---
frameworks:
- Pytorch
license: Apache License 2.0
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 图像结构控制模型 - Depth ControlNet

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

## 模型介绍

本模型是基于 [Qwen-Image](https://www.modelscope.cn/models/Qwen/Qwen-Image) 训练的图像结构控制模型，模型结构为 ControlNet，可根据深度(Depth)图控制生成的图像结构。训练框架基于 [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio) 构建，采用的数据集是 [BLIP3o](https://modelscope.cn/datasets/BLIP3o/BLIP3o-60k)。


## 效果展示

|结构图|生成图1|生成图2|
|-|-|-|
|![](./assets/depth2.jpg)|![](./assets/image2_0.jpg)|![](./assets/image2_1.jpg)|
|![](./assets/depth3.jpg)|![](./assets/image3_0.jpg)|![](./assets/image3_1.jpg)|
|![](./assets/depth1.jpg)|![](./assets/image1_0.jpg)|![](./assets/image1_1.jpg)|

## 推理代码
```
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-Depth", 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="depth/image_1.jpg"
)

controlnet_image = Image.open("data/example_image_dataset/depth/image_1.jpg").resize((1328, 1328))

prompt = "精致肖像，水下少女，蓝裙飘逸，发丝轻扬，光影透澈，气泡环绕，面容恬静，细节精致，梦幻唯美。"
image = pipe(
    prompt, seed=0,
    blockwise_controlnet_inputs=[ControlNetInput(image=controlnet_image)]
)
image.save("image.jpg")

```