Downloads · 30 days
7
26% of all-time downloads
mlx-community/tripo_splat_mlx
tripo_splat_mlx is a image-to-3d model from mlx-community. Use it for the image-to-3d task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as other.
MLX-native implementation of TripoSplat for Apple Silicon.
Downloads · 30 days
7
26% of all-time downloads
All-time downloads
27
Public
Repo size
4.6 GB
Likes
1
Public
Click a slice to open those files.
.safetensors3.8 GB · 85%
From the Hugging Face model README
MLX-native implementation of TripoSplat for Apple Silicon.
Part of TripoFlux MLX — a full MLX / CoreML accelerated text-to-3D pipeline (FLUX.2-klein-9B → BiRefNet → TripoSplat → .ply / .splat / .spz) with an R3F web UI featuring a Looking Glass holographic WebXR preview.
📺 Bilibili video: Looking Glass (LKG) WebXR holographic preview demo
This repository contains MLX ports of the TripoSplat submodules:
mlx_models/dinov3_mlx.py — DinoV3 ViT-H/16+ image encodermlx_models/flux2vae_mlx.py — Flux2 VAE encodermlx_models/flow_mlx.py — LatentSeqMMFlowModel (24-block multimodal flow transformer)The original TripoSplat decoder (OctreeGaussianDecoder) remains on PyTorch MPS due to its complex dynamic sampling logic.
| File | Size | Description |
|---|---|---|
dino_v3_vit_h.safetensors | 1.6 GB | DinoV3 ViT-H/16+ image encoder |
flux2-vae.safetensors | 336 MB | Flux2 VAE encoder |
triposplat_fp16.safetensors | 741 MB | LatentSeqMMFlowModel (flow transformer) |
triposplat_vae_decoder_fp16.safetensors | 576 MB | TripoSplat VAE decoder |
birefnet.safetensors | 444 MB | BiRefNet background removal |
This is a mixed-license repository. The most restrictive artifact determines
what the repository as a whole can be used for — with flux2-vae.safetensors
included, the repo as a whole is non-commercial only.
| File | Upstream | License | Terms |
|---|---|---|---|
flux2-vae.safetensors | black-forest-labs/FLUX.2-klein-9B | FLUX Non-Commercial License | Weights are gated upstream. Commercial use of the weights or their outputs requires a paid license from Black Forest Labs. If you need a fully permissive stack, delete this file and load the VAE from the upstream gated repo at runtime after accepting its terms. |
| File | Upstream | License | Terms |
|---|---|---|---|
dino_v3_vit_h.safetensors | facebook/dinov3 | DINOv3 License | Commercial use is allowed, but any redistribution of copies or derivatives must include the DINOv3 License text. Upstream downloads are gated and unavailable in sanctioned jurisdictions. |
| File | Upstream | License |
|---|---|---|
triposplat_fp16.safetensors | VAST-AI/TripoSplat | MIT |
triposplat_vae_decoder_fp16.safetensors | VAST-AI/TripoSplat | MIT |
birefnet.safetensors | ZhengPeng7/BiRefNet | MIT |
mlx_models/*.py | this repo (MLX port) | MIT |
The MLX port code in mlx_models/ is released under the
MIT License, same as the main project:
https://github.com/Jup33Q/tripoflux-mlx.
from mlx_models.dinov3_mlx import DinoV3ViT
from mlx_models.flux2vae_mlx import Flux2VAEEncoder
from mlx_models.flow_mlx import LatentSeqMMFlowModel
# Load models
dino = DinoV3ViT()
dino.load_safetensors("dino_v3_vit_h.safetensors")
vae = Flux2VAEEncoder()
vae.load_safetensors("flux2-vae.safetensors")
flow = LatentSeqMMFlowModel(
q_token_length=8192, in_channels=16, cam_channels=5, out_channels=16,
model_channels=1024, cond_channels=1280, cond2_channels=128,
num_refiner_blocks=2, num_blocks=24, num_heads=16, mlp_ratio=4,
qk_rms_norm=True, share_mod=True, use_shift_table=True,
)
flow.load_safetensors("triposplat_fp16.safetensors")
For the complete text-to-3D pipeline (FLUX.2-klein-9B → BiRefNet → TripoSplat → SPZ export), see the main project: https://github.com/Jup33Q/tripoflux-mlx
.spz / .ply / .splat)