Ir para o conteúdo
ModelListadosExterno
Browse files

AuraSR v2

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.

Fontehuggingface.co/research101/AuraSR-v2/tree/ff452185a7c8b51206dd62c21c292e7baad5c3a3
TipoOtherVersãoRevision ff45218Bnota

Fonte do modelo

Tipo
Other
Tamanho do arquivo
2,30 GB
Versão
vRevision ff45218
Atualizado
26 de out. de 2026
Downloads
5
Fonte
Hugging Face

Descrição da fonte

AuraSR-v2

aurasr example

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.

Usage

$ pip install aura-sr

from aura_sr import AuraSR

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

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)

Fontes

1 fonte
Hugging FacePrimárioVersão ff452185a7c8b51206dd62c21c292e7baad5c3a3
huggingface.co/research101/AuraSR-v2/tree/ff452185a7c8b51206dd62c21c292e7baad5c3a3

Verificado 26 de out.

Download files

Artefatos de modelo

2 artefatos

model.ckpt

ckpt · 2,30 GB · SHA-256 8028efd10725…8b7a · Hugging Face

Download file

model.safetensors

safetensors · 2,30 GB · SHA-256 8a80b4546f3f…4dde · Hugging Face

Download file

Trechos de fonte

3 trechos
Readme8 de ago.huggingface.co/research101/AuraSR-v2

--- license: apache-2.0 tags: - art - pytorch - super-resolution pipeline_tag: image-to-image --- # 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) ```

Note26 de out.huggingface.co/research101/AuraSR-v2

Source context: 5 downloads · 0 likes · Pipeline image-to-image · Repo research101/AuraSR-v2

Note8 de ago.huggingface.co/research101/AuraSR-v2

Source context: 6 downloads · 0 likes · Pipeline image-to-image · Repo research101/AuraSR-v2