speridlabs/idol-turbo
image-to-3d model by speridlabs
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
[](https://hf.co/chat?mode=ml-intern) Idol Turbo A distilled, few-step version of speridlabs/idol. One picture of an object in, up to a million 3D Gaussians out — in 5 guidance-free steps instead of 50 guided ones. Five objects, three panels each: the input image, the turbo at 5 steps (guidance-free, 0.75s), and the original model at 5 steps (with CFG, 2× the evaluations). The backpack was held out of training: Idol Turbo is Idol's flow-matching denoiser distilled for speed: The turbo works with the Comfy-Org/Idol repack and its TripoSplat workflows — the LoRA keys are compatible (verified: identical module paths) and pre-scaled for strength 1.0: Sampling settings: 5 steps, CFG 1.0 (guidance is folded into the LoRA — CFG 1.0 disables the duplicate guidance pass, which is where the 2× comes from). The two LoRA files are phase experts — slow covers the high-noise steps, fast the low-noise steps: Honest caveat: the LoRA weights…
Read the full model card ↗ · Preview checked 2026-11-09T09:29:07.027Z
Inside the original model card — Document outline
- Showcase
- What this is
- ComfyUI
- Step ladder: teacher / naive / turbo (current v5 weights)
- Turbo vs naive at 6 steps, with inputs
- Honest status
- Usage (Python)
- License
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
speridlabs/idol-turbo is a image-to-3d model repository published by speridlabs on Hugging Face. The source reports the idol library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-to-3d
- Library
- idol
- Recent downloads (30 days)
- 446
- Cumulative likes
- 53
- Hugging Face trending score
- 52
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-11-03T09:07:17.000Z
- Last modified
- 2026-11-03T23:03:27.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: speridlabs/idol
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-09T06:53:49.563Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.