junyanz/BicycleGAN

Toward Multimodal Image-to-Image Translation

49
/ 100
Emerging

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).

graphic-design image-transformation visual-prototyping e-commerce-imaging architectural-visualization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

1,515

Forks

252

Language

Python

License

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.