3D1.1B official

hunyuan3d-2-turbo

by Tencent Hunyuan

Hunyuan3D-2 with the turbo shape model: full-size 2.0 quality in a handful of steps, using FlashVDM decoding.

#3d #image-to-3d #fast #mesh

arcflare gen 3d photo.png -m hunyuan3d-2-turbo

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1

[ 02 ] // readme

Hunyuan3D-2 turbo

The full-size Hunyuan3D-2.0 shape model, step-distilled: 5 steps instead of 30, with FlashVDM speeding up mesh decoding. Detail sits between mini-turbo and the full model, at a fraction of the full model's time.

Run it

arcflare gen setup hunyuan3d-2-turbo

arcflare gen 3d robot.png -m hunyuan3d-2-turbo

Add --texture (NVIDIA + CUDA toolkit) to paint it with Hunyuan3D-Paint.

Licensed under the Tencent Hunyuan 3D Community License.

[ 03 ] // relatedmore →

hunyuan3d-2mini-fast

Tencent Hunyuan

Hunyuan3D-2 mini, guidance-distilled: about half the compute per step with nearly the same shapes. The middle ground between mini and mini-turbo.

size: 0.6B
vram: ~5 GB
license: Tencent Hunyuan Community

21% of a 24 GB card

#3d #image-to-3d #fast

triposr

Stability AI & Tripo

TripoSR reconstructs a 3D mesh from one image in a single feed-forward pass — under a second on a GPU. Rougher than Hunyuan, but instant.

size: 0.4B
vram: ~6 GB
license: MIT

25% of a 24 GB card

#3d #image-to-3d #fast

hunyuan3d-2mini

Tencent Hunyuan

Hunyuan3D-2 mini turns a single image into a clean 3D mesh. 0.6B parameters — the smallest Hunyuan shape model, and the one to start with.

size: 0.6B
vram: ~5 GB
license: Tencent Hunyuan Community

21% of a 24 GB card

#3d #image-to-3d #mesh