image-to-3d
Installation
SKILL.md
image-to-3d
Run every graph with the bundled client: python scripts/comfy_client.py --url $COMFY_URL run workflows/<file> --set NODE.INPUT=VALUE --out out/. Upload input files first with python scripts/comfy_client.py upload <file>. Before the first run on a server, check it with python scripts/preflight.py --url $COMFY_URL workflows/<file>. Node packs, model files, VRAM and weight licenses for this skill are in references/requirements.md. Use open-weights models only, and never swap in a hosted or closed model.
| Need | Workflow | Set |
|---|---|---|
| One image to a mesh (TRELLIS.2) | trellis2_image_to_3d.api.json |
1.image |
| One image to a mesh (Pixal3D) | pixal3d_image_to_3d.api.json |
1.image |
| Four views to a mesh | pixal3d_multiview_to_3d.api.json |
40, 43, 46, 49 .image (front, right, back, left) |
Notes
- The input should show one object on a plain background. The graph removes the background with BiRefNet.
- The output is a
.glb(SaveGLB). Use it for blocking in a 3D tool, or render turnarounds as references forimage-edit. - The licenses of the DINOv3, MoGe and Pixal3D weights are unverified. Check them before commercial use.