From 9a8982efb1d09f3708cc9df03d71171c635b16a5 Mon Sep 17 00:00:00 2001 From: Artiprocher Date: Mon, 11 Aug 2025 15:01:21 +0800 Subject: [PATCH 1/2] Qwen-Image-Distill-LoRA --- README.md | 3 +++ README_zh.md | 3 +++ examples/qwen_image/README.md | 4 ++++ examples/qwen_image/README_zh.md | 4 ++++ .../Qwen-Image-Distill-LoRA.py | 20 +++++++++++++++++++ 5 files changed, 34 insertions(+) create mode 100644 examples/qwen_image/model_inference/Qwen-Image-Distill-LoRA.py diff --git a/README.md b/README.md index 181a645..5e20ecd 100644 --- a/README.md +++ b/README.md @@ -363,6 +363,9 @@ https://github.com/Artiprocher/DiffSynth-Studio/assets/35051019/59fb2f7b-8de0-44 ## Update History + +- **August 11, 2025** We released another distilled acceleration model for Qwen-Image, [DiffSynth-Studio/Qwen-Image-Distill-LoRA](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-LoRA). It uses the same training process as [DiffSynth-Studio/Qwen-Image-Distill-Full](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-Full), but the model structure is changed to LoRA. This makes it work better with other open-source models. + - **August 7, 2025** We open-sourced the entity control LoRA of Qwen-Image, [DiffSynth-Studio/Qwen-Image-EliGen](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen). Qwen-Image-EliGen is able to achieve entity-level controlled text-to-image generation. See the [paper](https://arxiv.org/abs/2501.01097) for technical details. Training dataset: [EliGenTrainSet](https://www.modelscope.cn/datasets/DiffSynth-Studio/EliGenTrainSet). - **August 5, 2025** We open-sourced the distilled acceleration model of Qwen-Image, [DiffSynth-Studio/Qwen-Image-Distill-Full](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-Full), achieving approximately 5x speedup. diff --git a/README_zh.md b/README_zh.md index 7007a0e..8589a3a 100644 --- a/README_zh.md +++ b/README_zh.md @@ -380,6 +380,9 @@ https://github.com/Artiprocher/DiffSynth-Studio/assets/35051019/59fb2f7b-8de0-44 ## 更新历史 + +- **2025年8月11日** 我们开源了 Qwen-Image 的蒸馏加速模型 [DiffSynth-Studio/Qwen-Image-Distill-LoRA](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-LoRA)，沿用了与 [DiffSynth-Studio/Qwen-Image-Distill-Full](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-Full) 相同的训练流程，但模型结构修改为了 LoRA，因此能够更好地与其他开源生态模型兼容。 + - **2025年8月7日** 我们开源了 Qwen-Image 的实体控制 LoRA 模型 [DiffSynth-Studio/Qwen-Image-EliGen](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen)。Qwen-Image-EliGen 能够实现实体级可控的文生图。技术细节请参见[论文](https://arxiv.org/abs/2501.01097)。训练数据集：[EliGenTrainSet](https://www.modelscope.cn/datasets/DiffSynth-Studio/EliGenTrainSet)。 - **2025年8月5日** 我们开源了 Qwen-Image 的蒸馏加速模型 [DiffSynth-Studio/Qwen-Image-Distill-Full](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-Full)，实现了约 5 倍加速。 diff --git a/examples/qwen_image/README.md b/examples/qwen_image/README.md index d487bb7..bd5c11d 100644 --- a/examples/qwen_image/README.md +++ b/examples/qwen_image/README.md @@ -44,6 +44,7 @@ image.save("image.jpg") |-|-|-|-|-|-| |[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)| +|[DiffSynth-Studio/Qwen-Image-Distill-LoRA](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-LoRA)|[code](./model_inference/Qwen-Image-Distill-LoRA.py)|-|-|-|-| |[DiffSynth-Studio/Qwen-Image-EliGen](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen)|[code](./model_inference/Qwen-Image-EliGen.py)|-|-|[code](./model_training/lora/Qwen-Image-EliGen.sh)|[code](./model_training/validate_lora/Qwen-Image-EliGen.py)| ## Model Inference @@ -178,6 +179,9 @@ After enabling VRAM management, the framework will automatically choose a memory * GPUs that support FP8 operations (e.g., H200, etc.): Please install [Flash Attention 3](https://github.com/Dao-AILab/flash-attention). Otherwise, FP8 acceleration will only apply to Linear layers. * Faster inference but higher VRAM usage: Use [./accelerate/Qwen-Image-FP8.py](./accelerate/Qwen-Image-FP8.py) * Slightly slower inference but lower VRAM usage: Use [./accelerate/Qwen-Image-FP8-offload.py](./accelerate/Qwen-Image-FP8-offload.py) +* Distillation acceleration: We trained two distillation models for fast inference at `cfg_scale=1` and `num_inference_steps=15`. + * [DiffSynth-Studio/Qwen-Image-Distill-Full](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-Full): Full distillation version. Better image quality but lower LoRA compatibility. Use [./model_inference/Qwen-Image-Distill-Full.py](./model_inference/Qwen-Image-Distill-Full.py). + * [DiffSynth-Studio/Qwen-Image-Distill-LoRA](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-LoRA): LoRA distillation version. Slightly lower image quality but better LoRA compatibility. Use [./model_inference/Qwen-Image-Distill-LoRA.py](./model_inference/Qwen-Image-Distill-LoRA.py). diff --git a/examples/qwen_image/README_zh.md b/examples/qwen_image/README_zh.md index 1cc208c..6d7c8e6 100644 --- a/examples/qwen_image/README_zh.md +++ b/examples/qwen_image/README_zh.md @@ -44,6 +44,7 @@ image.save("image.jpg") |-|-|-|-|-|-| |[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)| +|[DiffSynth-Studio/Qwen-Image-Distill-LoRA](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-LoRA)|[code](./model_inference/Qwen-Image-Distill-LoRA.py)|-|-|-|-| |[DiffSynth-Studio/Qwen-Image-EliGen](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen)|[code](./model_inference/Qwen-Image-EliGen.py)|-|-|[code](./model_training/lora/Qwen-Image-EliGen.sh)|[code](./model_training/validate_lora/Qwen-Image-EliGen.py)| ## 模型推理 @@ -178,6 +179,9 @@ FP8 量化能够大幅度减少显存占用，但不会加速，部分模型在 * GPU 支持 FP8 运算（例如 H200 等）：请安装 [Flash Attention 3](https://github.com/Dao-AILab/flash-attention)，否则 FP8 加速仅对 Linear 层生效 * 更快的速度，但更大的显存：请使用 [./accelerate/Qwen-Image-FP8.py](./accelerate/Qwen-Image-FP8.py) * 稍慢的速度，但更小的显存：请使用 [./accelerate/Qwen-Image-FP8-offload.py](./accelerate/Qwen-Image-FP8-offload.py) +* 蒸馏加速：我们训练了两个蒸馏加速模型，可以在 `cfg_scale=1` 和 `num_inference_steps=15` 设置下进行快速推理 + * [DiffSynth-Studio/Qwen-Image-Distill-Full](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-Full)：全量蒸馏训练版本，更好的生成效果，稍差的 LoRA 兼容性，请使用 [./model_inference/Qwen-Image-Distill-Full.py](./model_inference/Qwen-Image-Distill-Full.py) + * [DiffSynth-Studio/Qwen-Image-Distill-LoRA](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-LoRA)：LoRA 蒸馏训练版本，稍差的生成效果，更好的 LoRA 兼容性，请使用 [./model_inference/Qwen-Image-Distill-LoRA.py](./model_inference/Qwen-Image-Distill-LoRA.py) diff --git a/examples/qwen_image/model_inference/Qwen-Image-Distill-LoRA.py b/examples/qwen_image/model_inference/Qwen-Image-Distill-LoRA.py new file mode 100644 index 0000000..3e89a99 --- /dev/null +++ b/examples/qwen_image/model_inference/Qwen-Image-Distill-LoRA.py @@ -0,0 +1,20 @@ +from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig +from modelscope import snapshot_download +import torch + +snapshot_download("DiffSynth-Studio/Qwen-Image-Distill-LoRA", local_dir="DiffSynth-Studio/Qwen-Image-Distill-LoRA") +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"), + 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/DiffSynth-Studio/Qwen-Image-Distill-LoRA/model.safetensors") + +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") \ No newline at end of file From 46f3c38c37f5da185c8851afbbcc0ae7ccc7b1db Mon Sep 17 00:00:00 2001 From: Artiprocher Date: Mon, 11 Aug 2025 15:04:21 +0800 Subject: [PATCH 2/2] Qwen-Image-Distill-LoRA --- README.md | 1 + README_zh.md | 1 + 2 files changed, 2 insertions(+) diff --git a/README.md b/README.md index 5e20ecd..41a8801 100644 --- a/README.md +++ b/README.md @@ -91,6 +91,7 @@ image.save("image.jpg") |-|-|-|-|-|-| |[Qwen/Qwen-Image](https://www.modelscope.cn/models/Qwen/Qwen-Image)|[code](./examples/qwen_image/model_inference/Qwen-Image.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image.sh)|[code](./examples/qwen_image/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](./examples/qwen_image/model_inference/Qwen-Image-Distill-Full.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image-Distill-Full.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image-Distill-Full.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Distill-Full.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Distill-Full.py)| +|[DiffSynth-Studio/Qwen-Image-Distill-LoRA](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-LoRA)|[code](./examples/qwen_image/model_inference/Qwen-Image-Distill-LoRA.py)|-|-|-|-| |[DiffSynth-Studio/Qwen-Image-EliGen](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen)|[code](./examples/qwen_image/model_inference/Qwen-Image-EliGen.py)|-|-|[code](./examples/qwen_image/model_training/lora/Qwen-Image-EliGen.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-EliGen.py)| diff --git a/README_zh.md b/README_zh.md index 8589a3a..005d76a 100644 --- a/README_zh.md +++ b/README_zh.md @@ -93,6 +93,7 @@ image.save("image.jpg") |-|-|-|-|-|-| |[Qwen/Qwen-Image](https://www.modelscope.cn/models/Qwen/Qwen-Image)|[code](./examples/qwen_image/model_inference/Qwen-Image.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image.sh)|[code](./examples/qwen_image/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](./examples/qwen_image/model_inference/Qwen-Image-Distill-Full.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image-Distill-Full.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image-Distill-Full.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Distill-Full.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Distill-Full.py)| +|[DiffSynth-Studio/Qwen-Image-Distill-LoRA](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-LoRA)|[code](./examples/qwen_image/model_inference/Qwen-Image-Distill-LoRA.py)|-|-|-|-| |[DiffSynth-Studio/Qwen-Image-EliGen](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen)|[code](./examples/qwen_image/model_inference/Qwen-Image-EliGen.py)|-|-|[code](./examples/qwen_image/model_training/lora/Qwen-Image-EliGen.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-EliGen.py)|