Qwen-Image Image Structure Control Model - Depth ControlNet

Model Introduction

This model is an image structure control model based on Qwen-Image, with a ControlNet architecture that enables structural control of generated images using depth maps. The training framework is built upon DiffSynth-Studio, and the dataset used for training is BLIP3o.

Result Demonstration

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-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 = "Exquisite portrait, underwater girl, flowing blue dress, gently floating hair, translucent lighting, surrounded by bubbles, serene expression, intricate details, dreamy and ethereal." image = pipe( prompt, seed=0, blockwise_controlnet_inputs=[ControlNetInput(image=controlnet_image)] ) image.save("image.jpg")