HVision-NKU/ImageCritic
Official implementation of ImageCritic (CVPR 2026)
This tool helps graphic designers, digital artists, and marketing professionals refine images generated by AI tools. It takes an AI-generated image and a reference image as input, then allows you to select specific areas to fix. The output is a corrected image where inconsistencies or errors in the selected region are aligned with the reference.
156 stars.
Use this if you need to fix small inconsistencies or misalignments in AI-generated images to match a reference, rather than generating an entirely new image.
Not ideal if you need to replace entire objects or make very large, fundamental changes to an AI-generated image.
Stars
156
Forks
7
Language
Python
License
—
Category
Last pushed
Mar 07, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/HVision-NKU/ImageCritic"
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...