hila-chefer/Conceptor
Official implementation of the paper The Hidden Language of Diffusion Models
This project helps AI researchers and practitioners understand how text-to-image diffusion models interpret concepts. You input a text concept (like "a president") or a specific image, and it outputs a breakdown of that concept into simple, human-understandable textual elements. This allows you to see the surprising visual connections and biases within the model's internal representations.
No commits in the last 6 months.
Use this if you need to explain, debug, or deeply understand the latent space and concept representation within your text-to-image diffusion models.
Not ideal if you are looking to generate images directly, fine-tune models, or evaluate image quality.
Stars
78
Forks
—
Language
—
License
—
Category
Last pushed
Jan 24, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/hila-chefer/Conceptor"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
siliconflow/onediff
OneDiff: An out-of-the-box acceleration library for diffusion models.
wooyeolbaek/attention-map-diffusers
🚀 Cross attention map tools for huggingface/diffusers
jina-ai/discoart
🪩 Create Disco Diffusion artworks in one line
chengzeyi/stable-fast
https://wavespeed.ai/ Best inference performance optimization framework for HuggingFace...
hkproj/pytorch-stable-diffusion
Stable Diffusion implemented from scratch in PyTorch