replacing mcp blender with reproducable flow.

decisions/0059-mac-mini-ray-worker.md

@@ -12,9 +12,9 @@
 
 - All Ray inference slots are already allocated and stable — adding a 5th GPU class (MPS) increases complexity without filling a gap
 - vLLM's MPS backend remains experimental — not production-ready for serving
-- The real unmet need is **3D avatar creation** for companions-frontend ([ADR-0062](0062-blender-mcp-3d-avatar-workflow.md))
+- The real unmet need is **3D avatar creation** for companions-frontend ([ADR-0063](0063-comfyui-3d-avatar-pipeline.md))
 
-[ADR-0062](0062-blender-mcp-3d-avatar-workflow.md) describes using BlenderMCP in a Kasm Blender workstation for AI-assisted avatar creation. While Kasm works, it runs Blender inside a DinD container with **no GPU acceleration** — rendering and viewport interaction are CPU-only, which is painfully slow for sculpting, material preview, and VRM export iteration.
+[ADR-0063](0063-comfyui-3d-avatar-pipeline.md) describes an automated ComfyUI + TRELLIS + UniRig pipeline for image-to-VRM avatar generation, running on a personal desktop as an on-demand Ray worker. This supersedes the manual BlenderMCP Kasm workflow from [ADR-0062](0062-blender-mcp-3d-avatar-workflow.md). waterdeep retains its role as an interactive Blender workstation for manual refinement of auto-generated models.
 
 waterdeep's M4 Pro has a 16-core GPU with hardware-accelerated Metal rendering and 48 GB of unified memory shared between CPU and GPU. Running Blender natively on waterdeep with BlenderMCP gives a dramatically better 3D creation experience than Kasm.
 
@@ -26,9 +26,9 @@ How should we use waterdeep to maximise the 3D avatar creation pipeline for comp
 * waterdeep has a 16-core Apple GPU with Metal support — Blender's Metal backend enables real-time viewport rendering, Cycles GPU rendering, and smooth sculpting
 * 48 GB unified memory means Blender, VS Code, and the MCP server can all run simultaneously without swapping
 * VS Code with Copilot agent mode and BlenderMCP server are installed on waterdeep — VS Code drives Blender via localhost:9876 with zero-latency socket communication
-* Exported VRM models must reach gravenhollow for production serving ([ADR-0062](0062-blender-mcp-3d-avatar-workflow.md))
+* Exported VRM models must reach gravenhollow for production serving ([ADR-0063](0063-comfyui-3d-avatar-pipeline.md))
 * **rclone** chosen for asset promotion to gravenhollow's RustFS S3 endpoint — simpler than NFS mounts on macOS, consistent with existing Kasm rclone patterns, and avoids autofs/NFS fstab complexity
-* The Kasm Blender workflow from ADR-0062 remains available as a fallback (browser-based, no local install required)
+* The automated ComfyUI pipeline from [ADR-0063](0063-comfyui-3d-avatar-pipeline.md) handles most avatar generation; waterdeep serves as the manual refinement station
 * ray cluster GPU fleet is fully allocated and stable — adding MPS complexity is not justified
 
 ## Considered Options
@@ -204,7 +204,7 @@ uvx blender-mcp --help
 
 ### 4. rclone for Asset Promotion
 
-Use rclone to promote finished VRM exports to gravenhollow's RustFS S3 endpoint. This is consistent with the Kasm rclone volume plugin pattern from [ADR-0062](0062-blender-mcp-3d-avatar-workflow.md) and avoids macOS NFS/autofs complexity.
+Use rclone to promote finished VRM exports to gravenhollow's RustFS S3 endpoint. This is consistent with the promotion pattern from [ADR-0063](0063-comfyui-3d-avatar-pipeline.md) and avoids macOS NFS/autofs complexity.
 
 ```bash
 # Install rclone
@@ -275,7 +275,8 @@ rclone sync ~/blender-avatars/exports/ gravenhollow:avatar-models/ --exclude "*.
 
 ## Links
 
-* Related: [ADR-0062](0062-blender-mcp-3d-avatar-workflow.md) — BlenderMCP 3D avatar workflow (Kasm + deployment architecture)
+* Related: [ADR-0063](0063-comfyui-3d-avatar-pipeline.md) — ComfyUI image-to-3D avatar pipeline (supersedes ADR-0062)
+* Related: [ADR-0062](0062-blender-mcp-3d-avatar-workflow.md) — BlenderMCP 3D avatar workflow (superseded)
 * Related: [ADR-0046](0046-companions-frontend-architecture.md) — Companions frontend architecture (Three.js + VRM avatars)
 * Related: [ADR-0026](0026-storage-strategy.md) — Storage strategy (gravenhollow NFS-fast)
 * Related: [ADR-0037](0037-node-naming-conventions.md) — Node naming conventions (waterdeep)