kayforkind/skill-slice/3d-image-to-model
Claude Code and agent skill by kayforkind/skill-slice
- community
Checking that the SKILL.md file is still in the repository.
Converts a 2D image, photo set, or SVG into a 3D mesh or printable STL (depth maps, photogrammetry, extrusion, lithophanes). Use when the user wants image-to-3D, photo-to-mesh, heightmap STL, or lithophane. Not for game engine meshes or Godot/Blender scene lighting. Never assume this folder ships helper scripts.
Install
npx vskill@latest install kayforkind/skill-slice/3d-image-to-modelSKILL.md
The same SKILL.md was published earlier as kayforkind/skill-slice/3d-image-to-model.
When to Use
Use this skill when the user wants to convert 2D images into 3D models or printable STL files. Trigger keywords: "image to 3D", "photo to 3D", "depth map to mesh", "lithophane", "SVG extrusion", "photogrammetry", "Meshroom", "COLMAP", "MiDaS", "Depth Anything", "Meshy", "Tripo3D", "InstantMesh", "heightmap to STL", "relief model".
Approach Selection Matrix
| Method | Input | Speed | Quality | Best For | |
|---|---|---|---|---|---|
| AI Image-to-3D | 1 image | Seconds–minutes | Approximate | Concept art, game assets, prototyping | |
| Depth Estimation | 1 image | Seconds | Relief / 2.5D | Bas-reliefs, heightmaps, lithophanes | |
| Photogrammetry | 30–200+ images | Hours | High fidelity | Real-world objects, archival | |
| SVG Extrusion | Vector art | Instant | Exact | Logos, text, flat designs | |
| Lithophane | 1 photo | Minutes | Photo-quality | Backlit photo displays |
Prerequisites
Python Environment (Windows / PowerShell)
GPU Requirements by Method
| Method | VRAM Minimum | Notes | |
|---|---|---|---|
| MiDaS DPT_Large | 2 GB | Runs on CPU if no GPU | |
| Depth Anything V2 Large | 4 GB | CPU fallback supported | |
| Depth Anything V2 Small | 1 GB | Real-time, low-resource | |
| Marigold | 8 GB | Diffusion-based, slow | |
| InstantMesh | 8 GB | NVIDIA GPU required |
External Tools
- Meshroom: Download from AliceVision releases; NVIDIA GPU required for full pipeline.
- COLMAP: Install from
https://colmap.github.io/; available as CLI or GUI. - OpenSCAD: Install for SVG extrusion method (
https://openscad.org/). - MeshLab: Install for mesh cleanup; CLI via
meshlabserver. - Blender: Optional for advanced mesh editing and retopology.
API Keys (if using commercial AI tools)
- Meshy AI: Register at
meshy.aito obtain an API key. Store as environment variable:
``powershell $env:MESHY_API_KEY = "YOUR_KEY" ``
- Tripo3D: Browser-based at
tripo3d.ai; no API key needed for basic use.
Procedure
Step 0 — Determine Input Type and Select Approach
- Single image, 3D object → AI tools (Meshy, Tripo3D) or InstantMesh (Step 1).
- Single image, relief / heightmap → Depth estimation +
heightmap_to_stl(Step 2 → Step 3). - Multiple photos, real object → Photogrammetry (Meshroom or COLMAP) (Step 4).
- Vector art / logo → SVG extrusion (Step 5).
- Photo display (backlit) → Lithophane:
heightmap_to_stlwithinvert=True(Step 3).
Step 1 — AI Image-to-3D Tools
Meshy AI
- URL:
meshy.ai - Capabilities: Text-to-3D, Image-to-3D, AI texturing, retopology
- Output formats: GLB, FBX, OBJ, STL
- Workflow:
- Upload a reference image (clear, well-lit, single object).
- Select style preset (realistic, cartoon, low-poly).
- Generate initial mesh (30–60 seconds).
- Refine with AI texturing or manual edits.
- Export as STL for 3D printing.
Tripo3D (Tripo AI)
- URL:
tripo3d.ai - Capabilities: Image-to-3D, text-to-3D, integrated editing/rigging
- Output formats: GLB, OBJ, FBX
- Workflow:
- Upload image or enter text prompt.
- AI generates mesh in 10–30 seconds.
- Use built-in editing tools (segmentation, cleanup).
- Export mesh for printing.
InstantMesh (Open-Source, Local)
- Repo:
github.com/TencentARC/InstantMesh - Architecture: Multi-view diffusion (Zero123++) + Large Reconstruction Model (LRM)
- Requirements: NVIDIA GPU with 8+ GB VRAM
Other Notable AI Tools
| Tool | Type | Highlights | |
|---|---|---|---|
| Wonder3D | Open-source | Multi-view generation + reconstruction | |
| Shap-E (OpenAI) | Open-source | Text/image to 3D; lightweight | |
| Rodin AI | Commercial | High-fidelity textures | |
| Stable Zero123 | Open-source | Single-view 3D diffusion | |
| LGM | Open-source | Large Gaussian Model; fast inference |
Step 2 — Depth Estimation
MiDaS (Intel Labs)
- Architecture: DPT (Dense Prediction Transformer)
- Output: Relative depth map (grayscale image)
- Models:
midas_v21_small,dpt_large,dpt_swin2_large - Strengths: Robust, well-tested, runs on CPU
Depth Anything V2 (TikTok / ByteDance)
- Architecture: DINOv2 backbone + DPT decoder
- Models:
vits(25M params),vitb(97M),vitl(335M) - Strengths: State-of-the-art quality, fast, multiple model sizes
Marigold (ETH Zurich)
- Architecture: Diffusion-based depth estimation
- Strengths: Fine detail, sharp edges, handles complex scenes
- Trade-off: Slower than feed-forward models (diffusion denoising steps)
- VRAM: 8 GB minimum
Model Comparison
| Model | Speed | Quality | VRAM | Best For | |
|---|---|---|---|---|---|
| MiDaS DPT_Large | Fast | Good | 2 GB | CPU-friendly general use | |
| Depth Anything V2 Large | Fast | Excellent | 4 GB | Best overall quality/speed | |
| Depth Anything V2 Small | Very Fast | Good | 1 GB | Real-time, low-resource | |
| Marigold | Slow | Excellent | 8 GB | Maximum detail, research |
Step 3 — Depth Map to 3D Mesh Conversion
Option A: numpy-stl Heightmap (Simpler, Recommended for Relief/Lithophane)
This is the start of the file. Read the full SKILL.md on GitHub.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/3d-image-to-model/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/kayforkind/skill-slice/3d-image-to-model)