/higgsfield-3d

name: higgsfield-3d
description: "Use when the user wants a 3D model, mesh or GLB out of Higgsfield — image-to-3D, multi-view-to-3D, text-to-3D, rigging or animating a mesh, remesh / retopology, retexture, or 3D Body (human shape + pose from one photo) — or mentions 3D Jutsu / Scene Builder 3D (private Blender scene projects built through Python). Also use for a 3D turnaround of a character or prop as a consistent multi-angle reference, or a physical 3D blockout rendered as a staging reference for a video shot. Names that trigger it: generate_3d, sam_3_3d, image_to_3d, multi_image_to_3d, meshy_v7_image_to_3d, tripo_h3_1_image_to_3d, tripo_h3_1_multiview_to_3d, hunyuan3d_v3_image_to_3d, meshy_v6_text_to_3d, hunyuan3d_v3_1_text_to_3d, tripo_3d, 3d_rigging, meshy_v5_remesh, meshy_v5_retexture, sam_3_3d_body, animation_actions, scene_builder_3d_*."
user-invocable: true
metadata:
  tags: [higgsfield, 3d, glb, mesh, image-to-3d, multi-view, text-to-3d, rigging, animation, remesh, retexture, 3d-body, 3d-jutsu, scene-builder, blender, turnaround, staging-reference]
  version: 1.0.0
  updated: 2026-09-26
  parent: higgsfield

Higgsfield 3D — Meshes, Rigs, and 3D Jutsu Scenes

QUICK FACTS

*Routing aids — read the linked sections for the full rules. Nothing in this sub-skill is field-tested.*

• 17 3D models in the 2026-09-26 snapshot, six jobs: single image→3D, multi-view→3D, text→3D, rig, remesh / retexture, 3D Body [→](#the-catalog--17-models-six-jobs)
• **THE law:** the mesh reproduces only what is in the source image — to add or change props, clothing or held objects, edit the IMAGE first, then convert the edited result [→](#the-source-image-law)
• Multi-view beats single-view for geometry: 2–4 views of the same subject → `multi_image_to_3d` / `tripo_h3_1_multiview_to_3d` [→](#multi-view-beats-single-view)
• The `prompt` field: the MCP schema says only `sam_3_3d` accepts one; the CLI marks it REQUIRED on the three text→3D models — send it there, confirm with `get_cost` [→](#the-prompt-field--two-surfaces-disagree)
• Server-enforced rules: animation needs rigging; texture options need texturing ON; Hunyuan std caps the prompt at 200 characters and has no PBR [→](#parameter-rules-the-server-enforces)
• Rig + animate: humanoids rig best; `animation_action_id` comes from a 678-action library (ids 0–696, not contiguous — look up, never guess) [→](#rigging-and-animation)
• `get_cost: true` preflights for free; never auto-resubmit after a transport timeout [→](#cost-and-submission-discipline)
• 3D Jutsu = private Blender 5.2 scene projects: inspect (query) → guarded edit (run) → `show_scene` LAST [→](#3d-jutsu-scene-builder-3d)
• A generated GLB cannot enter a 3D Jutsu scene — imports are curated-catalog assets only in this version [→](#what-3d-jutsu-cannot-take-in)
• Film use 1: a mesh turnaround as a multi-angle reference — UNMEASURED [→](#film-use-1--a-3d-turnaround-as-a-multi-angle-reference)
• Film use 2: a 3D blockout rendered front-on from the camera's side becomes the SOURCE FRAME for the staging template — UNMEASURED [→](#film-use-2--a-3d-blockout-as-a-staging-reference)

---

What this sub-skill is for

Higgsfield now generates **3D assets** (GLB meshes, optionally textured, PBR-mapped, rigged and animated) and hosts **3D Jutsu**, a private Blender scene editor driven through Python. This sub-skill documents what each surface is for, what its parameters are, the rules the server enforces, and the two uses that matter to this repo's film work: a consistent multi-angle reference, and a physical staging reference.

It is a **routing and discipline layer**, the same as the rest of this library: it picks the model and writes the inputs; the execution surface (MCP connector, CLI, web UI) runs the job — see `../higgsfield-stack/SKILL.md`.

**Everything here comes from the platform's own schemas** (provenance at the end). No 3D job and no 3D Jutsu edit has been run from this repo. There are no quality rankings, speed claims or prices in this file — none were measured, so none are stated.

**Not this sub-skill:** Cinema Studio 2.5's *3D Mode* (Gaussian splatting inside a generated image) — that is `../higgsfield-cinema/SKILL.md` § 3D Mode. And not a Blender tutorial: 3D Jutsu's Python surface is documented only as far as its tool contracts go.

---

The catalog — 17 models, six jobs

`[OFFICIAL — platform, 2026-09-26]` — `../../specs/models_explore_snapshot_3d_2026-09-26.json`. `../../scripts/sync_specs.py` has no 3D type yet, so there is no generated 3D spec table: this table is read straight from the snapshot. Names and providers are as the snapshot states them.

| Job | Model id | Snapshot name · provider | Input | |---|---|---|---| | Single image → 3D | `sam_3_3d` | SAM 3 3D Objects · Meta | 1 image (role `image`) | | Single image → 3D | `image_to_3d` | Image to 3D · Meshy | 1 image (role `image`) | | Single image → 3D | `meshy_image_to_3d` | Image to 3D · Meshy | 1 image (role `image`) | | Single image → 3D | `meshy_v7_image_to_3d` | Meshy 7 Image to 3D · Meshy | image (role `image_references`) | | Single image → 3D | `tripo_h3_1_image_to_3d` | Tripo H3.1 Image to 3D · Tripo | image (role `image_references`) | | Single OR multi-view → 3D | `hunyuan3d_v3_image_to_3d` | Hunyuan3D v3 Image to 3D · Tencent | "one image or multiple views" (role `image_references`) | | Multi-view → 3D | `multi_image_to_3d` | Multi-Image to 3D · Meshy | 1–4 images of the same subject (role `image`) | | Multi-view → 3D | `meshy_multi_image_to_3d` | Multi-Image to 3D · Meshy | 1–4 images of the same subject (role `image`) | | Multi-view → 3D | `tripo_h3_1_multiview_to_3d` | Tripo H3.1 Multiview to 3D · Tripo | 2–4 **ordered** views (role `image_references`) | | Text → 3D | `meshy_v6_text_to_3d` | Meshy 6 Text to 3D · Meshy | prompt | | Text → 3D | `hunyuan3d_v3_1_text_to_3d` | Hunyuan 3D v3.1 Text to 3D · Tencent | prompt | | Text → 3D | `tripo_3d` | Text to 3D · *(provider, description and tags blank