From ee73a29885354ec2218b81dd50db260297ae3297 Mon Sep 17 00:00:00 2001 From: mi804 <1576993271@qq.com> Date: Tue, 24 Feb 2026 15:19:16 +0800 Subject: [PATCH] qwen_image layercontrol v2 --- README.md | 3 ++ README_zh.md | 3 ++ diffsynth/pipelines/qwen_image.py | 6 ++- docs/en/Model_Details/Qwen-Image.md | 1 + docs/zh/Model_Details/Qwen-Image.md | 1 + .../Qwen-Image-Layered-Control-V2.py | 43 +++++++++++++++ .../Qwen-Image-Layered-Control-V2.py | 54 +++++++++++++++++++ .../lora/Qwen-Image-Layered-Control-V2.sh | 20 +++++++ examples/qwen_image/model_training/train.py | 6 ++- .../Qwen-Image-Layered-Control-V2.py | 37 +++++++++++++ 10 files changed, 171 insertions(+), 3 deletions(-) create mode 100644 examples/qwen_image/model_inference/Qwen-Image-Layered-Control-V2.py create mode 100644 examples/qwen_image/model_inference_low_vram/Qwen-Image-Layered-Control-V2.py create mode 100644 examples/qwen_image/model_training/lora/Qwen-Image-Layered-Control-V2.sh create mode 100644 examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered-Control-V2.py diff --git a/README.md b/README.md index 2bc45e6..fc051da 100644 --- a/README.md +++ b/README.md @@ -32,6 +32,8 @@ We believe that a well-developed open-source code framework can lower the thresh > DiffSynth-Studio has undergone major version updates, and some old features are no longer maintained. If you need to use old features, please switch to the [last historical version](https://github.com/modelscope/DiffSynth-Studio/tree/afd101f3452c9ecae0c87b79adfa2e22d65ffdc3) before the major version update. > Currently, the development personnel of this project are limited, with most of the work handled by [Artiprocher](https://github.com/Artiprocher). Therefore, the progress of new feature development will be relatively slow, and the speed of responding to and resolving issues is limited. We apologize for this and ask developers to understand. +- **February 24, 2026**: We released the [DiffSynth-Studio/Qwen-Image-Layered-Control-V2](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Layered-Control-V2) model, which is an updated version of Qwen-Image-Layered-Control. In addition to the originally supported text-guided functionality, it adds brush-controlled layer separation capabilities. + - **February 10, 2026** Added inference support for the LTX-2 audio-video generation model. See the documentation for details. Support for model training will be implemented in the future. - **February 2, 2026** The first document of the Research Tutorial series is now available, guiding you through training a small 0.1B text-to-image model from scratch. For details, see the [documentation](/docs/en/Research_Tutorial/train_from_scratch.md) and [model](https://modelscope.cn/models/DiffSynth-Studio/AAAMyModel). We hope DiffSynth-Studio can evolve into a more powerful training framework for Diffusion models. @@ -424,6 +426,7 @@ Example code for Qwen-Image is available at: [/examples/qwen_image/](/examples/q |[lightx2v/Qwen-Image-Edit-2511-Lightning](https://modelscope.cn/models/lightx2v/Qwen-Image-Edit-2511-Lightning)|[code](/examples/qwen_image/model_inference/Qwen-Image-Edit-2511-Lightning.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2511-Lightning.py)|-|-|-|-| |[Qwen/Qwen-Image-Layered](https://www.modelscope.cn/models/Qwen/Qwen-Image-Layered)|[code](/examples/qwen_image/model_inference/Qwen-Image-Layered.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Layered.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Layered.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Layered.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Layered.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered.py)| |[DiffSynth-Studio/Qwen-Image-Layered-Control](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Layered-Control)|[code](/examples/qwen_image/model_inference/Qwen-Image-Layered-Control.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Layered-Control.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Layered-Control.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Layered-Control.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Layered-Control.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered-Control.py)| +|[DiffSynth-Studio/Qwen-Image-Layered-Control-V2](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Layered-Control-V2)|[code](/examples/qwen_image/model_inference/Qwen-Image-Layered-Control-V2.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Layered-Control-V2.py)|-|-|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Layered-Control-V2.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered-Control-V2.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_inference_low_vram/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)| |[DiffSynth-Studio/Qwen-Image-EliGen-V2](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen-V2)|[code](/examples/qwen_image/model_inference/Qwen-Image-EliGen-V2.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-EliGen-V2.py)|-|-|[code](/examples/qwen_image/model_training/lora/Qwen-Image-EliGen.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-EliGen.py)| |[DiffSynth-Studio/Qwen-Image-EliGen-Poster](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen-Poster)|[code](/examples/qwen_image/model_inference/Qwen-Image-EliGen-Poster.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-EliGen-Poster.py)|-|-|[code](/examples/qwen_image/model_training/lora/Qwen-Image-EliGen-Poster.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-EliGen-Poster.py)| diff --git a/README_zh.md b/README_zh.md index 72c80d5..f660db7 100644 --- a/README_zh.md +++ b/README_zh.md @@ -32,6 +32,8 @@ DiffSynth 目前包括两个开源项目： > DiffSynth-Studio 经历了大版本更新，部分旧功能已停止维护，如需使用旧版功能，请切换到大版本更新前的[最后一个历史版本](https://github.com/modelscope/DiffSynth-Studio/tree/afd101f3452c9ecae0c87b79adfa2e22d65ffdc3)。 > 目前本项目的开发人员有限，大部分工作由 [Artiprocher](https://github.com/Artiprocher) 负责，因此新功能的开发进展会比较缓慢，issue 的回复和解决速度有限，我们对此感到非常抱歉，请各位开发者理解。 +- **2026年2月24日** 我们发布了 [DiffSynth-Studio/Qwen-Image-Layered-Control-V2](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Layered-Control-V2) 模型，这是 Qwen-Image-Layered-Control 的更新版本。除了原本就支持的文本引导功能，新增了画笔控制的图层拆分能力。 + - **2026年2月10日** 新增对[LTX-2](https://www.modelscope.cn/models/Lightricks/LTX-2)音视频生成模型的推理支持，详见[文档](docs/zh/Model_Details/LTX-2.md)，后续将推进模型训练的支持。 - **2026年2月2日** Research Tutorial 的第一篇文档上线，带你从零开始训练一个 0.1B 的小型文生图模型，详见[文档](/docs/zh/Research_Tutorial/train_from_scratch.md)、[模型](https://modelscope.cn/models/DiffSynth-Studio/AAAMyModel)，我们希望 DiffSynth-Studio 能够成为一个更强大的 Diffusion 模型训练框架。 @@ -424,6 +426,7 @@ Qwen-Image 的示例代码位于：[/examples/qwen_image/](/examples/qwen_image/ |[lightx2v/Qwen-Image-Edit-2511-Lightning](https://modelscope.cn/models/lightx2v/Qwen-Image-Edit-2511-Lightning)|[code](/examples/qwen_image/model_inference/Qwen-Image-Edit-2511-Lightning.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2511-Lightning.py)|-|-|-|-| |[Qwen/Qwen-Image-Layered](https://www.modelscope.cn/models/Qwen/Qwen-Image-Layered)|[code](/examples/qwen_image/model_inference/Qwen-Image-Layered.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Layered.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Layered.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Layered.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Layered.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered.py)| |[DiffSynth-Studio/Qwen-Image-Layered-Control](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Layered-Control)|[code](/examples/qwen_image/model_inference/Qwen-Image-Layered-Control.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Layered-Control.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Layered-Control.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Layered-Control.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Layered-Control.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered-Control.py)| +|[DiffSynth-Studio/Qwen-Image-Layered-Control-V2](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Layered-Control-V2)|[code](/examples/qwen_image/model_inference/Qwen-Image-Layered-Control-V2.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Layered-Control-V2.py)|-|-|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Layered-Control-V2.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered-Control-V2.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_inference_low_vram/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)| |[DiffSynth-Studio/Qwen-Image-EliGen-V2](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen-V2)|[code](/examples/qwen_image/model_inference/Qwen-Image-EliGen-V2.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-EliGen-V2.py)|-|-|[code](/examples/qwen_image/model_training/lora/Qwen-Image-EliGen.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-EliGen.py)| |[DiffSynth-Studio/Qwen-Image-EliGen-Poster](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen-Poster)|[code](/examples/qwen_image/model_inference/Qwen-Image-EliGen-Poster.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-EliGen-Poster.py)|-|-|[code](/examples/qwen_image/model_training/lora/Qwen-Image-EliGen-Poster.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-EliGen-Poster.py)| diff --git a/diffsynth/pipelines/qwen_image.py b/diffsynth/pipelines/qwen_image.py index 75cfbee..9677f86 100644 --- a/diffsynth/pipelines/qwen_image.py +++ b/diffsynth/pipelines/qwen_image.py @@ -682,14 +682,16 @@ class QwenImageUnit_Image2LoRADecode(PipelineUnit): class QwenImageUnit_ContextImageEmbedder(PipelineUnit): def __init__(self): super().__init__( - input_params=("context_image", "height", "width", "tiled", "tile_size", "tile_stride"), + input_params=("context_image", "height", "width", "tiled", "tile_size", "tile_stride", "layer_input_image"), output_params=("context_latents",), onload_model_names=("vae",) ) - def process(self, pipe: QwenImagePipeline, context_image, height, width, tiled, tile_size, tile_stride): + def process(self, pipe: QwenImagePipeline, context_image, height, width, tiled, tile_size, tile_stride, layer_input_image=None): if context_image is None: return {} + if layer_input_image is not None: + context_image = context_image.convert("RGBA") pipe.load_models_to_device(self.onload_model_names) context_image = pipe.preprocess_image(context_image.resize((width, height))).to(device=pipe.device, dtype=pipe.torch_dtype) context_latents = pipe.vae.encode(context_image, tiled=tiled, tile_size=tile_size, tile_stride=tile_stride) diff --git a/docs/en/Model_Details/Qwen-Image.md b/docs/en/Model_Details/Qwen-Image.md index ae417c1..0cff1c6 100644 --- a/docs/en/Model_Details/Qwen-Image.md +++ b/docs/en/Model_Details/Qwen-Image.md @@ -89,6 +89,7 @@ graph LR; |[lightx2v/Qwen-Image-Edit-2511-Lightning](https://modelscope.cn/models/lightx2v/Qwen-Image-Edit-2511-Lightning)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_inference/Qwen-Image-Edit-2511-Lightning.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2511-Lightning.py)|-|-|-|-| |[Qwen/Qwen-Image-Layered](https://www.modelscope.cn/models/Qwen/Qwen-Image-Layered)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_inference/Qwen-Image-Layered.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_inference_low_vram/Qwen-Image-Layered.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/full/Qwen-Image-Layered.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/validate_full/Qwen-Image-Layered.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/lora/Qwen-Image-Layered.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered.py)| |[DiffSynth-Studio/Qwen-Image-Layered-Control](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Layered-Control)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_inference/Qwen-Image-Layered-Control.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_inference_low_vram/Qwen-Image-Layered-Control.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/full/Qwen-Image-Layered-Control.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/validate_full/Qwen-Image-Layered-Control.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/lora/Qwen-Image-Layered-Control.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered-Control.py)| +|[DiffSynth-Studio/Qwen-Image-Layered-Control-V2](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Layered-Control-V2)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_inference/Qwen-Image-Layered-Control-V2.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_inference_low_vram/Qwen-Image-Layered-Control-V2.py)|-|-|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/lora/Qwen-Image-Layered-Control-V2.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered-Control-V2.py)| | [DiffSynth-Studio/Qwen-Image-EliGen](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen) | [code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_inference/Qwen-Image-EliGen.py) | [code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_inference_low_vram/Qwen-Image-EliGen.py) | - | - | [code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/lora/Qwen-Image-EliGen.sh) | [code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/validate_lora/Qwen-Image-EliGen.py) | | [DiffSynth-Studio/Qwen-Image-EliGen-V2](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen-V2) | [code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_inference/Qwen-Image-EliGen-V2.py) | [code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_inference_low_vram/Qwen-Image-EliGen-V2.py) | - | - | [code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/lora/Qwen-Image-EliGen.sh) | [code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/validate_lora/Qwen-Image-EliGen.py) | | [DiffSynth-Studio/Qwen-Image-EliGen-Poster](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen-Poster) | [code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_inference/Qwen-Image-EliGen-Poster.py) | [code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_inference_low_vram/Qwen-Image-EliGen-Poster.py) | - | - | [code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/lora/Qwen-Image-EliGen-Poster.sh) | [code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/validate_lora/Qwen-Image-EliGen-Poster.py) | diff --git a/docs/zh/Model_Details/Qwen-Image.md b/docs/zh/Model_Details/Qwen-Image.md index 3cf7368..77027d8 100644 --- a/docs/zh/Model_Details/Qwen-Image.md +++ b/docs/zh/Model_Details/Qwen-Image.md @@ -89,6 +89,7 @@ graph LR; |[lightx2v/Qwen-Image-Edit-2511-Lightning](https://modelscope.cn/models/lightx2v/Qwen-Image-Edit-2511-Lightning)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_inference/Qwen-Image-Edit-2511-Lightning.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2511-Lightning.py)|-|-|-|-| |[Qwen/Qwen-Image-Layered](https://www.modelscope.cn/models/Qwen/Qwen-Image-Layered)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_inference/Qwen-Image-Layered.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_inference_low_vram/Qwen-Image-Layered.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/full/Qwen-Image-Layered.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/validate_full/Qwen-Image-Layered.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/lora/Qwen-Image-Layered.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered.py)| |[DiffSynth-Studio/Qwen-Image-Layered-Control](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Layered-Control)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_inference/Qwen-Image-Layered-Control.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_inference_low_vram/Qwen-Image-Layered-Control.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/full/Qwen-Image-Layered-Control.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/validate_full/Qwen-Image-Layered-Control.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/lora/Qwen-Image-Layered-Control.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered-Control.py)| +|[DiffSynth-Studio/Qwen-Image-Layered-Control-V2](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Layered-Control-V2)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_inference/Qwen-Image-Layered-Control-V2.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_inference_low_vram/Qwen-Image-Layered-Control-V2.py)|-|-|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/lora/Qwen-Image-Layered-Control-V2.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered-Control-V2.py)| |[DiffSynth-Studio/Qwen-Image-EliGen](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_inference/Qwen-Image-EliGen.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_inference_low_vram/Qwen-Image-EliGen.py)|-|-|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/lora/Qwen-Image-EliGen.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/validate_lora/Qwen-Image-EliGen.py)| |[DiffSynth-Studio/Qwen-Image-EliGen-V2](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen-V2)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_inference/Qwen-Image-EliGen-V2.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_inference_low_vram/Qwen-Image-EliGen-V2.py)|-|-|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/lora/Qwen-Image-EliGen.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/validate_lora/Qwen-Image-EliGen.py)| |[DiffSynth-Studio/Qwen-Image-EliGen-Poster](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen-Poster)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_inference/Qwen-Image-EliGen-Poster.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_inference_low_vram/Qwen-Image-EliGen-Poster.py)|-|-|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/lora/Qwen-Image-EliGen-Poster.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/validate_lora/Qwen-Image-EliGen-Poster.py)| diff --git a/examples/qwen_image/model_inference/Qwen-Image-Layered-Control-V2.py b/examples/qwen_image/model_inference/Qwen-Image-Layered-Control-V2.py new file mode 100644 index 0000000..273ee19 --- /dev/null +++ b/examples/qwen_image/model_inference/Qwen-Image-Layered-Control-V2.py @@ -0,0 +1,43 @@ +from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig +from modelscope import dataset_snapshot_download +from PIL import Image +import torch + +pipe = QwenImagePipeline.from_pretrained( + torch_dtype=torch.bfloat16, + device="cuda", + model_configs=[ + ModelConfig(model_id="Qwen/Qwen-Image-Layered", 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-Layered", 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, ModelConfig(model_id="DiffSynth-Studio/Qwen-Image-Layered-Control-V2", origin_file_pattern="model.safetensors")) + +dataset_snapshot_download( + dataset_id="DiffSynth-Studio/example_image_dataset", + local_dir="./data/example_image_dataset", + allow_file_pattern="layer_v2/*.png" +) + +prompt = "Text 'APRIL'" +input_image = Image.open("data/example_image_dataset/layer_v2/image_1.png").convert("RGBA").resize((1024, 1024)) +image = pipe( + prompt, seed=0, + height=1024, width=1024, + layer_input_image=input_image, layer_num=0, + num_inference_steps=10, cfg_scale=4, +) +image[0].save("image_prompt.png") + +mask_image = Image.open("data/example_image_dataset/layer_v2/mask_2.png").convert("RGBA").resize((1024, 1024)) +input_image = Image.open("data/example_image_dataset/layer_v2/image_2.png").convert("RGBA").resize((1024, 1024)) +image = pipe( + prompt, seed=0, + height=1024, width=1024, + layer_input_image=input_image, layer_num=0, + context_image=mask_image, + num_inference_steps=10, cfg_scale=1.0, +) +image[0].save("image_mask.png") diff --git a/examples/qwen_image/model_inference_low_vram/Qwen-Image-Layered-Control-V2.py b/examples/qwen_image/model_inference_low_vram/Qwen-Image-Layered-Control-V2.py new file mode 100644 index 0000000..108dab5 --- /dev/null +++ b/examples/qwen_image/model_inference_low_vram/Qwen-Image-Layered-Control-V2.py @@ -0,0 +1,54 @@ +from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig +from modelscope import dataset_snapshot_download +from PIL import Image +import torch + + +vram_config = { + "offload_dtype": "disk", + "offload_device": "disk", + "onload_dtype": torch.float8_e4m3fn, + "onload_device": "cpu", + "preparing_dtype": torch.float8_e4m3fn, + "preparing_device": "cuda", + "computation_dtype": torch.bfloat16, + "computation_device": "cuda", +} +pipe = QwenImagePipeline.from_pretrained( + torch_dtype=torch.bfloat16, + device="cuda", + model_configs=[ + ModelConfig(model_id="Qwen/Qwen-Image-Layered", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors", **vram_config), + ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors", **vram_config), + ModelConfig(model_id="Qwen/Qwen-Image-Layered", origin_file_pattern="vae/diffusion_pytorch_model.safetensors", **vram_config), + ], + tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"), +) +pipe.load_lora(pipe.dit, ModelConfig(model_id="DiffSynth-Studio/Qwen-Image-Layered-Control-V2", origin_file_pattern="model.safetensors", **vram_config)) + +dataset_snapshot_download( + dataset_id="DiffSynth-Studio/example_image_dataset", + local_dir="./data/example_image_dataset", + allow_file_pattern="layer_v2/*.png" +) + +prompt = "Text 'APRIL'" +input_image = Image.open("data/example_image_dataset/layer_v2/image_1.png").convert("RGBA").resize((1024, 1024)) +image = pipe( + prompt, seed=0, + height=1024, width=1024, + layer_input_image=input_image, layer_num=0, + num_inference_steps=10, cfg_scale=4, +) +image[0].save("image_prompt.png") + +mask_image = Image.open("data/example_image_dataset/layer_v2/mask_2.png").convert("RGBA").resize((1024, 1024)) +input_image = Image.open("data/example_image_dataset/layer_v2/image_2.png").convert("RGBA").resize((1024, 1024)) +image = pipe( + prompt, seed=0, + height=1024, width=1024, + layer_input_image=input_image, layer_num=0, + context_image=mask_image, + num_inference_steps=10, cfg_scale=1.0, +) +image[0].save("image_mask.png") diff --git a/examples/qwen_image/model_training/lora/Qwen-Image-Layered-Control-V2.sh b/examples/qwen_image/model_training/lora/Qwen-Image-Layered-Control-V2.sh new file mode 100644 index 0000000..3574dfe --- /dev/null +++ b/examples/qwen_image/model_training/lora/Qwen-Image-Layered-Control-V2.sh @@ -0,0 +1,20 @@ +# Example Dataset: https://modelscope.cn/datasets/DiffSynth-Studio/example_image_dataset/tree/master/layer + +accelerate launch examples/qwen_image/model_training/train.py \ + --dataset_base_path data/example_image_dataset/layer_v2 \ + --dataset_metadata_path data/example_image_dataset/layer_v2/metadata_layered_control_v2.json \ + --data_file_keys "image,layer_input_image,context_image" \ + --max_pixels 1048576 \ + --dataset_repeat 50 \ + --model_id_with_origin_paths "Qwen/Qwen-Image-Layered:transformer/diffusion_pytorch_model*.safetensors,Qwen/Qwen-Image:text_encoder/model*.safetensors,Qwen/Qwen-Image-Layered:vae/diffusion_pytorch_model.safetensors" \ + --learning_rate 1e-4 \ + --num_epochs 5 \ + --remove_prefix_in_ckpt "pipe.dit." \ + --output_path "./models/train/Qwen-Image-Layered-Control-V2_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 64 \ + --extra_inputs "layer_num,layer_input_image,context_image" \ + --use_gradient_checkpointing \ + --dataset_num_workers 8 \ + --find_unused_parameters diff --git a/examples/qwen_image/model_training/train.py b/examples/qwen_image/model_training/train.py index ecb4239..447c16a 100644 --- a/examples/qwen_image/model_training/train.py +++ b/examples/qwen_image/model_training/train.py @@ -131,6 +131,10 @@ if __name__ == "__main__": "image": RouteByType(operator_map=[ (str, ToAbsolutePath(args.dataset_base_path) >> LoadImage() >> ImageCropAndResize(args.height, args.width, args.max_pixels, 16, 16)), (list, SequencialProcess(ToAbsolutePath(args.dataset_base_path) >> LoadImage(convert_RGB=False, convert_RGBA=True) >> ImageCropAndResize(args.height, args.width, args.max_pixels, 16, 16))), + ]), + "context_image": RouteByType(operator_map=[ + (str, ToAbsolutePath(args.dataset_base_path) >> LoadImage() >> ImageCropAndResize(args.height, args.width, args.max_pixels, 16, 16)), + (None, lambda x: None), ]) } ) @@ -152,7 +156,7 @@ if __name__ == "__main__": fp8_models=args.fp8_models, offload_models=args.offload_models, task=args.task, - device="cpu" if args.initialize_model_on_cpu else accelerator.device, + device=accelerator.device, zero_cond_t=args.zero_cond_t, ) model_logger = ModelLogger( diff --git a/examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered-Control-V2.py b/examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered-Control-V2.py new file mode 100644 index 0000000..971d35c --- /dev/null +++ b/examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered-Control-V2.py @@ -0,0 +1,37 @@ +from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig +from modelscope import dataset_snapshot_download +from PIL import Image +import torch + +pipe = QwenImagePipeline.from_pretrained( + torch_dtype=torch.bfloat16, + device="cuda", + model_configs=[ + ModelConfig(model_id="Qwen/Qwen-Image-Layered", 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-Layered", 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-Layered-Control-V2_lora/epoch-4.safetensors") + +prompt = "Text 'APRIL'" +input_image = Image.open("data/example_image_dataset/layer_v2/image_1.png").convert("RGBA").resize((1024, 1024)) +image = pipe( + prompt, seed=0, + height=1024, width=1024, + layer_input_image=input_image, layer_num=0, + num_inference_steps=10, cfg_scale=4, +) +image[0].save("image_prompt.png") + +mask_image = Image.open("data/example_image_dataset/layer_v2/mask_2.png").convert("RGBA").resize((1024, 1024)) +input_image = Image.open("data/example_image_dataset/layer_v2/image_2.png").convert("RGBA").resize((1024, 1024)) +image = pipe( + prompt, seed=0, + height=1024, width=1024, + layer_input_image=input_image, layer_num=0, + context_image=mask_image, + num_inference_steps=10, cfg_scale=1.0, +) +image[0].save("image_mask.png")