Downloads · 30 days
169
1% of all-time downloads
AuraSR
fal/AuraSR
AuraSR is a machine learning model from fal. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as cc.
All-time downloads
16.2K
Public
Parameters
618M
7.4 GB on disk
Likes
308
Public
Repo makeup
Click a slice to open those files.
.ckpt2.5 GB · 50%
At a glance
- Library
- transformers
- License
- cc
- Access
- Public
- Created
- Jun 25, 2024
- Updated
- Jul 15, 2024
- SHA
- 8b70681a
Model card
From the Hugging Face model README
AuraSR
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-ai/AuraSR")
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(image)
- Library
- transformers
- License
- cc
- Created
- Jun 25, 2024
- Updated
- Jul 15, 2024