Ka1b0/Foresight-Guidance
NeurIPS25 Spotlight | Classifier-free guidance (CFG) can be viewed as fixed-point iteration and thus be upgraded.
This project helps researchers and practitioners working with text-to-image diffusion models generate higher-quality images that better match their text descriptions. It takes existing diffusion models and their text prompts as input and produces more visually aligned and efficient image outputs. Anyone involved in developing or fine-tuning advanced image generation systems would find this useful.
Use this if you are a machine learning researcher or engineer looking to improve the image quality and computational efficiency of your text-to-image diffusion models.
Not ideal if you are an end-user simply generating images and not looking to dive into the underlying model guidance mechanisms.
Stars
9
Forks
—
Language
Python
License
MIT
Category
Last pushed
Nov 24, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Ka1b0/Foresight-Guidance"
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...