afiaka87/clip-guided-diffusion

A CLI tool/python module for generating images from text using guided diffusion and CLIP from OpenAI.

51
/ 100
Established

Combines diffusion model iterative refinement with CLIP-guided optimization and adjustable timestep respacing (25-1000 steps) for quality-speed tradeoffs. Supports weighted multi-prompt composition, image-to-image blending with VGG perceptual loss, and non-square aspect ratio generation. Includes performance optimizations like reduced CLIP frequency, progressive cutout sampling, and cached augmentation coordinates to accelerate generation by 10-30 seconds.

460 stars.

No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

460

Forks

60

Language

Python

License

MIT

Last pushed

Dec 31, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/afiaka87/clip-guided-diffusion"

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