ChenWu98/cycle-diffusion

[ICCV 2023] A latent space for stochastic diffusion models

40
/ 100
Emerging

This project helps graphic designers, content creators, or marketers quickly transform existing images into new ones using text prompts. You input an original image and a text description of the desired new image, and it outputs a modified image that matches the new description while retaining characteristics of the original. This is ideal for anyone needing to generate variations of images without extensive manual editing or dataset training.

652 stars. No commits in the last 6 months.

Use this if you need to perform zero-shot image-to-image translation, meaning you want to modify an image using text without prior training on paired images.

Not ideal if you require precise control over every pixel of the output image or if your image editing tasks are not well-suited for descriptive text prompts.

image-editing content-creation digital-art visual-marketing graphic-design
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

652

Forks

36

Language

Python

License

Last pushed

Dec 31, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ChenWu98/cycle-diffusion"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.