maple-research-lab/SIM

Inference-only implementation of "One-Step Diffusion Distillation through Score Implicit Matching" [NIPS 2024]

31
/ 100
Emerging

This project helps generate high-quality images from text descriptions or unconditional prompts significantly faster than traditional methods. It takes a text prompt or no input for unconditional generation and produces a high-quality image. This would be used by content creators, graphic designers, and AI artists who need to quickly generate diverse images without sacrificing quality.

No commits in the last 6 months.

Use this if you need to rapidly create diverse, high-quality images from text prompts or for general image generation, without waiting for multiple processing steps.

Not ideal if you require fine-tuning a diffusion model for custom datasets or if your workflow specifically demands multi-step generation for incremental artistic control.

AI art generation text-to-image creation digital content creation image synthesis graphic design
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

83

Forks

3

Language

Python

License

AGPL-3.0

Last pushed

Nov 17, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/maple-research-lab/SIM"

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