customdiffusion360/custom-diffusion360

CustomDiffusion360: Customizing Text-to-Image Diffusion with Camera Viewpoint Control

36
/ 100
Emerging

This project helps artists, designers, or marketers create images of a specific object from any angle using text prompts. You provide around 50 multi-view images of an object, and the system learns its appearance. Then, you can generate new images of that object with precise camera viewpoint control by just typing a description.

171 stars. No commits in the last 6 months.

Use this if you need to generate consistent, high-quality images of a custom object from various specific camera angles for product visualization, virtual try-ons, or creative content.

Not ideal if you only need generic image generation without detailed viewpoint control, or if you don't have a multi-view dataset of the custom object you wish to portray.

3D-rendering product-visualization digital-art e-commerce-imagery virtual-photography
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

171

Forks

11

Language

Python

License

Last pushed

Dec 02, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/customdiffusion360/custom-diffusion360"

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