JIA-Lab-research/RIVAL

[NeurIPS 2023 Spotlight] Real-World Image Variation by Aligning Diffusion Inversion Chain

36
/ 100
Emerging

This project helps graphic designers, marketers, and content creators quickly generate new variations of existing images while preserving their core content and style. You provide a reference image or text prompt, and it outputs a set of similar images, allowing for stylistic changes, object editing, or even filling in missing parts. It's ideal for anyone needing to iterate on visual concepts without starting from scratch.

153 stars. No commits in the last 6 months.

Use this if you need to create multiple visually distinct but semantically consistent images from a single source, such as for A/B testing marketing creatives or exploring design options.

Not ideal if you require highly precise, pixel-level control over image generation or if your primary need is for completely novel image synthesis unrelated to an input.

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

How are scores calculated?

Stars

153

Forks

10

Language

Python

License

Apache-2.0

Last pushed

Jan 02, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/JIA-Lab-research/RIVAL"

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