RockeyCoss/SPO
[CVPR 2025] Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization
This project helps artists, designers, and content creators generate more visually appealing images from text prompts. It takes your existing text-to-image diffusion models, like Stable Diffusion, and fine-tunes them to produce higher-quality, aesthetically pleasing images without sacrificing what your text prompt described. The end result is a diffusion model that generates beautiful images more consistently.
265 stars. No commits in the last 6 months.
Use this if you are using text-to-image models and want to consistently generate images that are not just accurate to your prompt but also highly aesthetic and visually refined.
Not ideal if your primary concern is generating images with perfect layout or specific factual correctness rather than general aesthetic quality.
Stars
265
Forks
11
Language
Python
License
MIT
Category
Last pushed
Apr 07, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/RockeyCoss/SPO"
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...