---
title: 5614645
canonical_url: "https://www.modelscope.ai/models/xiaohai001/5614645"
md_url: "https://www.modelscope.ai/models/xiaohai001/5614645.md"
repository: xiaohai001/5614645
last_updated: 2026-06-07
license: "Apache License 2.0"
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - Qwen/Qwen-Image-Edit-2511
base_model_relation: adapter
parameters: 589.8M
tensor_type:
  - BF16
library_name:
  - pytorch
  - lora
  - safetensors
frameworks:
  - pytorch
supports_inference: txt2img
downloads: 182
stars: 0
tags:
  - LoRA
  - text-to-image
---

# 5614645

> 5614645 - An open-source model by xiaohai001 on ModelScope. 本模型依托魔搭社区（ModelScope）AIGC专区模型训练环境与算力完成训练。

xiaohai001/5614645 is a 589.8M-parameter text-to-image-synthesis model on ModelScope. licensed under Apache License 2.0. derived from Qwen/Qwen-Image-Edit-2511. and supports online inference (txt2img).

- **Repository**: xiaohai001/5614645
- **License**: Apache License 2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 589.8M
- **Base model**: Qwen/Qwen-Image-Edit-2511
- **Online inference**: txt2img
- **Tags**: LoRA, text-to-image
- **Downloads**: 182
- **Stars**: 0
- **Last updated**: 2026-06-07

Source: https://www.modelscope.ai/models/xiaohai001/5614645

---

# 溶图千问

## 模型介绍

本模型依托魔搭社区（ModelScope）AIGC专区[模型训练](https://modelscope.cn/aigc/modelTraining)环境与算力完成训练。

* 模型类型：LoRA
* 基础模型：[Qwen/Qwen-Image-Edit-2511](https://modelscope.cn/models/Qwen/Qwen-Image-Edit-2511)
* 训练代码：[DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio)
* 训练数据量：59
* 总训练步数：5000
* 开源协议：Apache-2.0

## 推理代码

安装 [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio)：

```bash
pip install diffsynth
```

开始推理：

```python
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
from PIL import Image
import torch

pipe = QwenImagePipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
        ModelConfig(model_id="Qwen/Qwen-Image-Edit-2511", 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"),
    ],
    processor_config=ModelConfig(model_id="Qwen/Qwen-Image-Edit", origin_file_pattern="processor/"),
)
pipe.load_lora(pipe.dit, ModelConfig(model_id="xiaohai001/5614645", origin_file_pattern="5614645_c1-st5000.safetensors"))
prompt = "Convert the image style to anime style."
edit_image = Image.open("your_image.jpg")
image = pipe(prompt, edit_image=[edit_image], edit_image_auto_resize=True, zero_cond_t=True)
image.save("image.jpg")
```