---
title: rt132and74QWEN
canonical_url: "https://www.modelscope.cn/models/wissuny/rt132and74QWEN"
md_url: "https://www.modelscope.cn/models/wissuny/rt132and74QWEN.md"
repository: wissuny/rt132and74QWEN
chinese_name: "溶图与场景视角调整qwen2511"
last_updated: 2026-06-05
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: 471.9M
tensor_type:
  - BF16
library_name:
  - pytorch
  - lora
  - safetensors
supports_inference: img2img
downloads: 31
stars: 0
tags:
  - LoRA
  - text-to-image
---

# rt132and74QWEN

> rt132and74QWEN - wissuny 在 ModelScope 开源的模型。溶图+根据主体改变场景视角（改视角时强度可增大）。 提示词：Fix the subject in the image, optimize the scene effect, and achieve interactive fusion between the subject and the scene, realistic lighting. 改视角增加：Reconstruct the scene based on the…

wissuny/rt132and74QWEN 是 ModelScope 魔搭社区上的 471.9M 参数text-to-image-synthesis模型，采用 Apache License 2.0 许可，基于 Qwen/Qwen-Image-Edit-2511 构建，并支持在线推理（img2img）。

- **Repository**: wissuny/rt132and74QWEN
- **License**: Apache License 2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 471.9M
- **Base model**: Qwen/Qwen-Image-Edit-2511
- **Online inference**: img2img
- **Tags**: LoRA, text-to-image
- **Downloads**: 31
- **Stars**: 0
- **Last updated**: 2026-06-05

Source: https://www.modelscope.cn/models/wissuny/rt132and74QWEN

---

# rt132and74Qwen

## 模型介绍

溶图+根据主体改变场景视角（改视角时强度可增大）。
提示词：Fix the subject in the image, optimize the scene effect, and achieve interactive fusion between the subject and the scene, realistic lighting.
改视角增加：Reconstruct the scene based on the subject's perspective and vanishing point.




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：74
* 总训练步数：4000
* 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="wissuny/rt132and74QWEN", origin_file_pattern="rt132and74QWEN_c1-st4000.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")
```