ashawkey/stable-dreamfusion

Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.

45
/ 100
Emerging

Leverages Stable Diffusion as a guidance model via SDS loss to optimize a NeRF representation, supporting multiple backbones including Instant-NGP for fast rendering (~10 FPS) and optional Perp-Neg for reducing multi-view inconsistency artifacts. Integrates Zero-1-to-3 for image-conditioned generation, Omnidata for geometric priors, and offers both CUDA and CUDA-free Taichi backends for flexible hardware deployment.

8,818 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

8,818

Forks

774

Language

Python

License

Apache-2.0

Last pushed

Dec 10, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ashawkey/stable-dreamfusion"

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