Idol

Released
2026-10-29
Last refreshed
2026-11-02
Status
Researched 2d ago
Open sourceCommercial use: permittedMultimodalVision
Sperid Labs releases · 1 in the last 12 monthsChangelog →
Specifications
Family
Idol
Released
2026-10-29
Parameters
660M
Specialization
image
Openness
Open source
License
Apache 2.0OSI-approvedPermitted
Weights
Available
Code
Unknown
Training
Pretrained
Created by

Sperid Labs is a spatial AI lab that builds open models for understanding and generating 3D, including the Idol image-to

Website
Pricing

No tracked provider pricing is available yet.

Providers(1)

About

Idol is Sperid Labs' open-weight image-to-3D model, announced October 29, 2026. A 3D diffusion transformer pre-trained from scratch, it generates a complete 3D object as a Gaussian splat from a single image, with a GLB point-cloud preview, and runs on consumer GPUs. It has 0.66B parameters and can generate each object at several levels of detail, from 32,768 to 1,048,576 Gaussians. Weights are on Hugging Face at speridlabs/idol under Apache 2.0.

Providers(1)

Compare API pricing across 1 tracked provider route for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
fal API--
ServerlessPartial

Capabilities

VisionMultimodal

Benchmark peer barsfor Vision

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

API versions

speridlabs/idol