From 613dafbd090bfb7dc51b2da16197fa455033b22d Mon Sep 17 00:00:00 2001 From: Artiprocher Date: Thu, 21 Aug 2025 13:35:47 +0800 Subject: [PATCH] rename model --- README.md | 4 ++-- README_zh.md | 4 ++-- diffsynth/pipelines/qwen_image.py | 3 +-- examples/qwen_image/README.md | 2 +- examples/qwen_image/README_zh.md | 2 +- ...text-Control.py => Qwen-Image-In-Context-Control-Union.py} | 4 ++-- ...text-Control.py => Qwen-Image-In-Context-Control-Union.py} | 4 ++-- ...text-Control.sh => Qwen-Image-In-Context-Control-Union.sh} | 4 ++-- ...text-Control.py => Qwen-Image-In-Context-Control-Union.py} | 2 +- 9 files changed, 14 insertions(+), 15 deletions(-) rename examples/qwen_image/model_inference/{Qwen-Image-Context-Control.py => Qwen-Image-In-Context-Control-Union.py} (88%) rename examples/qwen_image/model_inference_low_vram/{Qwen-Image-Context-Control.py => Qwen-Image-In-Context-Control-Union.py} (88%) rename examples/qwen_image/model_training/lora/{Qwen-Image-Context-Control.sh => Qwen-Image-In-Context-Control-Union.sh} (84%) rename examples/qwen_image/model_training/validate_lora/{Qwen-Image-Context-Control.py => Qwen-Image-In-Context-Control-Union.py} (89%) diff --git a/README.md b/README.md index 6525fd7..b1c8716 100644 --- a/README.md +++ b/README.md @@ -98,7 +98,7 @@ image.save("image.jpg") |[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny)|[code](./examples/qwen_image/model_inference/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image-Blockwise-ControlNet-Canny.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Blockwise-ControlNet-Canny.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Canny.py)| |[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth)|[code](./examples/qwen_image/model_inference/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image-Blockwise-ControlNet-Depth.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Blockwise-ControlNet-Depth.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Depth.py)| |[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint)|[code](./examples/qwen_image/model_inference/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image-Blockwise-ControlNet-Inpaint.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Blockwise-ControlNet-Inpaint.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Inpaint.py)| -|[DiffSynth-Studio/Qwen-Image-Context-Control](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Context-Control)|[code](./examples/qwen_image/model_inference/Qwen-Image-Context-Control.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Context-Control.py)|-|-|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Context-Control.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Context-Control.py)| +|[DiffSynth-Studio/Qwen-Image-In-Context-Control-Union](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-In-Context-Control-Union)|[code](./examples/qwen_image/model_inference/Qwen-Image-In-Context-Control-Union.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-In-Context-Control-Union.py)|-|-|[code](./examples/qwen_image/model_training/lora/Qwen-Image-In-Context-Control-Union.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-In-Context-Control-Union.py)| |[DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix)|[code](./examples/qwen_image/model_inference/Qwen-Image-Edit-Lowres-Fix.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-Lowres-Fix.py)|-|-|-|-| @@ -374,7 +374,7 @@ https://github.com/Artiprocher/DiffSynth-Studio/assets/35051019/59fb2f7b-8de0-44 ## Update History - **August 21, 2025**: [DiffSynth-Studio/Qwen-Image-EliGen-V2](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen-V2) is released! Compared to the V1 version, the training dataset has been updated to the [Qwen-Image-Self-Generated-Dataset](https://www.modelscope.cn/datasets/DiffSynth-Studio/Qwen-Image-Self-Generated-Dataset), enabling generated images to better align with the inherent image distribution and style of Qwen-Image. Please refer to [our sample code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-EliGen-V2.py). -- **August 21, 2025**: We open-sourced the [DiffSynth-Studio/Qwen-Image-Context-Control](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Context-Control) structure control LoRA model. Following "In Context" routine, it supports various types of structural control conditions, including canny, depth, lineart, softedge, normal, and openpose. Please refer to [our sample code](./examples/qwen_image/model_inference/Qwen-Image-Context-Control.py). +- **August 21, 2025**: We open-sourced the [DiffSynth-Studio/Qwen-Image-In-Context-Control-Union](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-In-Context-Control-Union) structure control LoRA model. Following "In Context" routine, it supports various types of structural control conditions, including canny, depth, lineart, softedge, normal, and openpose. Please refer to [our sample code](./examples/qwen_image/model_inference/Qwen-Image-In-Context-Control-Union.py). - **August 20, 2025** We open-sourced [DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix), which improves the editing performance of Qwen-Image-Edit on low-resolution image inputs. Please refer to [our example code](./examples/qwen_image/model_inference/Qwen-Image-Edit-Lowres-Fix.py). diff --git a/README_zh.md b/README_zh.md index f218665..a8ff395 100644 --- a/README_zh.md +++ b/README_zh.md @@ -100,7 +100,7 @@ image.save("image.jpg") |[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny)|[code](./examples/qwen_image/model_inference/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image-Blockwise-ControlNet-Canny.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Blockwise-ControlNet-Canny.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Canny.py)| |[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth)|[code](./examples/qwen_image/model_inference/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image-Blockwise-ControlNet-Depth.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Blockwise-ControlNet-Depth.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Depth.py)| |[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint)|[code](./examples/qwen_image/model_inference/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image-Blockwise-ControlNet-Inpaint.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Blockwise-ControlNet-Inpaint.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Inpaint.py)| -|[DiffSynth-Studio/Qwen-Image-Context-Control](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Context-Control)|[code](./examples/qwen_image/model_inference/Qwen-Image-Context-Control.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Context-Control.py)|-|-|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Context-Control.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Context-Control.py)| +|[DiffSynth-Studio/Qwen-Image-In-Context-Control-Union](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-In-Context-Control-Union)|[code](./examples/qwen_image/model_inference/Qwen-Image-In-Context-Control-Union.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-In-Context-Control-Union.py)|-|-|[code](./examples/qwen_image/model_training/lora/Qwen-Image-In-Context-Control-Union.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-In-Context-Control-Union.py)| |[DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix)|[code](./examples/qwen_image/model_inference/Qwen-Image-Edit-Lowres-Fix.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-Lowres-Fix.py)|-|-|-|-| @@ -390,7 +390,7 @@ https://github.com/Artiprocher/DiffSynth-Studio/assets/35051019/59fb2f7b-8de0-44 ## 更新历史 - **2025年8月21日** [DiffSynth-Studio/Qwen-Image-EliGen-V2](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen-V2) 发布！相比于 V1 版本，训练数据集变为 [Qwen-Image-Self-Generated-Dataset](https://www.modelscope.cn/datasets/DiffSynth-Studio/Qwen-Image-Self-Generated-Dataset)，因此，生成的图像更符合 Qwen-Image 本身的图像分布和风格。 请参考[我们的示例代码](./examples/qwen_image/model_inference_low_vram/Qwen-Image-EliGen-V2.py)。 -- **2025年8月21日** 我们开源了 [DiffSynth-Studio/Qwen-Image-Context-Control](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Context-Control) 结构控制 LoRA 模型，采用 In Context 的技术路线，支持多种类别的结构控制条件，包括 canny, depth, lineart, softedge, normal, openpose。 请参考[我们的示例代码](./examples/qwen_image/model_inference/Qwen-Image-Context-Control.py)。 +- **2025年8月21日** 我们开源了 [DiffSynth-Studio/Qwen-Image-In-Context-Control-Union](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-In-Context-Control-Union) 结构控制 LoRA 模型，采用 In Context 的技术路线，支持多种类别的结构控制条件，包括 canny, depth, lineart, softedge, normal, openpose。 请参考[我们的示例代码](./examples/qwen_image/model_inference/Qwen-Image-In-Context-Control-Union.py)。 - **2025年8月20日** 我们开源了 [DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix) 模型，提升了 Qwen-Image-Edit 对低分辨率图像输入的编辑效果。请参考[我们的示例代码](./examples/qwen_image/model_inference/Qwen-Image-Edit-Lowres-Fix.py) diff --git a/diffsynth/pipelines/qwen_image.py b/diffsynth/pipelines/qwen_image.py index 595143f..57cc7c7 100644 --- a/diffsynth/pipelines/qwen_image.py +++ b/diffsynth/pipelines/qwen_image.py @@ -716,8 +716,7 @@ def model_fn_qwen_image( image = dit.norm_out(image, conditioning) image = dit.proj_out(image) - if edit_latents is not None or context_latents is not None: - image = image[:, :image_seq_len] + image = image[:, :image_seq_len] latents = rearrange(image, "B (H W) (C P Q) -> B C (H P) (W Q)", H=height//16, W=width//16, P=2, Q=2) return latents diff --git a/examples/qwen_image/README.md b/examples/qwen_image/README.md index 7b51208..db1cb83 100644 --- a/examples/qwen_image/README.md +++ b/examples/qwen_image/README.md @@ -51,7 +51,7 @@ image.save("image.jpg") |[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny)|[code](./model_inference/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./model_training/full/Qwen-Image-Blockwise-ControlNet-Canny.sh)|[code](./model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./model_training/lora/Qwen-Image-Blockwise-ControlNet-Canny.sh)|[code](./model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Canny.py)| |[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth)|[code](./model_inference/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./model_training/full/Qwen-Image-Blockwise-ControlNet-Depth.sh)|[code](./model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./model_training/lora/Qwen-Image-Blockwise-ControlNet-Depth.sh)|[code](./model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Depth.py)| |[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint)|[code](./model_inference/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./model_training/full/Qwen-Image-Blockwise-ControlNet-Inpaint.sh)|[code](./model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./model_training/lora/Qwen-Image-Blockwise-ControlNet-Inpaint.sh)|[code](./model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Inpaint.py)| -|[DiffSynth-Studio/Qwen-Image-Context-Control](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Context-Control)|[code](./model_inference/Qwen-Image-Context-Control.py)|[code](./model_inference_low_vram/Qwen-Image-Context-Control.py)|-|-|[code](./model_training/lora/Qwen-Image-Context-Control.sh)|[code](./model_training/validate_lora/Qwen-Image-Context-Control.py)| +|[DiffSynth-Studio/Qwen-Image-In-Context-Control-Union](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-In-Context-Control-Union)|[code](./model_inference/Qwen-Image-In-Context-Control-Union.py)|[code](./model_inference_low_vram/Qwen-Image-In-Context-Control-Union.py)|-|-|[code](./model_training/lora/Qwen-Image-In-Context-Control-Union.sh)|[code](./model_training/validate_lora/Qwen-Image-In-Context-Control-Union.py)| |[DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix)|[code](./model_inference/Qwen-Image-Edit-Lowres-Fix.py)|[code](./model_inference_low_vram/Qwen-Image-Edit-Lowres-Fix.py)|-|-|-|-| ## Model Inference diff --git a/examples/qwen_image/README_zh.md b/examples/qwen_image/README_zh.md index feb728e..db958a7 100644 --- a/examples/qwen_image/README_zh.md +++ b/examples/qwen_image/README_zh.md @@ -51,7 +51,7 @@ image.save("image.jpg") |[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny)|[code](./model_inference/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./model_training/full/Qwen-Image-Blockwise-ControlNet-Canny.sh)|[code](./model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./model_training/lora/Qwen-Image-Blockwise-ControlNet-Canny.sh)|[code](./model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Canny.py)| |[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth)|[code](./model_inference/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./model_training/full/Qwen-Image-Blockwise-ControlNet-Depth.sh)|[code](./model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./model_training/lora/Qwen-Image-Blockwise-ControlNet-Depth.sh)|[code](./model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Depth.py)| |[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint)|[code](./model_inference/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./model_training/full/Qwen-Image-Blockwise-ControlNet-Inpaint.sh)|[code](./model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./model_training/lora/Qwen-Image-Blockwise-ControlNet-Inpaint.sh)|[code](./model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Inpaint.py)| -|[DiffSynth-Studio/Qwen-Image-Context-Control](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Context-Control)|[code](./model_inference/Qwen-Image-Context-Control.py)|[code](./model_inference_low_vram/Qwen-Image-Context-Control.py)|-|-|[code](./model_training/lora/Qwen-Image-Context-Control.sh)|[code](./model_training/validate_lora/Qwen-Image-Context-Control.py)| +|[DiffSynth-Studio/Qwen-Image-In-Context-Control-Union](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-In-Context-Control-Union)|[code](./model_inference/Qwen-Image-In-Context-Control-Union.py)|[code](./model_inference_low_vram/Qwen-Image-In-Context-Control-Union.py)|-|-|[code](./model_training/lora/Qwen-Image-In-Context-Control-Union.sh)|[code](./model_training/validate_lora/Qwen-Image-In-Context-Control-Union.py)| |[DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix)|[code](./model_inference/Qwen-Image-Edit-Lowres-Fix.py)|[code](./model_inference_low_vram/Qwen-Image-Edit-Lowres-Fix.py)|-|-|-|-| ## 模型推理 diff --git a/examples/qwen_image/model_inference/Qwen-Image-Context-Control.py b/examples/qwen_image/model_inference/Qwen-Image-In-Context-Control-Union.py similarity index 88% rename from examples/qwen_image/model_inference/Qwen-Image-Context-Control.py rename to examples/qwen_image/model_inference/Qwen-Image-In-Context-Control-Union.py index 0e1a34f..2a27ac0 100644 --- a/examples/qwen_image/model_inference/Qwen-Image-Context-Control.py +++ b/examples/qwen_image/model_inference/Qwen-Image-In-Context-Control-Union.py @@ -17,8 +17,8 @@ pipe = QwenImagePipeline.from_pretrained( ], tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"), ) -snapshot_download("DiffSynth-Studio/Qwen-Image-Context-Control", local_dir="models/DiffSynth-Studio/Qwen-Image-Context-Control", allow_file_pattern="model.safetensors") -pipe.load_lora(pipe.dit, "models/DiffSynth-Studio/Qwen-Image-Context-Control/model.safetensors") +snapshot_download("DiffSynth-Studio/Qwen-Image-In-Context-Control-Union", local_dir="models/DiffSynth-Studio/Qwen-Image-In-Context-Control-Union", allow_file_pattern="model.safetensors") +pipe.load_lora(pipe.dit, "models/DiffSynth-Studio/Qwen-Image-In-Context-Control-Union/model.safetensors") dataset_snapshot_download(dataset_id="DiffSynth-Studio/examples_in_diffsynth", local_dir="./", allow_file_pattern=f"data/examples/qwen-image-context-control/image.jpg") origin_image = Image.open("data/examples/qwen-image-context-control/image.jpg").resize((1024, 1024)) diff --git a/examples/qwen_image/model_inference_low_vram/Qwen-Image-Context-Control.py b/examples/qwen_image/model_inference_low_vram/Qwen-Image-In-Context-Control-Union.py similarity index 88% rename from examples/qwen_image/model_inference_low_vram/Qwen-Image-Context-Control.py rename to examples/qwen_image/model_inference_low_vram/Qwen-Image-In-Context-Control-Union.py index 227f2c8..9faced8 100644 --- a/examples/qwen_image/model_inference_low_vram/Qwen-Image-Context-Control.py +++ b/examples/qwen_image/model_inference_low_vram/Qwen-Image-In-Context-Control-Union.py @@ -18,8 +18,8 @@ pipe = QwenImagePipeline.from_pretrained( tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"), ) pipe.enable_vram_management() -snapshot_download("DiffSynth-Studio/Qwen-Image-Context-Control", local_dir="models/DiffSynth-Studio/Qwen-Image-Context-Control", allow_file_pattern="model.safetensors") -pipe.load_lora(pipe.dit, "models/DiffSynth-Studio/Qwen-Image-Context-Control/model.safetensors") +snapshot_download("DiffSynth-Studio/Qwen-Image-In-Context-Control-Union", local_dir="models/DiffSynth-Studio/Qwen-Image-In-Context-Control-Union", allow_file_pattern="model.safetensors") +pipe.load_lora(pipe.dit, "models/DiffSynth-Studio/Qwen-Image-In-Context-Control-Union/model.safetensors") dataset_snapshot_download(dataset_id="DiffSynth-Studio/examples_in_diffsynth", local_dir="./", allow_file_pattern=f"data/examples/qwen-image-context-control/image.jpg") origin_image = Image.open("data/examples/qwen-image-context-control/image.jpg").resize((1024, 1024)) diff --git a/examples/qwen_image/model_training/lora/Qwen-Image-Context-Control.sh b/examples/qwen_image/model_training/lora/Qwen-Image-In-Context-Control-Union.sh similarity index 84% rename from examples/qwen_image/model_training/lora/Qwen-Image-Context-Control.sh rename to examples/qwen_image/model_training/lora/Qwen-Image-In-Context-Control-Union.sh index a4a4344..d241ad0 100644 --- a/examples/qwen_image/model_training/lora/Qwen-Image-Context-Control.sh +++ b/examples/qwen_image/model_training/lora/Qwen-Image-In-Context-Control-Union.sh @@ -8,11 +8,11 @@ accelerate launch examples/qwen_image/model_training/train.py \ --learning_rate 1e-4 \ --num_epochs 5 \ --remove_prefix_in_ckpt "pipe.dit." \ - --output_path "./models/train/Qwen-Image-Context-Control_lora" \ + --output_path "./models/train/Qwen-Image-In-Context-Control-Union_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 \ - --lora_checkpoint "models/DiffSynth-Studio/Qwen-Image-Context-Control/model.safetensors" \ + --lora_checkpoint "models/DiffSynth-Studio/Qwen-Image-In-Context-Control-Union/model.safetensors" \ --extra_inputs "context_image" \ --use_gradient_checkpointing \ --find_unused_parameters diff --git a/examples/qwen_image/model_training/validate_lora/Qwen-Image-Context-Control.py b/examples/qwen_image/model_training/validate_lora/Qwen-Image-In-Context-Control-Union.py similarity index 89% rename from examples/qwen_image/model_training/validate_lora/Qwen-Image-Context-Control.py rename to examples/qwen_image/model_training/validate_lora/Qwen-Image-In-Context-Control-Union.py index 1f3da52..83a93a3 100644 --- a/examples/qwen_image/model_training/validate_lora/Qwen-Image-Context-Control.py +++ b/examples/qwen_image/model_training/validate_lora/Qwen-Image-In-Context-Control-Union.py @@ -12,7 +12,7 @@ pipe = QwenImagePipeline.from_pretrained( ], tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"), ) -pipe.load_lora(pipe.dit, "models/train/Qwen-Image-Context-Control_lora/epoch-4.safetensors") +pipe.load_lora(pipe.dit, "models/train/Qwen-Image-In-Context-Control-Union_lora/epoch-4.safetensors") image = Image.open("data/example_image_dataset/canny/image_1.jpg").resize((1024, 1024)) prompt = "Context_Control. a dog" image = pipe(prompt=prompt, seed=0, context_image=image, height=1024, width=1024)