CFGpp-diffusion/CFGpp
Official repository for "CFG++: manifold-constrained classifier free guidance for diffusion models" (ICLR2025)
This project offers an improved way to generate images from text descriptions using diffusion models, or to accurately invert images back to their original noise representation. By using CFG++, you can get higher quality images that better match your text prompts, or achieve better image editing results. This is for AI practitioners, researchers, and developers working with generative AI to create, modify, or analyze images based on text.
238 stars. No commits in the last 6 months.
Use this if you need to generate high-quality images from text or perform precise image inversion/editing using diffusion models, especially if you're encountering issues like mode collapse or poor adherence to text prompts with standard methods.
Not ideal if you are looking for a simple, out-of-the-box image generation tool without diving into diffusion model specifics.
Stars
238
Forks
7
Language
Python
License
—
Category
Last pushed
Mar 21, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/CFGpp-diffusion/CFGpp"
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...