Qwen-Image 图像结构控制模型

模型介绍

本模型是基于 Qwen-Image 训练的图像局部重绘模型模型，模型结构为 ControlNet，可根据对图像的局部区域进行重绘。训练框架基于 DiffSynth-Studio 构建，采用的数据集是 Qwen-Image-Self-Generated-Dataset。

这个模型同时兼容 Qwen-Image 和 Qwen-Image-Edit，在 Qwen-Image 上可进行局部重绘，在 Qwen-Image-Edit 上可编辑指定区域。

效果展示

输入Prompt	输入图	重绘图
A robot with wings and a hat standing in a colorful garden with flowers and butterflies.
A girl in a school uniform stands gracefully in front of a vibrant stained glass window with colorful geometric patterns.
A small wooden boat battles against towering, crashing waves in a stormy sea.

局限性

• 基于 ControlNet 结构的 Inpaint 模型可能会导致重绘区域与非重绘区域的边界不和谐。
• 模型基于矩形框的重绘数据训练，对非矩形区域的重绘泛化性可能不佳。

推理代码

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

Qwen-Image：

import torch
from PIL import Image
from modelscope import dataset_snapshot_download
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig, ControlNetInput


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-Inpaint", 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="inpaint/*.jpg"
)
prompt = "a cat with sunglasses"
controlnet_image = Image.open("./data/example_image_dataset/inpaint/image_1.jpg").convert("RGB").resize((1328, 1328))
inpaint_mask = Image.open("./data/example_image_dataset/inpaint/mask.jpg").convert("RGB").resize((1328, 1328))
image = pipe(
    prompt, seed=0,
    input_image=controlnet_image, inpaint_mask=inpaint_mask,
    blockwise_controlnet_inputs=[ControlNetInput(image=controlnet_image, inpaint_mask=inpaint_mask)],
    num_inference_steps=40,
)
image.save("image.jpg")

Qwen-Image-Edit：

import torch
from PIL import Image
from modelscope import dataset_snapshot_download
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig, ControlNetInput


pipe = QwenImagePipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
        ModelConfig(model_id="Qwen/Qwen-Image-Edit", 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-Inpaint", origin_file_pattern="model.safetensors"),
    ],
    tokenizer_config=None,
    processor_config=ModelConfig(model_id="Qwen/Qwen-Image-Edit", origin_file_pattern="processor/"),
)

dataset_snapshot_download(
    dataset_id="DiffSynth-Studio/example_image_dataset",
    local_dir="./data/example_image_dataset",
    allow_file_pattern="inpaint/*.jpg"
)
prompt = "Put sunglasses on this cat"
controlnet_image = Image.open("./data/example_image_dataset/inpaint/image_1.jpg").convert("RGB").resize((1328, 1328))
inpaint_mask = Image.open("./data/example_image_dataset/inpaint/mask.jpg").convert("RGB").resize((1328, 1328))
image = pipe(
    prompt, seed=0,
    input_image=controlnet_image, inpaint_mask=inpaint_mask,
    blockwise_controlnet_inputs=[ControlNetInput(image=controlnet_image, inpaint_mask=inpaint_mask)],
    num_inference_steps=40,
    edit_image=controlnet_image, # add edit_image here.
)
image.save("image.jpg")