SuperAPI AI Directory

image-to-3d-pipeline

Design & creation

View repository

Updated 10-16 05:50

About this skill

Image to 3D Pipeline

Turn a 2D image into an animated 3D model ready for the web or a game in under 30 minutes, using the Dilum Sanjaya workflow (Hunyuan3D + Mixamo).

When to Use This Skill

  • Create a 3D character for a website - Mascot, avatar, interactive illustration
  • Prototype a game asset - Character design, props, environments
  • Produce 3D marketing content - Rotating products, animated characters
  • Convert existing illustrations - Logo, mascot, character design → 3D
  • Test an idea quickly - 3D prototype in 30 minutes instead of days

Methodology Foundation

Source: Dilum Sanjaya (@DilumSanjaya) - Game Character Pipeline (2025-2026)

Core Principle: "The 2D image is your blueprint. Hunyuan3D generates the mesh, Mixamo adds the rig automatically. In 30 minutes, you have an animated character usable in Three.js or Unity."

Why This Matters: Traditionally, going from a 2D concept to a rigged 3D model took days of modeling work. This workflow reduces the time to less than an hour while producing assets of sufficient quality for production.

What Claude Does vs What You Decide

Claude Does You Decide
Structures video workflow Final creative vision
Suggests shot compositions Equipment selection
Creates storyboard templates Brand aesthetics
Generates script frameworks Final approval
Identifies technical requirements Budget allocation

What This Skill Does

  1. Guides the choice of 3D tool - Hunyuan3D vs Tripo vs Meshy depending on the use case
  2. Structures the complete workflow - From source image to exported model
  3. Optimizes the generated mesh - Polygon reduction, texture correction
  4. Automates rigging - Mixamo setup for characters
  5. Prepares the export - GLB/FBX formats depending on the destination

How to Use

Convert a character design into an animated 3D character

J'ai cette image de personnage [joindre image]. Aide-moi à la convertir en modèle 3D animé avec le skill image-to-3d-pipeline.

Create a rotating 3D product

Je veux créer un modèle 3D de mon produit [description] à partir de photos. Guide-moi avec le pipeline image-to-3d.

Prototype a brand mascot

Voici le design de notre mascotte [image]. Je veux la transformer en 3D pour notre site web avec des animations idle.

Instructions

When you help convert a 2D image to 3D, follow this process:

Step 1: Evaluate the source image

## Analyse de l'Image Source

**Type d'image:**
[ ] Character design / Personnage
[ ] Objet / Produit
[ ] Illustration / Logo
[ ] Photo réelle

**Qualité pour conversion 3D:**
[ ] ✅ Vue frontale claire
[ ] ✅ Fond simple ou transparent
[ ] ✅ Couleurs/textures distinctes
[ ] ✅ Proportions cohérentes
[ ] ⚠️ Détails complexes (peut perdre en conversion)

**Complexité estimée:**
[ ] Simple - Forme géométrique basique
[ ] Moyenne - Personnage ou objet organique
[ ] Complexe - Détails fins, accessoires multiples

Key points:

  • Front views give better results
  • Transparent/white backgrounds simplify processing
  • Characters with distinct limbs rig better

Step 2: Choose the conversion tool

Tool Strengths Ideal for Limitations
Hunyuan3D Best texture, open source Characters, detailed objects Cleanup sometimes necessary
Tripo AI Simple UX, auto rigging Rapid prototypes Less control
Meshy Good for stylized Cartoon/low-poly assets Less realistic textures
Rodin Gen-1 Speed, game-ready topology Game assets Less fidelity
CSM Multi-view consistency Complex objects Slower

Recommendation by use case:

  • Character for web → Hunyuan3D + Mixamo
  • Rapid prototype → Tripo AI
  • Stylized game asset → Meshy or Rodin
  • Realistic product → Hunyuan3D + post-processing

Step 3: Conversion pipeline

## Pipeline Standard (Hunyuan3D)

### A. Préparation de l'image
1. Supprimer le fond (remove.bg ou outil intégré)
2. Recadrer serré sur le sujet
3. Résolution recommandée: 1024x1024 minimum
4. Sauvegarder en PNG (préserver transparence)

### B. Génération 3D
1. Uploader sur Hunyuan3D (hunyuan3d.tencent.com)
2. Sélectionner mode: "Image to 3D"
3. Paramètres recommandés:
   - Quality: High
   - Texture: Enable
   - Multi-view: Enable (si disponible)
4. Générer et télécharger (GLB ou OBJ)

### C. Validation du mesh
- Ouvrir dans Blender ou viewer en ligne
- Vérifier: topology, textures, scale
- Identifier problèmes: trous, textures manquantes

Step 4: Optimization and cleanup

## Checklist Optimisation

### Mesh
[ ] Poly count acceptable (< 50k pour web, < 100k pour jeu)
[ ] Pas de faces inversées
[ ] Pas de vertices orphelins
[ ] Mesh manifold (étanche)

### Textures
[ ] UV map correcte
[ ] Résolution appropriée (1024x1024 ou 2048x2048)
[ ] Pas de stretching visible
[ ] Couleurs fidèles à l'original

### Scale
[ ] Proportions correctes
[ ] Orientation (Y-up ou Z-up selon destination)
[ ] Centré sur origin

Cleanup tools:

  • Blender (free) - Decimate modifier, texture paint
  • Meshlab (free) - Automatic repair
  • gltf-transform (CLI) - GLB optimization for web

Step 5: Rigging with Mixamo (characters only)

## Workflow Mixamo

1. Exporter le mesh en FBX (sans textures embarquées)
2. Uploader sur mixamo.com
3. Positionner les markers:
   - Chin
   - Wrists
   - Elbows
   - Knees
   - Groin
4. Sélectionner "Auto-Rig"
5. Choisir animations:
   - Idle (standing, breathing)
   - Walk
   - Run
   - Autres selon besoin
6. Télécharger en FBX avec skin

Recommended animations for web:

  • Idle - Basic animation
  • Walking - For movement
  • Waving - Interaction
  • Talking - If voice-over

Step 6: Export and integration

Destination Format Notes
Three.js / Web GLB Recommended format, embedded textures
Unity FBX Native import, configure materials
Unreal FBX Requires skeleton retargeting
React Three Fiber GLB Use gltfjsx for component
# Optimisation GLB pour web (gltf-transform)
npx @gltf-transform/cli optimize input.glb output.glb --compress draco

Target size:

  • Hero 3D (first thing visible): < 2MB
  • Secondary asset: < 500KB
  • Animated character: < 5MB

Examples

Example 1: Game character - Character Selection Screen

Input: Character concept art (cartoon style)

Process:

  1. Nano Banana → Coherent character sheet generation
  2. Hunyuan3D → Conversion to 3D mesh
  3. Blender → Quick cleanup (5 min)
  4. Mixamo → Auto-rig + idle/select animations
  5. Three.js → Integration with rotation on hover

Output: Interactive 3D character with 3 animations Total time: ~45 minutes

Basic Three.js code:

import { useGLTF, useAnimations } from '@react-three/drei'

function Character({ url }) {
  const { scene, animations } = useGLTF(url)
  const { actions } = useAnimations(animations, scene)

  useEffect(() => {
    actions['idle']?.play()
  }, [])

  return <primitive object={scene} />
}

Example 2: Brand mascot for landing page

Input: 2D illustration of company mascot

Process:

  1. Background cleanup (remove.bg)
  2. Hunyuan3D → 3D mesh with textures
  3. No rigging (static)
  4. Optimized GLB export
  5. Spline or Three.js → Simple CSS/JS animation (rotation, bounce)

Output: Rotating 3D mascot in hero section Total time: ~20 minutes


Example 3: 360° e-commerce product

Input: 4 product photos (front, back, sides)

Process:

  1. CSM → Multi-view reconstruction (best for objects)
  2. Blender cleanup → Simplify geometry
  3. Bake high-resolution textures
  4. Export GLB
  5. model-viewer → Responsive 3D viewer

Output: Interactive 3D viewer with zoom/rotation Total time: ~1 hour

model-viewer code:

<model-viewer
  src="product.glb"
  ar
  auto-rotate
  camera-controls
  shadow-intensity="1"
></model-viewer>

Checklists & Templates

Pre-Conversion Checklist

## Image Source
[ ] Résolution suffisante (min 1024x1024)
[ ] Fond transparent ou uniforme
[ ] Sujet bien délimité
[ ] Style cohérent (pas de mix photo/illustration)

## Objectif
[ ] Destination claire (web/jeu/vidéo)
[ ] Poly budget défini
[ ] Animations nécessaires identifiées
[ ] Format d'export choisi

3D Brief Template

## Brief Conversion 2D → 3D

**Image source:** [joindre]
**Type:** [ ] Personnage [ ] Objet [ ] Logo [ ] Autre

**Destination finale:**
- Plateforme: _______________
- Interaction: [ ] Statique [ ] Rotation [ ] Animation complète
- Taille max: ___ MB

**Style souhaité:**
- [ ] Fidèle à l'original
- [ ] Stylisé/Low-poly
- [ ] Réaliste

**Animations (si personnage):**
- [ ] Idle
- [ ] Walk
- [ ] Autres: _______________

**Contraintes:**
- _______________

Tool Comparison Matrix

Criterion Hunyuan3D Tripo AI Meshy Rodin CSM
Texture quality ⭐⭐⭐⭐⭐ ⭐⭐⭐ ⭐⭐⭐ ⭐⭐⭐⭐ ⭐⭐⭐⭐
Speed ⭐⭐⭐ ⭐⭐⭐⭐⭐ ⭐⭐⭐⭐ ⭐⭐⭐⭐⭐ ⭐⭐
Ease of use ⭐⭐⭐ ⭐⭐⭐⭐⭐ ⭐⭐⭐⭐ ⭐⭐⭐⭐ ⭐⭐⭐
Cleanup required Medium Low Low Low Medium
Price Free Freemium Freemium Paid Freemium
Best for Characters Prototypes Stylized Games Multi-view

Troubleshooting

Problem Probable cause Solution
"Exploded" mesh Non-transparent background Remove background before upload
Missing textures Export without embedding Re-export with packed textures
Rigging fails Pose is not T-pose Modify pose in Blender before Mixamo
File too heavy Too many polygons Use Decimate modifier
Choppy animations Incompatible FPS Re-export at 30fps

Skill Boundaries

What This Skill Does Well

  • Structuring video production workflows
  • Creating storyboard frameworks
  • Suggesting technical approaches
  • Providing creative direction templates

What This Skill Cannot Do

  • Replace professional videography
  • Edit video files directly
  • Make final creative judgments
  • Guarantee audience engagement

References

Tools

Tutorials

  • Dilum Sanjaya: Character to 3D workflows (X/Twitter)
  • Three.js Fundamentals: Loading 3D models
  • React Three Fiber: useGLTF documentation

Research

  • docs/research-ai-design-workflows-2026-01.md - Deep research 75+ sources

Related Skills

  • character-design-ai/ - Generate consistent character images (input for this skill)
  • vibe-coding-design/ - Fast iterative methodology
  • ai-ui-generation/ - Integrate 3D into a generated interface

Skill version: 1.0 Last updated: 2026-01-28 Category: ai-design