WindVChen/Diff-Harmonization
A novel zero-shot image harmonization method based on Diffusion Model Prior.
This project helps graphic designers, digital artists, and photographers seamlessly blend foreground elements into new backgrounds. You provide a composite image (an object cut out and placed onto a new scene) and a mask image defining the object. The system automatically adjusts the foreground's lighting and colors to match the new background, producing a cohesive, realistic final image.
147 stars.
Use this if you need to integrate cut-out images into diverse backgrounds without extensive manual color correction or if you're working with many images and want to automate the harmonization process.
Not ideal if you don't have a high-end GPU with at least 20GB of memory, or if you need extremely fast processing for real-time applications.
Stars
147
Forks
10
Language
Python
License
Apache-2.0
Category
Last pushed
Nov 25, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/WindVChen/Diff-Harmonization"
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...