---
title: AuraSR-v2
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/AuraSR-v2"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/AuraSR-v2.md"
repository: AI-ModelScope/AuraSR-v2
last_updated: 2024-08-07
license: apache-2.0
pipeline_tag: image-to-image
tasks:
  - image-to-image
parameters: 617.6M
tensor_type:
  - F32
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 2516
stars: 1
tags:
  - art
  - pytorch
  - super-resolution
---

# AuraSR-v2

> AuraSR-v2 - AI-ModelScope 在 ModelScope 开源的模型。GAN-based Super-Resolution for upscaling generated images, a variation of the GigaGAN paper for image-conditioned upscaling. Torch implementation is based on the unofficial lucidrains/gigagan-pytorch repository.

AI-ModelScope/AuraSR-v2 是 ModelScope 魔搭社区上的 617.6M 参数image-to-image模型，采用 apache-2.0 许可。

- **Repository**: AI-ModelScope/AuraSR-v2
- **License**: apache-2.0
- **Tasks**: image-to-image
- **Parameters**: 617.6M
- **Tags**: art, pytorch, super-resolution
- **Downloads**: 2516
- **Stars**: 1
- **Last updated**: 2024-08-07

Source: https://www.modelscope.cn/models/AI-ModelScope/AuraSR-v2

---

# AuraSR-v2 
![aurasr example](https://storage.googleapis.com/falserverless/gallery/aurasr-animated.webp)

GAN-based Super-Resolution for upscaling generated images, a variation of the [GigaGAN](https://mingukkang.github.io/GigaGAN/) paper for image-conditioned upscaling. Torch implementation is based on the unofficial [lucidrains/gigagan-pytorch](https://github.com/lucidrains/gigagan-pytorch) repository.

## Usage

```bash
$ pip install aura-sr
```

```python
from aura_sr import AuraSR

aura_sr = AuraSR.from_pretrained("fal/AuraSR-v2")
```

```python
import requests
from io import BytesIO
from PIL import Image

def load_image_from_url(url):
    response = requests.get(url)
    image_data = BytesIO(response.content)
    return Image.open(image_data)

image = load_image_from_url("https://mingukkang.github.io/GigaGAN/static/images/iguana_output.jpg").resize((256, 256))
upscaled_image = aura_sr.upscale_4x_overlapped(image)
```