tuananhbui89/Erasing-Adversarial-Preservation
NeurIPS 2024 - Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation
This project helps AI developers and researchers refine text-to-image diffusion models like Stable Diffusion. It allows you to remove specific undesirable concepts (e.g., nudity, certain objects, or artistic styles) from a trained model while preserving its ability to generate other, unrelated content effectively. You provide a diffusion model and specify the concepts to erase, and it outputs a modified model that no longer generates the unwanted content.
No commits in the last 6 months.
Use this if you need to fine-tune a text-to-image diffusion model to prevent the generation of specific unwanted concepts, ensuring the model remains high-quality for other content.
Not ideal if you are an end-user simply generating images and not modifying the underlying AI model.
Stars
17
Forks
—
Language
Python
License
—
Category
Last pushed
Dec 05, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/tuananhbui89/Erasing-Adversarial-Preservation"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
huggingface/diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
bghira/SimpleTuner
A general fine-tuning kit geared toward image/video/audio diffusion models.
mcmonkeyprojects/SwarmUI
SwarmUI (formerly StableSwarmUI), A Modular Stable Diffusion Web-User-Interface, with an...
nateraw/stable-diffusion-videos
Create 🔥 videos with Stable Diffusion by exploring the latent space and morphing between text prompts
TheDesignFounder/DreamLayer
Benchmark diffusion models faster. Automate evals, seeds, and metrics for reproducible results.