---
frameworks:
- Pytorch
tasks:
- text-to-image-synthesis

#model-type:
##如 gpt、phi、llama、chatglm、baichuan 等
#- gpt

#domain:
##如 nlp、cv、audio、multi-modal
#- nlp

#language:
##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
#- cn

#metrics:
##如 CIDEr、Blue、ROUGE 等
#- CIDEr

#tags:
##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
#- pretrained

#tools:
##如 vllm、fastchat、llamacpp、AdaSeq 等
#- vllm
base_model:
  - Qwen/Qwen-Image
base_model_relation: adapter
---
# Qwen-Image Image Structure Control Model

![](./assets/title.png)

## Model Introduction

This model is a structure control model for images, trained based on [Qwen-Image](https://www.modelscope.cn/models/Qwen/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](https://github.com/modelscope/DiffSynth-Studio) and the dataset used is [BLIP3o](https://modelscope.cn/datasets/BLIP3o/BLIP3o-60k)。


## Effect Demonstration

|Structure Map|Generated Image 1|Generated Image 2|
|-|-|-|
|![](./assets/canny_3.png)|![](./assets/image_3_1.png)|![](./assets/image_3_2.png)|
|![](./assets/canny_2.png)|![](./assets/image_2_1.png)|![](./assets/image_2_2.png)|
|![](./assets/canny_1.png)|![](./assets/image_1_1.png)|![](./assets/image_1_2.png)|

## 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 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
---