LiyaoJiang1998/RAISE
"RAISE: Requirement-Adaptive Evolutionary Refinement for Training-Free Text-to-Image Alignment", accepted to CVPR'26.
This project helps graphic designers, marketers, or content creators generate high-quality images from complex text descriptions. You input a detailed text prompt, and it outputs an image that precisely matches your requirements, even for prompts with multiple objects and specific attributes. This is for anyone who needs to create visually accurate images from text without extensive manual adjustments.
Use this if you need to reliably generate complex images from detailed text prompts and want to minimize the time spent on manual refinement or re-generation.
Not ideal if you are looking for a simple, fast image generation tool for very basic prompts without intricate details or specific object relationships.
Stars
9
Forks
2
Language
Python
License
—
Category
Last pushed
Mar 03, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/LiyaoJiang1998/RAISE"
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...