Microsoft's TRELLIS.2 structured-latent 3D generator. ≈100 s per asset on an RTX 5090, and unlike most shape models it returns material already baked in — no separate texturing pass.
What this repo is: the TRELLIS.2 4B pipeline at FP16 — weights only, not a retrain. The samples below were generated with this build.
Single image in, textured mesh out. Source images were rendered with Z-Image
Turbo; the meshes are Blender Workbench renders of the raw .glb — no
cleanup, no retopology, and no separate paint stage.
| **source** — `a cute chunky retro robot toy standing upright, rounded metal body, simple friendly face, studio product photograph on a plain white background` | **mesh** — 26.3 MB `.glb`, generated in 98 s, seed 42 |
| **source** — `an ornate ceramic teapot with a curved spout and handle, glazed blue and white porcelain, studio product photograph` | **mesh** — 26.3 MB `.glb`, seed 42 |
Four views, 90° apart — the back is inferred, not copied from the source.
Note the level of preserved relief: the concentric ear knobs, the recessed chest display, and the fastener detail across the back panel all survive, and the surface reads as metal rather than flat clay because material comes out with the geometry.
| Parameter | Production value | Meaning |
|---|---|---|
seed |
any | Deterministic per seed |
| input | one RGB(A) image | Centred subject, plain background |
| output | .glb |
Mesh with baked material |
Supported modes: img2mesh, txt2mesh, and the _textured variants
img2mesh already returns a shaded mesh, so
the separate paint stage other shape models need is unnecessary here. That
is the main reason to pick TRELLIS.2 over a pure geometry model.[SPARSE] Conv backend: flex_gemm; Attention backend: flash_attn on load
and pulls a valeoai/NAF estimator from torch.hub the first time — the
first run on a fresh machine needs network access and is slower.microsoft/TRELLIS family, TRELLIS.2 4Bsplit/diffusion_models/trellis_2_bf16.safetensors 10 GBsplit/diffusion_models/trellis_2_int8_convrot.safetensors 5.3 GBfp16/slat_flow_imgshape2tex_dit_1_3B_1024_bf16.safetensors 2.6 GBfp16/slat_flow_imgshape2tex_dit_1_3B_512_bf16.safetensors 2.6 GBfp16/slat_flow_img2shape_dit_1_3B_1024_bf16.safetensors 2.6 GBfp16/slat_flow_img2shape_dit_1_3B_512_bf16.safetensors 2.6 GBfp16/ss_flow_img_dit_1_3B_64_bf16.safetensors 2.6 GBfacebook/model.safetensors 1.2 GBmicrosoft/ckpts/slat_flow_img_dit_L_64l8p2_fp16.safetensors 1.2 GBmicrosoft/ckpts/ss_flow_img_dit_L_16l8_fp16.safetensors 1.1 GBsplit/vae/trellis_2_shape_vae_bf16.safetensors 1.1 GBfp16/shape_dec_next_dc_f16c32_fp16.safetensors 948 MBsplit/vae/trellis_2_texture_vae_bf16.safetensors 948 MBfp16/tex_dec_next_dc_f16c32_fp16.safetensors 948 MBfp16/shape_enc_next_dc_f16c32_fp16.safetensors 709 MBfp16/tex_enc_next_dc_f16c32_fp16.safetensors 709 MBmicrosoft/ckpts/slat_dec_mesh_swin8_B_64l8m256c_fp16.safetensors 182 MBmicrosoft/ckpts/slat_enc_swin8_B_64l8_fp16.safetensors 173 MBmicrosoft/ckpts/slat_dec_gs_swin8_B_64l8gs32_fp16.safetensors 171 MBmicrosoft/ckpts/slat_dec_rf_swin8_B_64l8r16_fp16.safetensors 171 MBmicrosoft/ckpts/ss_dec_conv3d_16l8_fp16.safetensors 148 MBmicrosoft/ckpts/ss_enc_conv3d_16l8_fp16.safetensors 119 MBHave the files? Submit a torrent.
Submit a torrentHave the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo ChrisColeTech/TRELLIS.2-4B-FP16 ./model-folder