nupurkmr9/concept-ablation
Ablating Concepts in Text-to-Image Diffusion Models (ICCV 2023)
This helps creators and content managers remove specific images, styles, or concepts like copyrighted art or individual subjects from AI image generation models. You feed in a trained text-to-image model and specify the concept to remove, and it outputs a modified model that no longer generates that specific content, replacing it with a more general concept. This is for professionals managing AI-generated assets, aiming to avoid copyright infringement or unwanted content.
168 stars. No commits in the last 6 months.
Use this if you need to modify a text-to-image AI model to prevent it from generating specific copyrighted material, unique artistic styles, or particular image instances, without rebuilding the model from scratch.
Not ideal if you need to add new concepts or broadly alter the model's style, as this tool focuses specifically on targeted removal and replacement with a more general concept.
Stars
168
Forks
21
Language
Python
License
MIT
Category
Last pushed
Dec 21, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/nupurkmr9/concept-ablation"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
UCSC-VLAA/story-iter
[ICLR 2026] A Training-free Iterative Framework for Long Story Visualization
PaddlePaddle/PaddleMIX
Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks,...
keivalya/mini-vla
a minimal, beginner-friendly VLA to show how robot policies can fuse images, text, and states to...
adobe-research/custom-diffusion
Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)
byliutao/1Prompt1Story
🔥ICLR 2025 (Spotlight) One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation...