|
Download README.md from DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny: direct link, hf CLI and curl.
- Browser
- Download file 2.47 kB
-
https://huggingface.co/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny/resolve/main/README.md
- Command line
-
hf download hf://DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny/README.md
-
curl -L -o README.md https://huggingface.co/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny/resolve/main/README.md
2.47 kB
| license: apache-2.0 | |
| # Qwen-Image Image Structure Control Model | |
|  | |
| ## Model Introduction | |
| This model is an image structure control model trained based on [Qwen-Image](https://www.modelscope.cn/models/Qwen/Qwen-Image), with the ControlNet architecture. It can control the structure of generated images using edge detection (Canny) maps. The training framework is built on [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio), and the dataset used is [BLIP3o](https://modelscope.cn/datasets/BLIP3o/BLIP3o-60k). | |
| ## Result Demonstration | |
| |Canny Edge Map|Generated Image 1|Generated Image 2| | |
| |-|-|-| | |
| |||| | |
| |||| | |
| |||| | |
| ## Inference Code | |
| ``` | |
| git clone https://github.com/modelscope/DiffSynth-Studio.git | |
| cd DiffSynth-Studio | |
| pip install -e . | |
| ``` | |
| ```python | |
| from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig, ControlNetInput | |
| from PIL import Image | |
| import torch | |
| from modelscope import dataset_snapshot_download | |
| 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"), | |
| ModelConfig(model_id="DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny", origin_file_pattern="model.safetensors"), | |
| ], | |
| tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"), | |
| ) | |
| dataset_snapshot_download( | |
| dataset_id="DiffSynth-Studio/example_image_dataset", | |
| local_dir="./data/example_image_dataset", | |
| allow_file_pattern="canny/image_1.jpg" | |
| ) | |
| controlnet_image = Image.open("data/example_image_dataset/canny/image_1.jpg").resize((1328, 1328)) | |
| ``` | |
| prompt = "A little dog with shiny, soft fur and lively eyes, set in a spring courtyard with cherry blossoms falling, creating a beautiful and warm atmosphere." | |
| image = pipe( | |
| prompt, seed=0, | |
| blockwise_controlnet_inputs=[ControlNetInput(image=controlnet_image)] | |
| ) | |
| image.save("image.jpg") | |
| ``` |