PITI-Synthesis/PITI
PITI: Pretraining is All You Need for Image-to-Image Translation
This project helps graphic designers, digital artists, or anyone creating visual content to quickly generate realistic images from simple inputs. You provide an outline like a sketch or a mask (a basic colored shape indicating objects), and the system generates a high-quality, detailed image. This is useful for quickly visualizing concepts or expanding on basic visual ideas.
502 stars. No commits in the last 6 months.
Use this if you need to transform simple visual inputs like sketches or semantic masks into detailed, photorealistic images.
Not ideal if you need to edit or manipulate existing images directly rather than generating new ones from outlines.
Stars
502
Forks
26
Language
Python
License
MIT
Category
Last pushed
Jun 02, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/PITI-Synthesis/PITI"
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