AiArt-Gao/MATEBIT
[CVPR'23] Masked and Adaptive Transformer for Exemplar Based Image Translation (MATEBIT)
This project helps artists, designers, and e-commerce professionals create new images by applying the style from a reference image to a different content image. You provide a 'content' image (e.g., a sketch, a product photo) and an 'exemplar' image (e.g., a painting, a fashion model wearing an outfit), and it generates a new image that combines the content of the first with the style of the second. This is useful for tasks like virtual try-on or transferring artistic styles.
No commits in the last 6 months.
Use this if you need to generate high-quality images where you precisely control the style by providing a specific example image, especially for tasks like virtual fashion try-on, artistic style transfer to photos, or generating diverse portrait styles.
Not ideal if you need to generate images from text prompts or manipulate existing images without relying on a specific style exemplar.
Stars
95
Forks
5
Language
Python
License
MIT
Category
Last pushed
Jan 29, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/AiArt-Gao/MATEBIT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yunjey/domain-transfer-network
TensorFlow Implementation of Unsupervised Cross-Domain Image Generation
taesungp/contrastive-unpaired-translation
Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV...
PaddlePaddle/PaddleGAN
PaddlePaddle GAN library, including lots of interesting applications like First-Order motion...
tohinz/ConSinGAN
PyTorch implementation of "Improved Techniques for Training Single-Image GANs" (WACV-21)
sagiebenaim/DistanceGAN
Pytorch implementation of "One-Sided Unsupervised Domain Mapping" NIPS 2017