⬢github Python · 893 ★ +25 since we first saw it · pushed 9 d ago · Apache-2.0
speridlabs/idol-sdk
Idol: a single image to 3D Gaussians. Inference SDK and demo.
Idol is a Python SDK and demo that turns a single image of an object into a 3D Gaussian splat (.ply). It removes the background, frames the object, and generates up to ~1M Gaussians, including unseen sides, via a diffusion-transformer model with DINOv3 and FLUX.2 conditioning. It runs on consumer GPUs (~7.2 GB VRAM, under 2 seconds per image).
Why now: It was recently released and is trending on GitHub's most-starred new repos, with a live Hugging Face Space demo showing example results.
Who it is for: Developers and creators who want quick single-image 3D asset generation, such as graphics, game, and 3D-splatting hobbyists.
Stars over our 115 snapshots: 868 to 893, since 1 d ago.
Where people talked about it
- ⬢github new repos, most starred 10 min ago
- ⬢github new repos, most starred 11 h ago
API: https://socialmediatrends-api.osmike.com/v1/repos/speridlabs/idol-sdk