Idol
Turns a single image of an object into a 3D Gaussian splat (.ply), including the sides the picture never showed. 0.66B parameters; publisher-reported 7.2 GB peak VRAM.
What do you want to do?
Choose a task. Get the software, files, settings, and steps to run it.
Open a guide for its software, hardware requirements, and setup steps.
At a glance
- Parameters
- 0.66B (about 1.8B with encoders)
- License
- Apache 2.0 (encoders have their own gated terms)
- Software
- Idol SDK (PyTorch)
Will it run on your machine?
Save your machine to see a personalized rating and its reasoning.
Add my hardwareBest for
- Turn a product or object photo into a rotatable 3D splat.
Tradeoffs
- Output is a Gaussian splat, not a mesh.
- Requires an NVIDIA CUDA GPU and access to two gated encoders.
- Single objects, not whole scenes.
Ways to run it
Idol SDK · Linux · NVIDIA
Publisher command-line route.
python -m idol.sample --image photo.jpg --mode realWhat to expect
Run the publisher SDK on an NVIDIA GPU with 10 GB or more, or rent one.
Explore its uses
Sources and files
Primary sources and files behind this model page.
Keep exploring
Qwen-Image 2.1
Generate and edit images, including transparent images and edits guided by reference images.
FLUX.1 schnell
A 12-billion-parameter image model designed for generation in one to four steps.
FLUX.2 Klein
Explore 2 versions of FLUX.2 Klein. Compare model sizes, packages, hardware requirements, and available setups.