Use when generating 3D assets with Rodin Hyper3D models on Scenario via MCP: image-to-3D from up to five multiview stills, text-to-3D from a prompt, fast prototyping versus full quality tiers, quad or triangle topology, PBR materials, HighPack 4K textures, T-pose or A-pose characters for rigging, or splitting a finished mesh into parts and retexturing it with Bang!. Keywords: Rodin Gen-2.5, Hyper3D, Deemos, image to 3D, text to 3D, part segmentation, texture delight.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Rodin Hyper3D, Deemos Technology's 3D family on Scenario, picks its mode by member: image-to-3D and text-to-3D each ship as a full model and a Fast variant, and Bang! splits finished meshes into parts. Discover them with search and treat model_schema_get as the contract: the lanes agree on ideas and disagree on parameter names.
Connection and the core loop: see the scenario skill in this repo; model-agnostic 3D work: the scenario-3d skill. If a sibling skill named here is missing from your available skills, ask the user to install it (npx skills add scenario-labs/skills --skill <name>); unattended, proceed from tool schemas and flag the gap.
Pick the member by task:
| Task | Member | Required inputs |
|---|---|---|
Image to 3D (img23d) | Gen-2.5, or Fast | images |
Text to 3D (txt23d) | Gen-2.5 Text to 3D, or Fast | prompt |
Split and retexture (3d23d) | Bang! | model + image |
images is an array even for one still (up to 5 at authoring time), every entry a view of one subject, never an alternative concept. Prompt is optional on the image members: left empty, Rodin writes one from the images. Shared generator knobs: qualityMeshOption (topology and poly budget in one enum string, "18K Quad"), material (PBR, Shaded, All, None), textureDelight (strips baked lighting), TAPose (true poses the character in T or A pose for rigging; the schema does not pick between them), seed (0 to 65535).
Full and Fast express the same ideas through different parameters, so a payload never moves between lanes unchanged. At authoring time the full lane's tier ran Gen-2.5-Extreme-Low through Gen-2.5-Extreme-High (Extreme High bills double the base rate), HighPack rode in addons as a string (on a Quad mesh it multiplies faces about 16 times), geometryInstructMode: "creative" loosened interpretation, isSymmetric steered symmetry, and isMicro took effect only on Extreme High. The Fast lane's tier stopped at Gen-2.5-Minimum, Gen-2.5-Extreme-Low, and Gen-2.5-Low for one fixed price, highPack was a boolean, enableCreativeMode added generative robustness without losing consistency, and meshes capped at 20K behind an Auto default. In both lanes HighPack means 4K textures plus high-poly geometry at extra cost: dry_run the exact payload before any batch. Text members drop the image-only switches (useOriginalAlpha, previewRender).
Bang! is 3D-to-3D: it takes an existing 3D asset as model plus a reference image (both required at authoring time, prompt is optional guidance), splits the mesh into semantically meaningful parts, and regenerates each part's materials in the same pass. strength (2 to 12, default 5) sets how fine the split gets, higher splitting into more parts; material defaults to PBR here, not All; resolution "Basic" is 2K, "High" is 4K. At authoring time it ran several minutes and cost more per asset than a default generator run: dry_run it like any other member.
search with target="models", query="rodin", public=true. Match capability to task (img23d here, txt23d for prompt-only, Fast for cheap drafts), e.g. model_rodin-hyper3d-v2-5 (a live hit at authoring time: re-discover each session).model_schema_get with that id: enums, defaults, and caps before anything else.upload_asset the turnaround stills (see the scenario skill) to get asset ids.model_run with that model_id, dry_run=true, and parameters={"images": ["asset_front", "asset_side", "asset_back"], "prompt": "stylized adventurer, clean silhouette", "tier": "Gen-2.5-Medium", "qualityMeshOption": "18K Quad", "material": "PBR", "textureDelight": true, "TAPose": true}; re-estimate after any tier or HighPack change.wait=false, then jobs_wait with the returned job id, re-called with pending_job_ids on timeout. Full-lane jobs take minutes; a timeout is not a failure and never justifies a second model_run.asset_display the mesh, then asset_download for engine import (details in the scenario-3d skill).images: one still goes as ["asset_x"].addons: "HighPack" versus boolean highPack, geometryInstructMode versus enableCreativeMode, disjoint tier enums.isMicro below Extreme High on the full lane: it changes nothing.model: model is a 3D asset; the image guides the regenerated textures.まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Handle review comments received on GitHub for the current branch's PR or a given PR number or URL, by triaging each unresolved thread, fixing what is warranted, pushing, and replying in each thread, when asked to address, fix or answer PR comments. Works in any Scenario repository.
日本語の概要は準備中です。原文の説明を表示しています。
Generate one short Conventional Commits squash message describing only the net diff between the PR's base and head, set its header as the PR title, validate it with the repository's commitlint and both copy its description to the clipboard and display it, when asked for a squash message. Works in any Scenario repository, whatever its default branch.
日本語の概要は準備中です。原文の説明を表示しています。
Refresh the current pull request description from its net changes, following the repository's PR template, when asked to update or write the PR summary. Works in any Scenario repository, whatever its default branch.
日本語の概要は準備中です。原文の説明を表示しています。
Use when connecting an AI agent to Scenario (scenario.com) through MCP, or when a task involves generating images, video, 3D, audio, sprites, textures, or game assets. Also when picking a Scenario model, running a LoRA, refining a generation prompt, uploading reference images, waiting on generation jobs, checking credits or quota, hitting Scenario auth, scope, or Forbidden errors, or setting up mcp.scenario.com in Claude Code, Cursor, VSCode, or another agent.
日本語の概要は準備中です。原文の説明を表示しています。
Use when generating or handling 3D assets through the Scenario MCP server, including text-to-3D or image-to-3D meshes, GPT-6 Astra 3D or Claude Opus 5.5 3D, GLB, FBX, OBJ, STL, or VOX files, PBR-textured or game-ready models, voxel models, multi-view reconstruction, retexture, remesh, UV unwrap, auto-rigging a biped or quadruped, or retargeting an animation, previewing a mesh in the inline 3D viewer, or downloading a model for import into Unity, Unreal, Godot, or Blender.
日本語の概要は準備中です。原文の説明を表示しています。
Use when generating navigable 3D worlds or Gaussian splat scenes on Scenario via MCP: text-to-world, image-to-world, a 360 panorama or skybox turned into a walkable splat, multi-view photos or a video walkthrough reconstructed as a splat, or one object photo to splat. Keywords: World Labs Marble 1.1, 1.1 Plus, 1.0 Draft, Hunyuan World, HY World, image-to-skybox, skybox-to-splat, multiview-to-splat, TripoSplat, gaussian splatting, 3DGS, spz, world generation, explorable scene, VR.
日本語の概要は準備中です。原文の説明を表示しています。