SahilCarterr/Qwen-Image-Blockwise-ControlNet-Canny

Qwen-Image Image Structure Control Model

Model Introduction

This model is a structure control model for images, trained based on Qwen-Image. The model architecture is ControlNet, capable of controlling the generated image structure according to edge detection (Canny) maps. The training framework is built upon DiffSynth-Studio and the dataset used is BLIP3o。

Effect Demonstration

Structure Map	Generated Image 1	Generated Image 2

Inference Code

git clone https://github.com/modelscope/DiffSynth-Studio.git  
cd DiffSynth-Studio
pip install -e .

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 puppy with shiny, smooth fur and lively eyes, with a spring garden full of cherry blossoms as the background, beautiful and warm."
image = pipe(
    prompt, seed=0,
    blockwise_controlnet_inputs=[ControlNetInput(image=controlnet_image)]
)
image.save("image.jpg")

---

license: apache-2.0