lehduong/OneDiffusion

Official implementation of OneDiffusion paper (CVPR 2025)

36
/ 100
Emerging

This tool helps creative professionals like graphic designers, marketers, or digital artists generate a wide variety of images and visual content from text descriptions or existing images. You provide text prompts, reference images, or specific instructions, and it outputs new images, edited images, or even multiple views of a subject. It's designed for anyone needing advanced image generation and manipulation without deep technical knowledge of AI models.

665 stars. No commits in the last 6 months.

Use this if you need a versatile tool to generate high-quality images from text, customize subjects across different scenes, create multiple views from a single image, or edit existing images with specific instructions.

Not ideal if you require very low memory usage for image generation, as it needs a GPU with at least 12GB of memory (more for higher resolutions or complex tasks).

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

How are scores calculated?

Stars

665

Forks

19

Language

Python

License

Last pushed

Dec 14, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/lehduong/OneDiffusion"

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