Imported from baneeishaque/ljt-520_openclaw-backup (skills/heyixuan2/bambu-studio-ai/SKILL.md). Install upstream with npx skills add baneeishaque/ljt-520_openclaw-backup --skill bambu-studio-ai. Copyright stays with the author.

🖨️ Bambu Studio AI

Request → Collect Info → Search/Generate → Analyze(11pt) → [Colorize] → Slice → Preview(chat) → Preview(BS) → Confirm → Print → Monitor

Pre-check: If config.json does not exist → run First-Time Setup before any operation.

Quick Reference

All scripts support --help. generate.py auto-enhances prompts and limits size to printer build volume.

Overall Flow

User Request
    │
    ▼
Information Collection
    │
    ▼
Decision 1: Model Source
    ├─ A: Internet Search (preferred default)
    ├─ B: AI Generate (single-color)
    ├─ C: AI Generate (multi-color)
    └─ D: User-provided file
    │
    ▼
Model Processing (analyze → repair → orient → [colorize] → slice)
    │
    ▼
Report Results to User
    │
    ▼
⛔ Open in Bambu Studio → User Inspects
    │
    ▼
User Confirms ("looks good" / "print it")
    │
    ▼
Decision 2: Print Method
    ├─ E: Auto Print (bambu.py print --confirmed)
    └─ F: Manual Print (user handles in Bambu Studio)
    │
    ▼
Print Monitoring (auto print only, or on user request)

Step 1: Information Collection

Collect before proceeding:

Model requirements:

• What to print (object description)
• Target dimensions — MUST ask before generating ("How big? e.g., 80mm tall")
• Style / appearance (optional)

Print parameters:

• Single-color or multi-color (AMS)
• Material (default: PLA)
• Quality: draft / standard / fine / extra (optional)
• Purpose: functional or decorative (optional, affects walls + infill)

Model source — ask user:

"Do you want me to:

1. 🔎 Search online — existing models, usually higher quality
2. 🎨 AI generate — custom model from scratch
3. 🤷 Not sure — I'll search first, generate if nothing fits"

Default: search first. Common objects (phone stand, hook, vase) almost always exist online.

Step 2: Model Source (Decision Point 1)

Workflow A — Internet Search (preferred)

1. search.py "query" --limit 5 → MakerWorld, Printables, Thingiverse, Thangs
2. Present results with name, source, URL
3. User selects → download → validate format (STL/OBJ/3MF)
4. → Model Processing

If no good results → offer AI generate.

Workflow B — AI Generate (single-color)

1. First-time disclaimer (once): "AI models depend on provider + prompt. NOT production-ready — always review in Bambu Studio."
2. Confirm dimensions
3. generate.py text "prompt" --wait → auto-enhances, auto-limits to build volume
4. → Model Processing

Workflow C — AI Generate (multi-color)

1. Same disclaimer as B
2. Confirm dimensions + desired colors
3. generate.py text "prompt" --wait → textured GLB
4. colorize.py model.glb --height <size> --max_colors 8 → vertex-color OBJ
   • Pixel HSV classify → greedy area-based color select → CIELAB assign → vertex color
   • No shadow removal needed — HSV classification bypasses baked lighting
5. Show quantized texture preview to user — send the _preview.png image
6. Analyze results and suggest tuning if needed:
   • Report detected colors with names, hex codes, and percentages
   • If small but meaningful colors were lost (e.g., <1% features like eyes, accessories): → Suggest: --min-pct 0 (keep all colors above 0.1%)
   • If similar colors are merged incorrectly (e.g., yellow body + brown pants): → Suggest: --no-merge (disable family mutual exclusion)
   • If too many artifact colors appear: → Suggest: higher --min-pct or --island-size
   • If boundaries are too noisy or too smooth: → Suggest: adjust --smooth (0=none, 5=default, higher=smoother)
7. If user requests changes → re-run colorize with adjusted params → show new preview
8. When user approves → Model Processing

Colorize tunable parameters:

Workflow D — User-Provided File

1. Validate format (STL/OBJ/3MF/GLB), convert if needed
2. → Model Processing

Step 3: Model Processing

All models MUST go through this. No exceptions.

Analysis (11-point check):

analyze.py model.stl --orient --repair --material PLA --purpose functional

Checks: dimensional tolerance, wall thickness, load direction, overhangs (>45°), print orientation, floating parts, layer height, infill rate, wall count, top layers, material compatibility. Also: watertight, manifold, build volume fit.

Auto-repair: Fix normals, fill holes, remove degenerate faces.

Auto-orient: Optimal stability, auto unit detection (meters→mm).

Report to user (MANDATORY):

• Printability score (X/10)
• Warnings and issues
• Repairs performed
• Recommended settings (layer height, infill, walls, temps, supports)

Example: "Score 8/10. Repaired 58K non-manifold edges. Walls: 1.5mm ✅ Overhangs: 3.2% ✅ Recommended: 0.20mm layers, 20% infill, PLA 210°C."

Slice (skip if user will slice in Bambu Studio):

slice.py model.stl --orient --arrange --quality standard

Auto-detects printer + nozzle. Quality: draft(0.24) / standard(0.20) / fine(0.12) / extra(0.08). Output: .3mf with G-code.

Step 4: User Confirmation

⛔ MANDATORY — NEVER SKIP

1. Open in Bambu Studio: open -a "BambuStudio" model_sliced.3mf
2. Tell user to inspect:

   "I've opened the model in Bambu Studio. Please check:

   • Does it look correct? Missing or deformed parts?
   • Floating/disconnected pieces?
   • Correct size? (check dimensions in bottom bar)
   • Any red warnings?
   • Slice and check: estimated time, filament usage, supports. Let me know when ready!"

3. WAIT for explicit confirmation.

⛔ NEVER auto-print. AI models frequently have errors analysis can't fully catch.

4. Ask print method:
   • Direct automatic printing → Workflow E
   • Manual in Bambu Studio → Workflow F

Step 5: Print Execution (Decision Point 2)

Workflow E — Auto Print

1. bambu.py print model.3mf --confirmed
2. Confirm: "Print started!"
3. → Monitoring

Workflow F — Manual Print

• Model already open in Bambu Studio
• User adjusts settings and prints manually
• Agent does NOT auto-print or auto-monitor
• CAN monitor on request

Step 6: Print Monitoring

Trigger: Auto print (Workflow E) or user request. Requires LAN mode + consent.

⚠️ Always ask: "Want me to monitor? Auto-pause on serious issues?"

Silent when normal. Progress summary every 30 min. Completion notification.

First-Time Setup

Triggered when config.json doesn't exist. Conversational:

1. Printer model — A1 Mini, A1, P1S, P2S, X1C, X1E, H2C, H2S, H2D
2. Connection — LAN (recommended: IP + serial + access code) or Cloud (email + password, limited)
3. 3D generation (optional) — Meshy, Tripo, Printpal, 3D AI Studio + API key
4. Notifications — auto / Discord / iMessage / Telegram / etc.
5. Save — config.json + .secrets.json (chmod 600, git-ignored)
6. Verify (ask permission) — test connection, camera, AMS
7. Summary

Environment & Dependencies

Required: python3, pip3

pip3 install bambulabs-api bambu-lab-cloud-api requests trimesh numpy Pillow ddgs

Optional: ffmpeg (camera), Bambu Studio (preview/slicing), Blender 4.0+ (multi-color + HQ preview), OrcaSlicer (CLI slicing)

Env vars (override config.json): BAMBU_MODE, BAMBU_MODEL, BAMBU_EMAIL, BAMBU_IP, BAMBU_SERIAL, BAMBU_3D_PROVIDER

Secrets (.secrets.json, chmod 600): password, access_code, 3d_api_key. All user-provided, never shipped.

Common Issues

Known Limitations

Reference Documents

• references/model-specs.md — All 9 printer specifications
• references/bambu_filament_colors.json — Bambu Lab 43-color palette (reference only, colorize v4 uses texture-native colors)
• references/bambu-mqtt-protocol.md — MQTT protocol
• references/bambu-cloud-api.md — Cloud API
• references/3d-generation-apis.md — Provider API endpoints
• references/3d-prompt-guide.md — Prompt engineering for 3D

License

MIT · GitHub: https://github.com/heyixuan2/bambu-studio-ai