huggingface/pytorch-pretrained-BigGAN

🦋A PyTorch implementation of BigGAN with pretrained weights and conversion scripts.

59
/ 100
Established

This project helps artists, designers, or content creators generate high-fidelity, photorealistic images from simple text descriptions. You provide a concept (like "soap bubble" or "mushroom") and a randomness setting, and it outputs unique, realistic images at various resolutions (128x128, 256x256, or 512x512 pixels). It's ideal for anyone looking to quickly create visual assets based on semantic categories without needing complex artistic skills.

1,045 stars. No commits in the last 6 months. Available on PyPI.

Use this if you need to rapidly prototype visual ideas or generate unique imagery based on common object categories, using a simple text input.

Not ideal if you need to generate images from scratch using your own custom training data, or if you require fine-grained control over specific image elements beyond semantic categories.

generative-art image-synthesis content-creation visual-prototyping digital-design
Stale 6m
Maintenance 0 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 24 / 25

How are scores calculated?

Stars

1,045

Forks

178

Language

Python

License

MIT

Last pushed

Feb 12, 2021

Commits (30d)

0

Dependencies

5

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/huggingface/pytorch-pretrained-BigGAN"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.