Con6924/SPM

Official implementation of paper "One-dimensional Adapter to Rule Them All: Concepts, Diffusion Models and Erasing Applications".

39
/ 100
Emerging

This tool helps users control the content generated by diffusion models, specifically by preventing or suppressing unwanted concepts from appearing in images. You provide a diffusion model and specify a concept to remove (e.g., 'cat' or 'Van Gogh style'), and it outputs a modified model that avoids generating that concept. It's ideal for artists, marketers, or content creators who use AI to generate images but need to ensure specific elements are excluded.

152 stars. No commits in the last 6 months.

Use this if you need to reliably remove or reduce the presence of a specific concept, object, or style from images generated by a diffusion model without needing to retrain the entire model or provide new data.

Not ideal if you need to precisely replace or add concepts, as this tool is designed for concept suppression rather than comprehensive editing.

AI-art content-moderation image-generation brand-safety digital-design
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

152

Forks

14

Language

Python

License

Apache-2.0

Last pushed

Dec 28, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Con6924/SPM"

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