From 03e530dc39ff47f05ddfc51a9ac3b613f08568c0 Mon Sep 17 00:00:00 2001 From: Artiprocher Date: Mon, 12 Jan 2026 17:20:01 +0800 Subject: [PATCH] support qwen-image-layered-control --- README.md | 5 +++ README_zh.md | 5 +++ docs/en/Model_Details/Qwen-Image.md | 1 + docs/zh/Model_Details/Qwen-Image.md | 1 + .../Qwen-Image-Layered-Control.py | 34 ++++++++++++++ .../Qwen-Image-Layered-Control.py | 44 +++++++++++++++++++ .../full/Qwen-Image-Layered-Control.sh | 18 ++++++++ .../lora/Qwen-Image-Layered-Control.sh | 20 +++++++++ .../Qwen-Image-Layered-Control.py | 26 +++++++++++ .../Qwen-Image-Layered-Control.py | 25 +++++++++++ 10 files changed, 179 insertions(+) create mode 100644 examples/qwen_image/model_inference/Qwen-Image-Layered-Control.py create mode 100644 examples/qwen_image/model_inference_low_vram/Qwen-Image-Layered-Control.py create mode 100644 examples/qwen_image/model_training/full/Qwen-Image-Layered-Control.sh create mode 100644 examples/qwen_image/model_training/lora/Qwen-Image-Layered-Control.sh create mode 100644 examples/qwen_image/model_training/validate_full/Qwen-Image-Layered-Control.py create mode 100644 examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered-Control.py diff --git a/README.md b/README.md index 2e4a41a..69f70e1 100644 --- a/README.md +++ b/README.md @@ -33,6 +33,10 @@ We believe that a well-developed open-source code framework can lower the thresh > 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. +- **January 12, 2026**: We trained and open-sourced a text-guided image layer separation model ([Model Link](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Layered-Control)). Given an input image and a textual description, the model isolates the image layer corresponding to the described content. + +- **December 24, 2025**: Based on Qwen-Image-Edit-2511, we trained an In-Context Editing LoRA model ([Model Link](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Edit-2511-ICEdit-LoRA)). This model takes three images as input (Image A, Image B, and Image C), and automatically analyzes the transformation from Image A to Image B, then applies the same transformation to Image C to generate Image D. For more details, please refer to our blog post ([Chinese version](https://mp.weixin.qq.com/s/41aEiN3lXKGCJs1-we4Q2g), [English version](https://huggingface.co/blog/kelseye/qwen-image-edit-2511-icedit-lora)). + - **December 9, 2025** We release a wild model based on DiffSynth-Studio 2.0: [Qwen-Image-i2L](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-i2L) (Image-to-LoRA). This model takes an image as input and outputs a LoRA. Although this version still has significant room for improvement in terms of generalization, detail preservation, and other aspects, we are open-sourcing these models to inspire more innovative research. For more details, please refer to our [blog](https://huggingface.co/blog/kelseye/qwen-image-i2l). - **December 4, 2025** DiffSynth-Studio 2.0 released! Many new features online @@ -401,6 +405,7 @@ Example code for Qwen-Image is available at: [/examples/qwen_image/](/examples/q |[Qwen/Qwen-Image-Edit-2509](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit-2509)|[code](/examples/qwen_image/model_inference/Qwen-Image-Edit-2509.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2509.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Edit-2509.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Edit-2509.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Edit-2509.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit-2509.py)| |[Qwen/Qwen-Image-Edit-2511](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit-2511)|[code](/examples/qwen_image/model_inference/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Edit-2511.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Edit-2511.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit-2511.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-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 8deb8bf..250c48e 100644 --- a/README_zh.md +++ b/README_zh.md @@ -33,6 +33,10 @@ DiffSynth 目前包括两个开源项目： > 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1月12日** 我们训练并开源了一个文本引导的图层拆分模型（[模型链接](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Layered-Control)），这一模型输入一张图与一段文本描述，模型会将图像中与文本描述相关的图层拆分出来。 + +- **2025年12月24日** 我们基于 Qwen-Image-Edit-2511 训练了一个 In-Context Editing LoRA 模型（[模型链接](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Edit-2511-ICEdit-LoRA)），这个模型可以输入三张图：图A、图B、图C，模型会自行分析图A到图B的变化，并将这样的变化应用到图C，生成图D。更多细节请阅读我们的 blog（[中文版](https://mp.weixin.qq.com/s/41aEiN3lXKGCJs1-we4Q2g)、[英文版](https://huggingface.co/blog/kelseye/qwen-image-edit-2511-icedit-lora)）。 + - **2025年12月9日** 我们基于 DiffSynth-Studio 2.0 训练了一个疯狂的模型：[Qwen-Image-i2L](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-i2L)（Image to LoRA）。这一模型以图像为输入，以 LoRA 为输出。尽管这个版本的模型在泛化能力、细节保持能力等方面还有很大改进空间，我们将这些模型开源，以启发更多创新性的研究工作。更多细节，请参考我们的 [blog](https://huggingface.co/blog/kelseye/qwen-image-i2l)。 - **2025年12月4日** DiffSynth-Studio 2.0 发布！众多新功能上线 @@ -401,6 +405,7 @@ Qwen-Image 的示例代码位于：[/examples/qwen_image/](/examples/qwen_image/ |[Qwen/Qwen-Image-Edit-2509](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit-2509)|[code](/examples/qwen_image/model_inference/Qwen-Image-Edit-2509.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2509.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Edit-2509.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Edit-2509.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Edit-2509.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit-2509.py)| |[Qwen/Qwen-Image-Edit-2511](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit-2511)|[code](/examples/qwen_image/model_inference/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Edit-2511.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Edit-2511.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit-2511.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-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/docs/en/Model_Details/Qwen-Image.md b/docs/en/Model_Details/Qwen-Image.md index 3a7c1e6..08b8a35 100644 --- a/docs/en/Model_Details/Qwen-Image.md +++ b/docs/en/Model_Details/Qwen-Image.md @@ -86,6 +86,7 @@ graph LR; | [Qwen/Qwen-Image-Edit-2509](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit-2509) | [code](/examples/qwen_image/model_inference/Qwen-Image-Edit-2509.py) | [code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2509.py) | [code](/examples/qwen_image/model_training/full/Qwen-Image-Edit-2509.sh) | [code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Edit-2509.py) | [code](/examples/qwen_image/model_training/lora/Qwen-Image-Edit-2509.sh) | [code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit-2509.py) | |[Qwen/Qwen-Image-Edit-2511](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit-2511)|[code](/examples/qwen_image/model_inference/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Edit-2511.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Edit-2511.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit-2511.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-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/docs/zh/Model_Details/Qwen-Image.md b/docs/zh/Model_Details/Qwen-Image.md index 8fe9de4..697438f 100644 --- a/docs/zh/Model_Details/Qwen-Image.md +++ b/docs/zh/Model_Details/Qwen-Image.md @@ -86,6 +86,7 @@ graph LR; |[Qwen/Qwen-Image-Edit-2509](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit-2509)|[code](/examples/qwen_image/model_inference/Qwen-Image-Edit-2509.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2509.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Edit-2509.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Edit-2509.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Edit-2509.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit-2509.py)| |[Qwen/Qwen-Image-Edit-2511](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit-2511)|[code](/examples/qwen_image/model_inference/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Edit-2511.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Edit-2511.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit-2511.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-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/examples/qwen_image/model_inference/Qwen-Image-Layered-Control.py b/examples/qwen_image/model_inference/Qwen-Image-Layered-Control.py new file mode 100644 index 0000000..5ce82c7 --- /dev/null +++ b/examples/qwen_image/model_inference/Qwen-Image-Layered-Control.py @@ -0,0 +1,34 @@ +from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig +from modelscope import snapshot_download +from PIL import Image +import torch + + +pipe = QwenImagePipeline.from_pretrained( + torch_dtype=torch.bfloat16, + device="cuda", + model_configs=[ + ModelConfig(model_id="DiffSynth-Studio/Qwen-Image-Layered-Control", 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"), + ], + processor_config=ModelConfig(model_id="Qwen/Qwen-Image-Edit", origin_file_pattern="processor/"), +) + +snapshot_download( + model_id="DiffSynth-Studio/Qwen-Image-Layered-Control", + allow_file_pattern="assets/image_1_input.png", + local_dir="data/layered_input" +) + +prompt = "A cartoon skeleton character wearing a purple hat and holding a gift box" +input_image = Image.open("data/layered_input/assets/image_1_input.png").convert("RGBA").resize((1024, 1024)) +images = pipe( + prompt, + seed=0, + num_inference_steps=30, cfg_scale=4, + height=1024, width=1024, + layer_input_image=input_image, + layer_num=0, +) +images[0].save("image.png") diff --git a/examples/qwen_image/model_inference_low_vram/Qwen-Image-Layered-Control.py b/examples/qwen_image/model_inference_low_vram/Qwen-Image-Layered-Control.py new file mode 100644 index 0000000..eb5c77d --- /dev/null +++ b/examples/qwen_image/model_inference_low_vram/Qwen-Image-Layered-Control.py @@ -0,0 +1,44 @@ +from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig +from modelscope import 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="DiffSynth-Studio/Qwen-Image-Layered-Control", 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), + ], + processor_config=ModelConfig(model_id="Qwen/Qwen-Image-Edit", origin_file_pattern="processor/"), +) + +snapshot_download( + model_id="DiffSynth-Studio/Qwen-Image-Layered-Control", + allow_file_pattern="assets/image_1_input.png", + local_dir="data/layered_input" +) + +prompt = "A cartoon skeleton character wearing a purple hat and holding a gift box" +input_image = Image.open("data/layered_input/assets/image_1_input.png").convert("RGBA").resize((1024, 1024)) +images = pipe( + prompt, + seed=0, + num_inference_steps=30, cfg_scale=4, + height=1024, width=1024, + layer_input_image=input_image, + layer_num=0, +) +images[0].save("image.png") diff --git a/examples/qwen_image/model_training/full/Qwen-Image-Layered-Control.sh b/examples/qwen_image/model_training/full/Qwen-Image-Layered-Control.sh new file mode 100644 index 0000000..14a3cb4 --- /dev/null +++ b/examples/qwen_image/model_training/full/Qwen-Image-Layered-Control.sh @@ -0,0 +1,18 @@ +# Example Dataset: https://modelscope.cn/datasets/DiffSynth-Studio/example_image_dataset/tree/master/layer + +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_metadata_path data/example_image_dataset/layer/metadata_layered_control.json \ + --data_file_keys "image,layer_input_image" \ + --max_pixels 1048576 \ + --dataset_repeat 50 \ + --model_id_with_origin_paths "DiffSynth-Studio/Qwen-Image-Layered-Control:transformer/diffusion_pytorch_model*.safetensors,Qwen/Qwen-Image:text_encoder/model*.safetensors,Qwen/Qwen-Image-Layered:vae/diffusion_pytorch_model.safetensors" \ + --learning_rate 1e-5 \ + --num_epochs 2 \ + --remove_prefix_in_ckpt "pipe.dit." \ + --output_path "./models/train/Qwen-Image-Layered-Control_full" \ + --trainable_models "dit" \ + --extra_inputs "layer_num,layer_input_image" \ + --use_gradient_checkpointing \ + --dataset_num_workers 8 \ + --find_unused_parameters diff --git a/examples/qwen_image/model_training/lora/Qwen-Image-Layered-Control.sh b/examples/qwen_image/model_training/lora/Qwen-Image-Layered-Control.sh new file mode 100644 index 0000000..397c975 --- /dev/null +++ b/examples/qwen_image/model_training/lora/Qwen-Image-Layered-Control.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 \ + --dataset_metadata_path data/example_image_dataset/layer/metadata_layered_control.json \ + --data_file_keys "image,layer_input_image" \ + --max_pixels 1048576 \ + --dataset_repeat 50 \ + --model_id_with_origin_paths "DiffSynth-Studio/Qwen-Image-Layered-Control: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_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 \ + --extra_inputs "layer_num,layer_input_image" \ + --use_gradient_checkpointing \ + --dataset_num_workers 8 \ + --find_unused_parameters diff --git a/examples/qwen_image/model_training/validate_full/Qwen-Image-Layered-Control.py b/examples/qwen_image/model_training/validate_full/Qwen-Image-Layered-Control.py new file mode 100644 index 0000000..961904f --- /dev/null +++ b/examples/qwen_image/model_training/validate_full/Qwen-Image-Layered-Control.py @@ -0,0 +1,26 @@ +from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig +from diffsynth import load_state_dict +from PIL import Image +import torch + + +pipe = QwenImagePipeline.from_pretrained( + torch_dtype=torch.bfloat16, + device="cuda", + model_configs=[ + ModelConfig(model_id="DiffSynth-Studio/Qwen-Image-Layered-Control", 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/"), +) +state_dict = load_state_dict("models/train/Qwen-Image-Layered-Control_full/epoch-1.safetensors") +pipe.dit.load_state_dict(state_dict) +prompt = "Text 'HELLO' and 'Have a great day'" +input_image = Image.open("data/example_image_dataset/layer/image.png").convert("RGBA").resize((864, 480)) +images = pipe( + prompt, seed=0, + height=480, width=864, + layer_input_image=input_image, layer_num=0, +) +images[0].save("image.png") diff --git a/examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered-Control.py b/examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered-Control.py new file mode 100644 index 0000000..1a96e8b --- /dev/null +++ b/examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered-Control.py @@ -0,0 +1,25 @@ +from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig +from diffsynth import load_state_dict +from PIL import Image +import torch + + +pipe = QwenImagePipeline.from_pretrained( + torch_dtype=torch.bfloat16, + device="cuda", + model_configs=[ + ModelConfig(model_id="DiffSynth-Studio/Qwen-Image-Layered-Control", 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_lora/epoch-4.safetensors") +prompt = "Text 'HELLO' and 'Have a great day'" +input_image = Image.open("data/example_image_dataset/layer/image.png").convert("RGBA").resize((864, 480)) +images = pipe( + prompt, seed=0, + height=480, width=864, + layer_input_image=input_image, layer_num=0, +) +images[0].save("image.png")