junyanz/BicycleGAN
Toward Multimodal Image-to-Image Translation
This project helps graphic designers, e-commerce managers, or architects transform an image from one visual style to another, generating multiple plausible alternatives. For example, you can input a night scene photo and get various versions of what it might look like during the day, complete with different lighting and cloud patterns. This tool is ideal for anyone who needs to quickly create diverse visual representations from a single source image.
1,515 stars. No commits in the last 6 months.
Use this if you need to generate multiple visually distinct output images from a single input image (e.g., transforming a sketch into various shoe designs or a map into different aerial views).
Not ideal if you need to precisely control every detail of the output image or if you don't have pairs of corresponding images for training (e.g., night-to-day photos of the same scene).
Stars
1,515
Forks
252
Language
Python
License
—
Category
Last pushed
Aug 05, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/junyanz/BicycleGAN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
NVIDIA/pix2pixHD
Synthesizing and manipulating 2048x1024 images with conditional GANs
GaParmar/clean-fid
PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]
yuanming-hu/exposure
Learning infinite-resolution image processing with GAN and RL from unpaired image datasets,...
albertpumarola/GANimation
GANimation: Anatomically-aware Facial Animation from a Single Image (ECCV'18 Oral) [PyTorch]
wuhuikai/GP-GAN
Official Chainer implementation of GP-GAN: Towards Realistic High-Resolution Image Blending...