dome272/Paella

Official Implementation of Paella https://arxiv.org/abs/2211.07292v2

42
/ 100
Emerging

Operates on compressed, quantized latent spaces conditioned with CLIP embeddings to achieve high-fidelity image generation in under 10 steps and 500ms per image. Beyond text-to-image synthesis, supports latent space interpolation and image manipulations including inpainting, outpainting, and structural editing. Prioritizes accessibility with minimalistic codebases—training and sampling implementations fit under 140 lines—enabling rapid experimentation and community contribution.

748 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

748

Forks

53

Language

Jupyter Notebook

License

MIT

Last pushed

Oct 04, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/dome272/Paella"

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