meshy

# 3D Model Generation (Multi-Provider) Generate 3D models from text prompts, images, or apply textures to existing models. Four providers with different cost/quality tradeoffs. ## Provider Selection | Provider | Script | Cost | Speed | Best for | |----------|--------|------|-------|----------| | **Meshy** (default) | `meshy_text_to_3d.py`, `meshy_image_to_3d.py` | 5-20 credits | 2-7 min | Text-to-3D, texturing, low-poly game assets, batch | | **fal.ai Hunyuan3D** | `fal_hunyuan3d.py` | $0.225 | ~2 min | High-fidelity image-to-3D with PBR, text-to-3D | | **WaveSpeedAI Rapid** | `wavespeed_rapid.py` | $0.0225 | ~1 min | Bulk iteration, concept validation (16x cheaper) | | **Trellis 2** | `trellis2.py` | 15-55 credits | 30s-4 min | Precise poly count control, geometry-only fast runs | | **Local Depth** | `depth_local.py` | Free | ~5s | Offline depth maps, local mesh gen, preprocessing | **Decision guide:** - Quick concept check → WaveSpeedAI ($0.02, fastest) - Production image-to-3D → fal.ai Hunyuan3D (best PBR quality) - Text-to-3D → Meshy (only provider with text prompt support + refine pipeline) - Specific poly budget → Trellis 2 (`--decimation 5000` for low-poly) - Batch generation → Meshy (`meshy_batch.py` with manifest) - Free offline depth/mesh → Local Depth (zero API cost, ONNX on-device) - Depth map as preprocessing → Local Depth + any cloud provider for texturing ## Prerequisites ```bash # API key in environment (already in ~/.config/env/secrets.env) export MESHY...