garibida/cross-image-attention
Officail Implementation for "Cross-Image Attention for Zero-Shot Appearance Transfer"
This tool helps creative professionals or visual artists combine the visual style of one image with the structure of another. You provide two images: one with the desired shape or layout (e.g., a cat's pose) and another with the desired look and feel (e.g., a painting style or a specific texture). The output is a new image where the first image's structure adopts the second image's appearance.
395 stars. No commits in the last 6 months.
Use this if you need to quickly generate new images that blend the composition of one photo with the artistic style or texture of another, without needing complex editing software or manual adjustments.
Not ideal if you need pixel-perfect accuracy or intricate, detailed modifications that require fine-grained control over individual elements, as this tool focuses on broader appearance transfer.
Stars
395
Forks
27
Language
Python
License
MIT
Category
Last pushed
May 05, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/garibida/cross-image-attention"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jolibrain/joliGEN
Generative AI Image and Video Toolset with GANs and Diffusion for Real-World Applications
zhangmozhe/Deep-Exemplar-based-Video-Colorization
The source code of CVPR 2019 paper "Deep Exemplar-based Video Colorization".
naver-ai/StyleKeeper
Official Pytorch implementation of "StyleKeeper: Prevent Content Leakage using Negative Visual...
un1tz3r0/finetunepixelartdiffusion
Fine tune a pixelart diffusion model with isometric dataset.
lixiaowen-xw/DiffuEraser
DiffuEraser is a diffusion model for video inpainting, which performs great content completeness...