pb-image-to-3d
Turn one reference image into a cleaned, scaled 3D asset: your own image-to-3D ComfyUI workflow makes the mesh, Blender decimates it to a poly budget, fixes scale, origin and material, and exports a .
SKILL.mdskills/playbooks/pb-image-to-3d/SKILL.md
GitHubImage to 3D asset
What you get: a cleaned, scaled .glb from one reference image, with a preview you approved.
Availability: needs the comfyui-mcp server configured in the harness (no config is shipped). Missing → stop at preflight with that message.
Inputs
- image — the reference image path
- comfy_workflow — path to a ComfyUI API-format workflow JSON that contains the image-to-3D nodes; required, never invented (no TripoSR or TRELLIS server ships with AOS)
- poly_budget — maximum face count
- project — a slug for
renders/<project>/
Steps
- Preflight — one probe per server, before any file is written:
check_comfyui_healthoncomfyui-mcp;get_scene_infoonbdb_blender_mcp. MCP tools may be deferred in the harness: try to load the tool once via the harness MCP list before declaring it missing. Tool not loaded, call errors, or ComfyUIstatusis not"online"→ stop with "Missing MCP:<server>(<tool>unavailable). Start <ComfyUI|Blender and click Connect to Claude in the BlenderMCP sidebar tab> and checkmcpServers.<server>in your harness config." (comfyui-mcp: use the Availability message above) and write nothing except the run log — both probes answered - Ask — image, comfy_workflow path, poly_budget, project slug, target size in metres → run log and
renders/<project>/— all answered, image and workflow files exist - ComfyUI — the workflow file's text with the image filled in as the JSON string for
queue_prompt→get_history <prompt_id>status success →get_output_media_infopath of the mesh file — a mesh file exists;local_pathis only set whenCOMFYUI_DIRis set, so iflocal_pathis empty orexists_locallyis false, stop with a clear message and import nothing - Blender (bdb-blender-mcp, godmode-3d-creation) — mesh file → via
execute_blender_code: import, Decimate modifier down to poly_budget, scale to the target size, origin to base centre, one material, and report face count and dimensions;get_scene_infoas the cross-check — face count <= poly_budget and non-zero dimensions; save the Blender project first, since scripted code can crash the session - Preview — a viewport render saved to
renders/<project>/preview.pngviaexecute_blender_code— file exists — stops for approval (taste review); changes loop back to step 4 - Export —
execute_blender_coderuns the glTF binary export →renders/<project>/asset.glb— file exists and is larger than 0 bytes; re-import the file or read the exported object stats and log face count and dimensions again
Run log: production_artifacts/pb-image-to-3d-<date>.md in the start directory, never committed
Rules
- A failed check stops the run: write the failure into the run log and report. No silent retries.
- Write one run-log line per step as it completes (
N. done|skipped|failed — artifact — check result) andWAITING FOR APPROVAL: <step>at each stop. - This playbook has no GO step: it writes only under
renders/<project>/and publishes nothing.