tgxs002/align_sd
Better Aligning Text-to-Image Models with Human Preference. ICCV 2023
This project helps graphic designers, content creators, and marketers generate higher-quality images using AI. By learning from human preferences, it takes your text prompts and produces images that better match your vision, reducing common flaws like distorted limbs or faces. The end result is visually appealing images that require less editing.
294 stars. No commits in the last 6 months.
Use this if you frequently use text-to-image AI tools like Stable Diffusion and want to improve the quality and accuracy of the images generated from your prompts.
Not ideal if you need to generate images that intentionally include surreal or abstract distortions, as this tool is designed to reduce such artifacts.
Stars
294
Forks
10
Language
Python
License
Apache-2.0
Category
Last pushed
Jul 14, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/tgxs002/align_sd"
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...