Hunyuan3D-2mini — fast image-to-3D mesh
The 0.6B "mini" shape model from the Hunyuan3D-2 family, bundled with the delight and paint pipelines. ≈6–18 s per mesh on an RTX 5090, producing compact meshes under 1 MB.
What this repo is: the Hunyuan3D-2mini shape DiT, the 2.0-turbo DiT, and the delight / paint / paint-PBR pipelines — weights only, not a retrain. The samples below were generated with this build.
Samples
Single image in, mesh out. Source images were rendered with Z-Image Turbo;
the meshes are Blender Workbench clay renders of the raw .glb output.
Textured (img2mesh_textured)
The same robot through the full chain — mini shape, then the bundled paint pipeline — instead of shape alone.
Turntable
Four views, 90° apart.
Recommended settings
| Parameter | Production value | Meaning |
|---|---|---|
seed | any | Deterministic per seed |
| input | one RGB(A) image | Centred subject, plain background |
| output | .glb | Watertight triangle mesh, no texture |
Supported modes: img2mesh, txt2mesh, and the _textured variants (texturing is a separate paint stage — see gotchas)
Notes and gotchas
- This is the speed/size tier, not the detail tier. At 0.6B it returns meshes around 0.7 MB where a 1.5B model returns 15–38 MB for the same inputs — roughly 20–50× lighter. Silhouette, proportion and major features are captured; fine relief is smoothed away (in the robot sample the chest panel survives, the moulded nose does not). That trade is the point: it is the right model for drafts, previews and bulk generation, and the wrong one for hero assets.
- Sub-10 s generation makes it usable interactively — 6 s for a simple object, 18 s including model load on the first call.
img2meshoutput is untextured; texturing is a separate paint stage. The bundled delight/paint pipelines back the_texturedjob types and do produce correctly textured meshes. Paint cost scales with vertex count, and this model's small meshes make it the cheapest in the family to texture: 85 s here, against ≈14 min for a 3.3B mesh and ≈24 min for an 845k-face one. Most of that time is a pure-Python UV hole-filling loop, not GPU work.- Give it a clean, centred subject on a plain background — background clutter costs geometry.
Files
| Path | Size | Role |
|---|---|---|
split/Hunyuan3D-2mini/model.fp16.{ckpt,safetensors} | 3.82 GB | mini shape DiT (0.6B) — the model these samples came from |
split/hunyuan3d-dit-v2-0-turbo/ | 4.93 GB | 2.0-turbo shape DiT |
split/hunyuan3d-delight-v2-0/ | 4.3 GB | delighting pipeline (removes baked lighting before texturing) |
split/hunyuan3d-paint-v2-0/ | 5.2 GB | texture-painting pipeline |
split/hunyuan3d-paintpbr-v2-1/ | 6.6 GB | PBR texture-painting pipeline |
Provenance
- Upstream base model:
tencent/Hunyuan3D-2miniand the Hunyuan3D-2 paint/delight pipelines - This build: redistributed as a split component tree. Weights are not retrained here.
- License: Tencent Hunyuan3D community license — refer to upstream for redistribution and commercial-use terms.