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 β€” merged weights with transformer.*, vae.*, image_encoder.* and text_encoder.* prefixes
  • resolved_config.json β€” every component config, the pipeline defaults, and the embedded CLIP vocab.json / merges.txt / tokenizer configs
  • manifest.json β€” family, variant, provenance, source checksums, tensor count
  • checksums.json β€” 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

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.

Downloads last month

-

Downloads are not tracked for this model. How to track
Safetensors
Model size
2B params
Tensor type
F16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for oxide-lab/TripoSG-scribble

Finetuned
(1)
this model

Collection including oxide-lab/TripoSG-scribble