Instructions to use suvadityamuk/idol-diffusers-3d with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use suvadityamuk/idol-diffusers-3d with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("suvadityamuk/idol-diffusers-3d", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
File size: 917 Bytes
5d90070 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 | This repository holds the denoiser and Gaussian decoders of speridlabs/idol (revision
2731c2291fc65a797c5cb627a5e5526fc1490902), converted by diffusers-3d into Diffusers component folders. Parameters
were renamed and the two decoders merged; weight values are unchanged. They are provided under the accompanying
Apache License 2.0 (LICENSE-APACHE-2.0).
IDOL's networks keep the architecture of VAST-AI-Research TripoSplat, provided under the MIT License
(LICENSE-MIT, Copyright (c) 2026 VAST).
The DINOv3 image encoder (facebook/dinov3-vith16plus-pretrain-lvd1689m, DINOv3 License) and the
FLUX.2 VAE encoder (black-forest-labs/FLUX.2-dev, FLUX non-commercial license) are not included in this repository.
diffusers-3d loads them from those repositories at pinned revisions; their own terms apply.
No affiliation, sponsorship, or endorsement by Speridlabs, VAST-AI-Research, Meta, or Black Forest Labs is claimed.
|