Download README.md from oxide-lab/TripoSG-scribble: direct link, hf CLI and curl.
- Browser
- Download file 3.37 kB
-
https://huggingface.co/oxide-lab/TripoSG-scribble/resolve/main/README.md
- Command line
-
hf download hf://oxide-lab/TripoSG-scribble/README.md
-
curl -L -o README.md https://huggingface.co/oxide-lab/TripoSG-scribble/resolve/main/README.md
license: mit
pipeline_tag: image-to-3d
base_model: VAST-AI/TripoSG-scribble
tags:
- lux3d
- rust
- candle
- safetensors
- canonical-weights
- 3d
- image-to-3d
- mesh
- triposg
- triposg-scribble
- scribble
Lux3D TripoSG-scribble Canonical Weights
Canonicalized safetensors export of the
VAST-AI/TripoSG-scribble
checkpoint used by the Lux3D runtime.
Model Details
- Model family:
triposg - Variant:
triposg-scribble - Canonical file:
model.safetensors(4,705,388,818 bytes, about 4.38 GiB) - Tensor count:
1735 - Parameter storage: F16 (same precision as the upstream shards)
- SHA-256:
0c31d6c251c89ea18556ad4e15fd8d499405fc868fb002d5491fea87dbb705b1
TripoSG-scribble is the dual-conditioning variant of TripoSG:
- a DINOv2-large scribble image encoder (24 layers, width 1024, patch 14);
- a 21-block rectified-flow DiT with two cross-attention branches:
CLIP text (
cross_attention_dim=768) and scribble image (cross_attention_2_dim=1024); - an SDF VAE decoder;
- a CLIP text encoder and its byte-level BPE tokenizer;
- 512 latent tokens, 16 steps, CFG-distilled (
guidance_scale=0), dense and hierarchical octree depth 8.
Included Files
model.safetensors— merged weights withtransformer.*,vae.*,image_encoder.*andtext_encoder.*prefixesresolved_config.json— every component config, the pipeline defaults, and the embedded CLIPvocab.json/merges.txt/ tokenizer configsmanifest.json— family, variant, provenance, source checksums, tensor countchecksums.json— SHA-256 and size for every required package file
No raw diffusers checkpoint or tokenizer files are needed at run time.
Usage With Lux3D
cargo run -p lux3d-cli --features cuda -- run triposg --mode scribble `
--prompt "a cat with wings" `
--model-path <canonical-triposg-scribble-dir> `
--source <scribble.png> --output <output.glb>
The package can also contain a quantized model.gguf; the canonical loader
prefers it over model.safetensors. The standalone GGUF packages in
TripoSG-scribble-GGUF are a separate, smaller distribution.
Provenance
- Upstream model:
VAST-AI/TripoSG-scribble - Upstream code:
VAST-AI-Research/TripoSG(MIT) - Canonicalization:
weights normalize ... triposg(auto-detects thetext_encoder/model.safetensorsshard) ortools/python_baseline/normalize_weights.py
The raw checkpoint is split across transformer/, vae/,
image_encoder_dinov2/, text_encoder/ and tokenizer/. Normalization merges
the four shards under one safetensors file, records every source checksum in
manifest.json, and embeds the tokenizer documents in
resolved_config.json. No tensor values are modified.
Validation
On CPU, a canonical package and the raw checkpoint produced a byte-identical OBJ for the same input, prompt and step count. The canonical loader test constructs DINOv2, the dual-cross-attention DiT, the VAE decoder and the CLIP text encoder, and parses the embedded tokenizer.
License
TripoSG-scribble code and weights are distributed under the MIT License. The embedded CLIP text encoder, DINOv2 image encoder and VAE components keep their upstream terms.