---
title: FLUX.1-Kontext-dev-lora-SuperOutpainting
canonical_url: "https://www.modelscope.cn/models/DiffSynth-Studio/FLUX.1-Kontext-dev-lora-SuperOutpainting"
md_url: "https://www.modelscope.cn/models/DiffSynth-Studio/FLUX.1-Kontext-dev-lora-SuperOutpainting.md"
repository: DiffSynth-Studio/FLUX.1-Kontext-dev-lora-SuperOutpainting
chinese_name: "图像外扩 - Kontext 图像编辑 LoRA"
last_updated: 2025-07-08
license: "Apache License 2.0"
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - "MusePublic/FLUX.1-Kontext-Dev@v1"
base_model_relation: adapter
parameters: 153.2M
tensor_type:
  - BF16
  - F32
library_name:
  - pytorch
  - lora
  - safetensors
frameworks:
  - Pytorch
supports_inference: img2img
downloads: 2331
stars: 34
tags:
  - LoRA
  - text-to-image
---

# FLUX.1-Kontext-dev-lora-SuperOutpainting

> FLUX.1-Kontext-dev-lora-SuperOutpainting - DiffSynth-Studio 在 ModelScope 开源的模型。高分辨率修复 - Kontext 图像编辑 LoRA

DiffSynth-Studio/FLUX.1-Kontext-dev-lora-SuperOutpainting 是 ModelScope 魔搭社区上的 153.2M 参数text-to-image-synthesis模型，采用 Apache License 2.0 许可，基于 MusePublic/FLUX.1-Kontext-Dev@v1 构建，并支持在线推理（img2img）。

- **Repository**: DiffSynth-Studio/FLUX.1-Kontext-dev-lora-SuperOutpainting
- **License**: Apache License 2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 153.2M
- **Base model**: MusePublic/FLUX.1-Kontext-Dev@v1
- **Online inference**: img2img
- **Tags**: LoRA, text-to-image
- **Downloads**: 2331
- **Stars**: 34
- **Last updated**: 2025-07-08

Source: https://www.modelscope.cn/models/DiffSynth-Studio/FLUX.1-Kontext-dev-lora-SuperOutpainting

---

# 高分辨率修复 - Kontext 图像编辑 LoRA

## 模型介绍

本 LoRA 模型是基于 [Kontext](https://www.modelscope.cn/models/black-forest-labs/FLUX.1-Kontext-dev) 模型和 [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio) 训练的 LoRA 模型，使用本模型后，可输入指令 `Outpaint the image.` 进行图像外扩。

## 模型效果

||样例 1|样例 2|样例 3|
|-|-|-|-|
|Prompt|Outpaint the image.|Outpaint the image.| Outpaint the image.|
|输入|![](./assets/image1_0.png)|![](./assets/image2_0.png)|![](./assets/image3_0.png)|
|外扩图|![](./assets/image1_1.png)|![](./assets/image2_1.png)|![](./assets/image3_1.png)|

||样例 4|样例 5|样例 6|
|-|-|-|-|
|Prompt|Outpaint the image. A chicken-headed man in suspenders is playing the basketball.|Outpaint the image. A man in suspenders is playing the basketball.| Outpaint the image. A chicken-headed man in suspenders is playing the basketball with a white background. |
|输入|![](./assets/image4_0.jpg)|![](./assets/image5_0.png)|![](./assets/image6_0.png)|
|外扩图|![](./assets/image4_1.png)|![](./assets/image5_1.png)|![](./assets/image6_1.png)|

## 使用说明

本模型基于框架 [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio/tree/main/examples/flux) 训练，请先安装

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

```python
import torch
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
from PIL import Image
from modelscope import snapshot_download

snapshot_download("DiffSynth-Studio/FLUX.1-Kontext-dev-lora-SuperOutpainting", cache_dir="./models")
pipe = FluxImagePipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
        ModelConfig(model_id="black-forest-labs/FLUX.1-Kontext-dev", origin_file_pattern="flux1-kontext-dev.safetensors"),
        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
    ],
)
pipe.load_lora(pipe.dit, "models/DiffSynth-Studio/FLUX.1-Kontext-dev-lora-SuperOutpainting/model.safetensors", alpha=1)

image = Image.open("your_image.jpg")
image = pipe(
    prompt="Outpaint the image.",
    kontext_images=image,
    embedded_guidance=2.5,
    seed=0,
)
image.save("output.jpg")
```