Merge branch 'main' into qwen-image-eligen

2026-03-18 22:08:13 +00:00 · 2025-08-06 15:57:13 +08:00
parent a3b67436a6 d0b9b25db7
commit 1f25ad416b
23 changed files with 220 additions and 29 deletions
--- a/examples/flux/README.md
+++ b/examples/flux/README.md
@@ -249,6 +249,7 @@ The script includes the following parameters:
  * `--width`: Width of the image or video. Leave `height` and `width` empty to enable dynamic resolution.
  * `--data_file_keys`: Data file keys in the metadata. Separate with commas.
  * `--dataset_repeat`: Number of times the dataset repeats per epoch.
+  * `--dataset_num_workers`: Number of workers for data loading.
 * Model
  * `--model_paths`: Paths to load models. In JSON format.
  * `--model_id_with_origin_paths`: Model ID with original paths, e.g., black-forest-labs/FLUX.1-dev:flux1-dev.safetensors. Separate with commas.
@@ -257,6 +258,8 @@ The script includes the following parameters:
  * `--num_epochs`: Number of epochs.
  * `--output_path`: Save path.
  * `--remove_prefix_in_ckpt`: Remove prefix in checkpoint.
+  * `--save_steps`: Number of checkpoint saving invervals. If None, checkpoints will be saved every epoch.
+  * `--find_unused_parameters`: Whether to find unused parameters in DDP.
 * Trainable Modules
  * `--trainable_models`: Models that can be trained, e.g., dit, vae, text_encoder.
  * `--lora_base_model`: Which model to add LoRA to.
--- a/examples/flux/README_zh.md
+++ b/examples/flux/README_zh.md
@@ -249,6 +249,7 @@ FLUX 系列模型训练通过统一的 [`./model_training/train.py`](./model_tra
  * `--width`: 图像或视频的宽度。将 `height` 和 `width` 留空以启用动态分辨率。
  * `--data_file_keys`: 元数据中的数据文件键。用逗号分隔。
  * `--dataset_repeat`: 每个 epoch 中数据集重复的次数。
+  * `--dataset_num_workers`: 每个 Dataloder 的进程数量。
 * 模型
  * `--model_paths`: 要加载的模型路径。JSON 格式。
  * `--model_id_with_origin_paths`: 带原始路径的模型 ID，例如 black-forest-labs/FLUX.1-dev:flux1-dev.safetensors。用逗号分隔。
@@ -257,6 +258,8 @@ FLUX 系列模型训练通过统一的 [`./model_training/train.py`](./model_tra
  * `--num_epochs`: 轮数（Epoch）。
  * `--output_path`: 保存路径。
  * `--remove_prefix_in_ckpt`: 在 ckpt 中移除前缀。
+  * `--save_steps`: 保存模型的间隔 step 数量，如果设置为 None ，则每个 epoch 保存一次
+  * `--find_unused_parameters`: DDP 训练中是否存在未使用的参数
 * 可训练模块
  * `--trainable_models`: 可训练的模型，例如 dit、vae、text_encoder。
  * `--lora_base_model`: LoRA 添加到哪个模型上。
--- a/examples/flux/model_training/train.py
+++ b/examples/flux/model_training/train.py
@@ -121,4 +121,7 @@ if __name__ == "__main__":
        dataset, model, model_logger, optimizer, scheduler,
        num_epochs=args.num_epochs,
        gradient_accumulation_steps=args.gradient_accumulation_steps,
+        save_steps=args.save_steps,
+        find_unused_parameters=args.find_unused_parameters,
+        num_workers=args.dataset_num_workers,
    )
--- a/examples/qwen_image/README.md
+++ b/examples/qwen_image/README.md
@@ -43,6 +43,7 @@ image.save("image.jpg")
 |Model ID|Inference|Full Training|Validation after Full Training|LoRA Training|Validation after LoRA Training|
 |-|-|-|-|-|-|
 |[Qwen/Qwen-Image](https://www.modelscope.cn/models/Qwen/Qwen-Image  )|[code](./model_inference/Qwen-Image.py)|[code](./model_training/full/Qwen-Image.sh)|[code](./model_training/validate_full/Qwen-Image.py)|[code](./model_training/lora/Qwen-Image.sh)|[code](./model_training/validate_lora/Qwen-Image.py)|
+|[DiffSynth-Studio/Qwen-Image-Distill-Full](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-Full)|[code](./model_inference/Qwen-Image-Distill-Full.py)|[code](./model_training/full/Qwen-Image-Distill-Full.sh)|[code](./model_training/validate_full/Qwen-Image-Distill-Full.py)|[code](./model_training/lora/Qwen-Image-Distill-Full.sh)|[code](./model_training/validate_lora/Qwen-Image-Distill-Full.py)|


 ## Model Inference
@@ -218,6 +219,7 @@ The script includes the following parameters:
  * `--width`: Width of image or video. Leave `height` and `width` empty to enable dynamic resolution.
  * `--data_file_keys`: Data file keys in metadata. Separate with commas.
  * `--dataset_repeat`: Number of times the dataset repeats per epoch.
+  * `--dataset_num_workers`: Number of workers for data loading.
 * Model
  * `--model_paths`: Model paths to load. In JSON format.
  * `--model_id_with_origin_paths`: Model ID with original paths, e.g., Qwen/Qwen-Image:transformer/diffusion_pytorch_model*.safetensors. Separate with commas.
@@ -227,6 +229,8 @@ The script includes the following parameters:
  * `--num_epochs`: Number of epochs.
  * `--output_path`: Save path.
  * `--remove_prefix_in_ckpt`: Remove prefix in checkpoint.
+  * `--save_steps`: Number of checkpoint saving invervals. If None, checkpoints will be saved every epoch.
+  * `--find_unused_parameters`: Whether to find unused parameters in DDP.
 * Trainable Modules
  * `--trainable_models`: Models to train, e.g., dit, vae, text_encoder.
  * `--lora_base_model`: Which model to add LoRA to.
--- a/examples/qwen_image/README_zh.md
+++ b/examples/qwen_image/README_zh.md
@@ -43,6 +43,7 @@ image.save("image.jpg")
 |模型 ID|推理|全量训练|全量训练后验证|LoRA 训练|LoRA 训练后验证|
 |-|-|-|-|-|-|
 |[Qwen/Qwen-Image](https://www.modelscope.cn/models/Qwen/Qwen-Image)|[code](./model_inference/Qwen-Image.py)|[code](./model_training/full/Qwen-Image.sh)|[code](./model_training/validate_full/Qwen-Image.py)|[code](./model_training/lora/Qwen-Image.sh)|[code](./model_training/validate_lora/Qwen-Image.py)|
+|[DiffSynth-Studio/Qwen-Image-Distill-Full](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-Full)|[code](./model_inference/Qwen-Image-Distill-Full.py)|[code](./model_training/full/Qwen-Image-Distill-Full.sh)|[code](./model_training/validate_full/Qwen-Image-Distill-Full.py)|[code](./model_training/lora/Qwen-Image-Distill-Full.sh)|[code](./model_training/validate_lora/Qwen-Image-Distill-Full.py)|


 ## 模型推理
@@ -218,6 +219,7 @@ Qwen-Image 系列模型训练通过统一的 [`./model_training/train.py`](./mod
  * `--width`: 图像或视频的宽度。将 `height` 和 `width` 留空以启用动态分辨率。
  * `--data_file_keys`: 元数据中的数据文件键。用逗号分隔。
  * `--dataset_repeat`: 每个 epoch 中数据集重复的次数。
+  * `--dataset_num_workers`: 每个 Dataloder 的进程数量。
 * 模型
  * `--model_paths`: 要加载的模型路径。JSON 格式。
  * `--model_id_with_origin_paths`: 带原始路径的模型 ID，例如 Qwen/Qwen-Image:transformer/diffusion_pytorch_model*.safetensors。用逗号分隔。
@@ -227,6 +229,8 @@ Qwen-Image 系列模型训练通过统一的 [`./model_training/train.py`](./mod
  * `--num_epochs`: 轮数（Epoch）。
  * `--output_path`: 保存路径。
  * `--remove_prefix_in_ckpt`: 在 ckpt 中移除前缀。
+  * `--save_steps`: 保存模型的间隔 step 数量，如果设置为 None ，则每个 epoch 保存一次
+  * `--find_unused_parameters`: DDP 训练中是否存在未使用的参数
 * 可训练模块
  * `--trainable_models`: 可训练的模型，例如 dit、vae、text_encoder。
  * `--lora_base_model`: LoRA 添加到哪个模型上。
--- a/examples/qwen_image/model_inference/Qwen-Image-Distill-Full.py
+++ b/examples/qwen_image/model_inference/Qwen-Image-Distill-Full.py
@@ -0,0 +1,17 @@
+from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
+import torch
+
+
+pipe = QwenImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="DiffSynth-Studio/Qwen-Image-Distill-Full", origin_file_pattern="diffusion_pytorch_model*.safetensors"),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors"),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
+    ],
+    tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
+)
+prompt = "精致肖像，水下少女，蓝裙飘逸，发丝轻扬，光影透澈，气泡环绕，面容恬静，细节精致，梦幻唯美。"
+image = pipe(prompt, seed=0, num_inference_steps=15, cfg_scale=1)
+image.save("image.jpg")
--- a/examples/qwen_image/model_inference_lor_vram/Qwen-Image-Distill-Full.py
+++ b/examples/qwen_image/model_inference_lor_vram/Qwen-Image-Distill-Full.py
@@ -0,0 +1,18 @@
+from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
+import torch
+
+
+pipe = QwenImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="DiffSynth-Studio/Qwen-Image-Distill-Full", origin_file_pattern="diffusion_pytorch_model*.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
+    ],
+    tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
+)
+pipe.enable_vram_management()
+prompt = "精致肖像，水下少女，蓝裙飘逸，发丝轻扬，光影透澈，气泡环绕，面容恬静，细节精致，梦幻唯美。"
+image = pipe(prompt, seed=0, num_inference_steps=15, cfg_scale=1)
+image.save("image.jpg")
--- a/examples/qwen_image/model_training/full/Qwen-Image-Distill-Full.sh
+++ b/examples/qwen_image/model_training/full/Qwen-Image-Distill-Full.sh
@@ -0,0 +1,12 @@
+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_metadata_path data/example_image_dataset/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" \
+  --learning_rate 1e-5 \
+  --num_epochs 2 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Qwen-Image-Distill-Full_full" \
+  --trainable_models "dit" \
+  --use_gradient_checkpointing
--- a/examples/qwen_image/model_training/lora/Qwen-Image-Distill-Full.sh
+++ b/examples/qwen_image/model_training/lora/Qwen-Image-Distill-Full.sh
@@ -0,0 +1,15 @@
+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 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" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Qwen-Image-Distill-Full_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 \
+  --align_to_opensource_format \
+  --use_gradient_checkpointing
--- a/examples/qwen_image/model_training/lora/Qwen-Image.sh
+++ b/examples/qwen_image/model_training/lora/Qwen-Image.sh
@@ -12,4 +12,6 @@ accelerate launch examples/qwen_image/model_training/train.py \
  --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 \
  --align_to_opensource_format \
-  --use_gradient_checkpointing
+  --use_gradient_checkpointing \
+  --dataset_num_workers 8 \
+  --find_unused_parameters
--- a/examples/qwen_image/model_training/train.py
+++ b/examples/qwen_image/model_training/train.py
@@ -1,6 +1,7 @@
 import torch, os, json
 from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
 from diffsynth.trainers.utils import DiffusionTrainingModule, ImageDataset, ModelLogger, launch_training_task, qwen_image_parser
+from diffsynth.models.lora import QwenImageLoRAConverter
 os.environ["TOKENIZERS_PARALLELISM"] = "false"


@@ -29,7 +30,7 @@ class QwenImageTrainingModule(DiffusionTrainingModule):
            self.pipe = QwenImagePipeline.from_pretrained(torch_dtype=torch.bfloat16, device="cpu", model_configs=model_configs, tokenizer_config=ModelConfig(tokenizer_path))
        else:
            self.pipe = QwenImagePipeline.from_pretrained(torch_dtype=torch.bfloat16, device="cpu", model_configs=model_configs)
-        
+
        # Reset training scheduler (do it in each training step)
        self.pipe.scheduler.set_timesteps(1000, training=True)
        
@@ -49,7 +50,7 @@ class QwenImageTrainingModule(DiffusionTrainingModule):
        self.use_gradient_checkpointing = use_gradient_checkpointing
        self.use_gradient_checkpointing_offload = use_gradient_checkpointing_offload
        self.extra_inputs = extra_inputs.split(",") if extra_inputs is not None else []
-        
+
    
    def forward_preprocess(self, data):
        # CFG-sensitive parameters
@@ -108,6 +109,7 @@ if __name__ == "__main__":
    model_logger = ModelLogger(
        args.output_path,
        remove_prefix_in_ckpt=args.remove_prefix_in_ckpt,
+        state_dict_converter=QwenImageLoRAConverter.align_to_opensource_format if args.align_to_opensource_format else lambda x:x,
    )
    optimizer = torch.optim.AdamW(model.trainable_modules(), lr=args.learning_rate)
    scheduler = torch.optim.lr_scheduler.ConstantLR(optimizer)
@@ -115,4 +117,7 @@ if __name__ == "__main__":
        dataset, model, model_logger, optimizer, scheduler,
        num_epochs=args.num_epochs,
        gradient_accumulation_steps=args.gradient_accumulation_steps,
+        save_steps=args.save_steps,
+        find_unused_parameters=args.find_unused_parameters,
+        num_workers=args.dataset_num_workers,
    )
--- a/examples/qwen_image/model_training/validate_full/Qwen-Image-Distill-Full.py
+++ b/examples/qwen_image/model_training/validate_full/Qwen-Image-Distill-Full.py
@@ -0,0 +1,20 @@
+from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
+from diffsynth import load_state_dict
+import torch
+
+
+pipe = QwenImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="DiffSynth-Studio/Qwen-Image-Distill-Full", origin_file_pattern="diffusion_pytorch_model*.safetensors"),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors"),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
+    ],
+    tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
+)
+state_dict = load_state_dict("models/train/Qwen-Image-Distill-Full_full/epoch-1.safetensors")
+pipe.dit.load_state_dict(state_dict)
+prompt = "a dog"
+image = pipe(prompt, seed=0, num_inference_steps=15, cfg_scale=1)
+image.save("image.jpg")
--- a/examples/qwen_image/model_training/validate_full/Qwen-Image.py
+++ b/examples/qwen_image/model_training/validate_full/Qwen-Image.py
@@ -7,9 +7,9 @@ pipe = QwenImagePipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
-        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
-        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
-        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors"),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
    ],
    tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
 )
--- a/examples/qwen_image/model_training/validate_lora/Qwen-Image-Distill-Full.py
+++ b/examples/qwen_image/model_training/validate_lora/Qwen-Image-Distill-Full.py
@@ -0,0 +1,18 @@
+from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
+import torch
+
+
+pipe = QwenImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="DiffSynth-Studio/Qwen-Image-Distill-Full", origin_file_pattern="diffusion_pytorch_model*.safetensors"),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors"),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
+    ],
+    tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
+)
+pipe.load_lora(pipe.dit, "models/train/Qwen-Image-Distill-Full_lora/epoch-4.safetensors")
+prompt = "a dog"
+image = pipe(prompt, seed=0, num_inference_steps=15, cfg_scale=1)
+image.save("image.jpg")
--- a/examples/qwen_image/model_training/validate_lora/Qwen-Image.py
+++ b/examples/qwen_image/model_training/validate_lora/Qwen-Image.py
@@ -6,9 +6,9 @@ pipe = QwenImagePipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
-        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
-        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
-        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors"),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
    ],
    tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
 )
--- a/examples/wanvideo/README.md
+++ b/examples/wanvideo/README.md
@@ -280,6 +280,7 @@ The script includes the following parameters:
  * `--num_frames`: Number of frames per video. Frames are sampled from the video prefix.
  * `--data_file_keys`: Data file keys in the metadata. Comma-separated.
  * `--dataset_repeat`: Number of times to repeat the dataset per epoch.
+  * `--dataset_num_workers`: Number of workers for data loading.
 * Models
  * `--model_paths`: Paths to load models. In JSON format.
  * `--model_id_with_origin_paths`: Model ID with origin paths, e.g., Wan-AI/Wan2.1-T2V-1.3B:diffusion_pytorch_model*.safetensors. Comma-separated.
@@ -290,6 +291,8 @@ The script includes the following parameters:
  * `--num_epochs`: Number of epochs.
  * `--output_path`: Output save path.
  * `--remove_prefix_in_ckpt`: Remove prefix in ckpt.
+  * `--save_steps`: Number of checkpoint saving invervals. If None, checkpoints will be saved every epoch.
+  * `--find_unused_parameters`: Whether to find unused parameters in DDP.
 * Trainable Modules
  * `--trainable_models`: Models to train, e.g., dit, vae, text_encoder.
  * `--lora_base_model`: Which model LoRA is added to.
--- a/examples/wanvideo/README_zh.md
+++ b/examples/wanvideo/README_zh.md
@@ -282,6 +282,7 @@ Wan 系列模型训练通过统一的 [`./model_training/train.py`](./model_trai
  * `--num_frames`: 每个视频中的帧数。帧从视频前缀中采样。
  * `--data_file_keys`: 元数据中的数据文件键。用逗号分隔。
  * `--dataset_repeat`: 每个 epoch 中数据集重复的次数。
+  * `--dataset_num_workers`: 每个 Dataloder 的进程数量。
 * 模型
  * `--model_paths`: 要加载的模型路径。JSON 格式。
  * `--model_id_with_origin_paths`: 带原始路径的模型 ID，例如 Wan-AI/Wan2.1-T2V-1.3B:diffusion_pytorch_model*.safetensors。用逗号分隔。
@@ -292,6 +293,8 @@ Wan 系列模型训练通过统一的 [`./model_training/train.py`](./model_trai
  * `--num_epochs`: 轮数（Epoch）。
  * `--output_path`: 保存路径。
  * `--remove_prefix_in_ckpt`: 在 ckpt 中移除前缀。
+  * `--save_steps`: 保存模型的间隔 step 数量，如果设置为 None ，则每个 epoch 保存一次
+  * `--find_unused_parameters`: DDP 训练中是否存在未使用的参数
 * 可训练模块
  * `--trainable_models`: 可训练的模型，例如 dit、vae、text_encoder。
  * `--lora_base_model`: LoRA 添加到哪个模型上。
--- a/examples/wanvideo/model_training/train.py
+++ b/examples/wanvideo/model_training/train.py
@@ -127,4 +127,7 @@ if __name__ == "__main__":
        dataset, model, model_logger, optimizer, scheduler,
        num_epochs=args.num_epochs,
        gradient_accumulation_steps=args.gradient_accumulation_steps,
+        save_steps=args.save_steps,
+        find_unused_parameters=args.find_unused_parameters,
+        num_workers=args.dataset_num_workers,
    )