---
license: apache-2.0
pipeline_tag: image-to-3d
tags:
  - localmesh-engine
  - image-to-3d
  - mesh
  - gltf
  - trellis
  - multi-view
  - 3d-generation
base_model: TencentARC/Pixal3D
base_model_relation: quantized
---

![LocalMesh Engine](https://raw.githubusercontent.com/Quentincls/localmesh-engine/main/assets/banner.png)

# LocalMesh Engine, multi-view weights

LocalMesh Engine turns one photo, or four sides of the same subject, into a
textured `.glb`. It runs on an 8 GB NVIDIA card. The code is Apache-2.0 and
lives on [GitHub](https://github.com/Quentincls/localmesh-engine). The project
page is [local-mesh.com/localmesh-engine](https://local-mesh.com/localmesh-engine/).

TRELLIS.2 works from a single image. This repository holds the weights of the
four view path: the three fp8 conversions of the Pixal3D multi-view models,
and the field network that recovers detail between image tokens. The three
conversions exist nowhere else. Everything else the engine needs comes from
upstream repositories and is listed below.

## What is in this repository

This repository holds **the whole LocalMesh engine**, except one set Meta
gates. It is laid out exactly like the folder the engine reads, so one command
places all of it:

| Folder | Size | What it is | Whose |
|---|---|---|---|
| `TRELLIS.2-4B/` | 8.1 GB | the single photo path, in fp8 | [visualbruno](https://huggingface.co/visualbruno/TRELLIS.2-4B-FP8), MIT — rehosted unchanged |
| `microsoft/` | 148 MB | the sparse structure decoder | [Microsoft](https://huggingface.co/microsoft/TRELLIS-image-large), MIT — rehosted unchanged |
| `multivue/` | 4.8 GB | the four view path | ours, from Pixal3D — see below |

Rehosted so that one `hf download` replaces six. Taking those two from their
own repositories works exactly as well; nothing here is modified.

### What is ours, under `multivue/`

| File | Size | Source |
|---|---|---|
| `multivue/structure_mv_fp8.safetensors` + `.json` | 1.39 GB | fp8 conversion of `ckpts/ss_flow_img_dit_1_3B_64_bf16_mv.safetensors`, TencentARC/Pixal3D |
| `multivue/forme_512_mv_fp8.safetensors` + `.json` | 1.44 GB | fp8 conversion of `ckpts/slat_flow_img2shape_dit_1_3B_512_bf16_mv.safetensors`, TencentARC/Pixal3D |
| `multivue/forme_1024_mv_fp8.safetensors` + `.json` | 1.44 GB | fp8 conversion of `ckpts/slat_flow_img2shape_dit_1_3B_1024_bf16_mv.safetensors`, TencentARC/Pixal3D |
| `multivue/champ.safetensors` | 2.7 MB | valeoai/NAF, official checkpoint, tensors unchanged |

**`structure_mv_fp8`** fuses the four encoded views into a sparse volume of
cells. Each view is projected onto the shared grid by its own camera.

**`forme_512_mv_fp8`** is the first shape pass, on the grid inherited from the
structure. **`forme_1024_mv_fp8`** is the second, and the TRELLIS.2 shape
decoder turns its latent into the mesh.

**`champ`** is the NAF field network. It returns a 512 by 512 query map, which
fills in the detail the token map loses: the token map is sixteen times coarser
than the photo.

4.28 GB, seven files, plus `multivue/cameras/` — DA3-BASE and the code that
reads it, 544 MB, Apache-2.0, unchanged. Keep the three `.json` descriptors
next to their `.safetensors`: the engine builds each flow model on the `meta` device from that
descriptor, then loads the tensors in place, so the weights are never held
twice. The descriptors declare `dtype: float8_e4m3fn`.

The four view path serves the `draft`, `standard` and `high` tiers. The
multi-view weights exist at 512 and 1024 only, so `max` falls back to the
earlier way of blending the views rather than shipping a `standard` shape under
another name.

## What is not in this repository

| Weights | Where | Licence | Note |
|---|---|---|---|
| TRELLIS.2-4B, fp8 | https://huggingface.co/visualbruno/TRELLIS.2-4B-FP8 | MIT | 8.1 GB. Texture on both paths, the single photo path, and the shape decoder the four view path ends on. Required either way. |
| TRELLIS-image-large, structure decoder | https://huggingface.co/microsoft/TRELLIS-image-large | MIT | Two files, `ss_dec_conv3d_16l8_fp16.json` and `.safetensors`. |
| DINOv3 ViT-L/16 | https://huggingface.co/facebook/dinov3-vitl16-pretrain-lvd1689m | DINOv3 License, Meta | Image encoder, required on both paths. Access is gated and approved by hand, so ask for it first. |
| BiRefNet_HR | https://huggingface.co/ZhengPeng7/BiRefNet_HR | MIT | Cutout. The engine fetches this one from the Hub on the first generation if the cache is empty, and loads it with `trust_remote_code=True`, so that first run executes code from the Hub. |
| DA3-BASE | https://huggingface.co/depth-anything/DA3-BASE | Apache-2.0 | `model.safetensors` (541 MB) and `config.json`, plus the `depth_anything_3` source tree beside them: 544 MB in place. Measures the azimuth of each shot and which side each profile shows. The engine runs without it, but it then guesses which side each profile is on, and says so in its result. A wrong guess puts a face at the front and at the back. |

## Using them

Set `LOCALMESH_ROOT` to the folder that holds `models/`, then:

```bash
pip install -U huggingface_hub
hf download Qtn-Cls/LocalMeshEngine --local-dir "$LOCALMESH_ROOT/models"
```

13.1 GB, and every file lands exactly where the engine looks for it. There is
nothing to move afterwards. For the single photo path alone, 8.3 GB, add
`--exclude "multivue/*"`.

**Then ask Meta for DINOv3**, the one set that is not here and cannot be: it is
gated, and a human grants access. Nothing generates without it, and approval is
not instant, so send the request before anything else —
[facebook/dinov3-vitl16-pretrain-lvd1689m](https://huggingface.co/facebook/dinov3-vitl16-pretrain-lvd1689m).

The layout the engine reads:

```
<LOCALMESH_ROOT>/models/
  TRELLIS.2-4B/                              this repository
  microsoft/TRELLIS-image-large/ckpts/       this repository
  multivue/                                  this repository
  multivue/cameras/                          this repository, DA3-BASE
  facebook/dinov3-vitl16-pretrain-lvd1689m/  from Meta, gated
  hf/                                        Hugging Face cache (HF_HOME), where BiRefNet_HR lands
```

Then, from the four sides of one subject:

```bash
python -m localmesh_engine face.png --right right.png --left left.png --back back.png --to out/
```

`--tier` picks the tier: `draft`, `standard`, `high` or `max`, written
Draft, Standard, Detailed and Extreme where these pages spell them out.
`--seed` sets the seed, `--to` the output folder. The command assumes the package is installed.
The four view path also needs `natten`. Installation, including the three CUDA
extensions that are not on PyPI, is written up in `docs/INSTALL.md` in the
GitHub repository; the four tiers, frozen, are in `docs/RECIPES.md`.

## Results

![Four views to one .glb](https://raw.githubusercontent.com/Quentincls/localmesh-engine/main/assets/four-views.png)

![Gallery](https://raw.githubusercontent.com/Quentincls/localmesh-engine/main/assets/gallery.png)

![Four of the six meshes on a full turntable](https://raw.githubusercontent.com/Quentincls/localmesh-engine/main/assets/turntable.gif)

A full turn each. One pose can be chosen; a full turn cannot.

Six subjects, four photos each, `high` tier, RTX 4060 Laptop 8 GB: samurai on a
base, crowned stone head, sword in the stone, motorcycle, cassette with a clear
shell, traffic light.

| Tier | Four views, measured over the six subjects |
|---|---|
| Standard, `standard` | 6 min 30 to 8 min 30 |
| Detailed, `high` | 9 min 20 to 13 min |

Texture accounts for about 60 % of that time.

## The conversion

The three flow models start from the official `*_mv` weights of
TencentARC/Pixal3D. Their tensors are stored in float32, despite the `bf16` in
their filenames. The transformer blocks are cast to `float8_e4m3fn`, and the
descriptor beside each file records that dtype, so the engine builds the model
in fp8 rather than casting after the fact. Of each model, 480 tensors are
converted; the input and output layers, the norms and modulations, and the
structure model's complex rotary table are left as they were.

Measured against the source: RMSE of 0.025 to 0.026 on the weights, and 0.027
on a projection probe.

`champ.safetensors` is not converted. It carries the tensors of the official
valeoai/NAF checkpoint, `naf_release.pth`, unchanged, re-serialised to
safetensors. The file records the source URL and its SHA-256 in its own
metadata.

## Licences and attribution

The `license` field above is the repository tag. It is Apache-2.0, the licence
of the engine code and of this card. The files themselves keep the licence of
their own source:

- The three fp8 conversions derive from **TencentARC/Pixal3D**, MIT License,
  Copyright (c) 2026 Tencent. Code: https://github.com/TencentARC/Pixal3D,
  weights: https://huggingface.co/TencentARC/Pixal3D
- `champ.safetensors` comes from **valeoai/NAF**, Apache-2.0,
  https://github.com/valeoai/NAF

The engine also builds on:

- **TRELLIS.2**, Microsoft, MIT License, https://github.com/microsoft/TRELLIS.2
- **ComfyUI-Trellis2**, visualbruno, MIT License, for the ported multi-view path
  and the fp8 loading, https://github.com/visualbruno/ComfyUI-Trellis2
- **Depth Anything 3**, Apache-2.0, for the camera measurement,
  https://github.com/ByteDance-Seed/depth-anything-3
- **BiRefNet**, MIT License, for the cutout,
  https://github.com/ZhengPeng7/BiRefNet

Built with DINOv3. DINOv3 is the image encoder on both paths. Its weights are
not redistributed here: request them from Meta, and ship a copy of the DINOv3
License Agreement with any redistribution of your own.

## Citing

```bibtex
@software{colus2026localmeshengine,
  author  = {Colus, Quentin},
  title   = {LocalMesh Engine},
  year    = {2026},
  version = {1.0.0},
  license = {Apache-2.0},
  url     = {https://github.com/Quentincls/localmesh-engine}
}
```

The upstream work these weights rest on: TRELLIS.2 (Microsoft,
arXiv:2512.14692), Pixal3D (TencentARC, arXiv:2605.10922), NAF (valeoai),
DINOv3 (Meta), Depth Anything 3 (arXiv:2511.10647).

## Code

The engine is at **https://github.com/Quentincls/localmesh-engine**. Recipes,
installation, measurements and the provenance of every vendored file are there.
Open issues there, not here.

## The application

These weights and this engine are the generation core of LocalMesh, a Windows
application at [local-mesh.com](https://local-mesh.com): the same core with a
board, a library and a viewer, installed in one step instead of fifteen. The
engine is free and open; the application is what is sold.

![The LocalMesh board, covered in generated objects](https://raw.githubusercontent.com/Quentincls/localmesh-engine/main/assets/localmesh-app.webp)