_pixels 1048576 \

examples/qwen_image/model_training/full/Qwen-Image-Layered-Control.sh

@@ -1,8 +1,8 @@
-# Example Dataset: https://modelscope.cn/datasets/DiffSynth-Studio/example_image_dataset/tree/master/layer
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Layered-Control/*" --local_dir ./data/diffsynth_example_dataset
 
 accelerate launch --config_file examples/qwen_image/model_training/full/accelerate_config_zero2offload.yaml examples/qwen_image/model_training/train.py \
-  --dataset_base_path data/example_image_dataset/layer \
+  --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Layered-Control \
-  --dataset_metadata_path data/example_image_dataset/layer/metadata_layered_control.json \
+  --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Layered-Control/metadata.json \
   --data_file_keys "image,layer_input_image" \
   --max_pixels 1048576 \
   --dataset_repeat 50 \

examples/qwen_image/model_training/full/Qwen-Image-Layered.sh

@@ -1,8 +1,8 @@
-# Example Dataset: https://modelscope.cn/datasets/DiffSynth-Studio/example_image_dataset/tree/master/layer
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Layered/*" --local_dir ./data/diffsynth_example_dataset
 
 accelerate launch --config_file examples/qwen_image/model_training/full/accelerate_config_zero2offload.yaml examples/qwen_image/model_training/train.py \
-  --dataset_base_path data/example_image_dataset/layer \
+  --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Layered \
-  --dataset_metadata_path data/example_image_dataset/layer/metadata_layered.json \
+  --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Layered/metadata.json \
   --data_file_keys "image,layer_input_image" \
   --max_pixels 1048576 \
   --dataset_repeat 50 \

examples/qwen_image/model_training/full/Qwen-Image.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch --config_file examples/qwen_image/model_training/full/accelerate_config_zero2offload.yaml examples/qwen_image/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image \
-  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image/metadata.csv \
   --max_pixels 1048576 \
   --dataset_repeat 50 \
   --model_id_with_origin_paths "Qwen/Qwen-Image:transformer/diffusion_pytorch_model*.safetensors,Qwen/Qwen-Image:text_encoder/model*.safetensors,Qwen/Qwen-Image:vae/diffusion_pytorch_model.safetensors" \

examples/qwen_image/model_training/lora/FireRed-Image-Edit-1.0.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/FireRed-Image-Edit-1.0/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/qwen_image/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/qwen_image/FireRed-Image-Edit-1.0 \
-  --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \
+  --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/FireRed-Image-Edit-1.0/metadata.json \
   --data_file_keys "image,edit_image" \
   --extra_inputs "edit_image" \
   --max_pixels 1048576 \

examples/qwen_image/model_training/lora/FireRed-Image-Edit-1.1.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/FireRed-Image-Edit-1.1/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/qwen_image/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/qwen_image/FireRed-Image-Edit-1.1 \
-  --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \
+  --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/FireRed-Image-Edit-1.1/metadata.json \
   --data_file_keys "image,edit_image" \
   --extra_inputs "edit_image" \
   --max_pixels 1048576 \

examples/qwen_image/model_training/lora/Qwen-Image-2512.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-2512/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/qwen_image/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-2512 \
-  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-2512/metadata.csv \
   --max_pixels 1048576 \
   --dataset_repeat 50 \
   --model_id_with_origin_paths "Qwen/Qwen-Image-2512:transformer/diffusion_pytorch_model*.safetensors,Qwen/Qwen-Image:text_encoder/model*.safetensors,Qwen/Qwen-Image:vae/diffusion_pytorch_model.safetensors" \

examples/qwen_image/model_training/lora/Qwen-Image-Blockwise-ControlNet-Canny.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Blockwise-ControlNet-Canny/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/qwen_image/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Blockwise-ControlNet-Canny \
-  --dataset_metadata_path data/example_image_dataset/metadata_blockwise_controlnet_canny.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Blockwise-ControlNet-Canny/metadata.csv \
   --data_file_keys "image,blockwise_controlnet_image" \
   --max_pixels 1048576 \
   --dataset_repeat 50 \

examples/qwen_image/model_training/lora/Qwen-Image-Blockwise-ControlNet-Depth.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Blockwise-ControlNet-Depth/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/qwen_image/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Blockwise-ControlNet-Depth \
-  --dataset_metadata_path data/example_image_dataset/metadata_blockwise_controlnet_depth.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Blockwise-ControlNet-Depth/metadata.csv \
   --data_file_keys "image,blockwise_controlnet_image" \
   --max_pixels 1048576 \
   --dataset_repeat 50 \

examples/qwen_image/model_training/lora/Qwen-Image-Blockwise-ControlNet-Inpaint.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Blockwise-ControlNet-Inpaint/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/qwen_image/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Blockwise-ControlNet-Inpaint \
-  --dataset_metadata_path data/example_image_dataset/metadata_blockwise_controlnet_inpaint.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Blockwise-ControlNet-Inpaint/metadata.csv \
   --data_file_keys "image,blockwise_controlnet_image,blockwise_controlnet_inpaint_mask" \
   --max_pixels 1048576 \
   --dataset_repeat 50 \

examples/qwen_image/model_training/lora/Qwen-Image-Distill-Full.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Distill-Full/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/qwen_image/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Distill-Full \
-  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Distill-Full/metadata.csv \
   --max_pixels 1048576 \
   --dataset_repeat 50 \
   --model_id_with_origin_paths "DiffSynth-Studio/Qwen-Image-Distill-Full:diffusion_pytorch_model*.safetensors,Qwen/Qwen-Image:text_encoder/model*.safetensors,Qwen/Qwen-Image:vae/diffusion_pytorch_model.safetensors" \

examples/qwen_image/model_training/lora/Qwen-Image-Distill-LoRA.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Distill-LoRA/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/qwen_image/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Distill-LoRA \
-  --dataset_metadata_path data/example_image_dataset/metadata_distill_qwen_image.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Distill-LoRA/metadata.csv \
   --data_file_keys "image" \
   --extra_inputs "seed,rand_device,num_inference_steps,cfg_scale" \
   --height 1328 \

examples/qwen_image/model_training/lora/Qwen-Image-Edit-2509.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Edit-2509/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/qwen_image/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2509 \
-  --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \
+  --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2509/metadata.json \
   --data_file_keys "image,edit_image" \
   --extra_inputs "edit_image" \
   --max_pixels 1048576 \

examples/qwen_image/model_training/lora/Qwen-Image-Edit-2511.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Edit-2511/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/qwen_image/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511 \
-  --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \
+  --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511/metadata.json \
   --data_file_keys "image,edit_image" \
   --extra_inputs "edit_image" \
   --max_pixels 1048576 \

examples/qwen_image/model_training/lora/Qwen-Image-Edit.sh

@@ -1,6 +1,8 @@
+modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Edit/*" --local_dir ./data/diffsynth_example_dataset
+
 accelerate launch examples/qwen_image/model_training/train.py \
-  --dataset_base_path data/example_image_dataset \
+  --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit \
-  --dataset_metadata_path data/example_image_dataset/metadata_edit.csv \
+  --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit/metadata.csv \
   --data_file_keys "image,edit_image" \
   --extra_inputs "edit_image" \
   --max_pixels 1048576 \