#2828th of 75 in Image and videoFor image, video and design, 3d
image-to-3dlab
Local pipeline from text or image to rigged, animated 3D game characters
- Stars
- 1.2k
- License
- Apache-2.0
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- Python
9 on 4 Aug 20261,169 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
AssetFurnace is a browser studio that turns a sentence or picture into a textured 3D model, cleans it up for games, rigs it with SkinTokens and applies one of 21 animation presets, exporting GLB. It wraps Pixal3D, TRELLIS.2, Hunyuan3D and Stable Fast 3D on Apple Silicon, NVIDIA or AMD (ROCm), and ships an MCP server for agents. Source pictures come from FLUX.2 klein 4B or Qwen-Image run locally.
Who it is for: Game developers wanting local text/image-to-rigged-3D asset generation
Strengths
- Full local pipeline: image, 3D model, rig, animation and GLB export in one studio
- Pixel Match restores source-image pixels on low-poly models, keeping text and logos sharp
- Runs on Apple Silicon, NVIDIA and AMD ROCm (Pixal3D only on AMD)
- Built-in MCP server lets Claude Code, Codex and other agents drive it
Weaknesses
- Weights run roughly 8 to 20 GB per backend and are downloaded separately
- TRELLIS.2 and Hunyuan3D-2.1 CUDA routes are Linux-only and untested on real hardware
- Windows has limited testing; MCP agent use is untested there
- Several backend weights carry non-OSI licences (Tencent, Stability, DINOv3)
What it needs
- GPU required
- Needs Python 3.11, uv, Xcode (Metal builds on Mac), CUDA toolkit (some NVIDIA builds), ROCm HIP SDK (AMD), Hugging Face access for gated weights
- Models: Pixal3D, TRELLIS.2, Hunyuan3D-2.1, Hunyuan3D-MLX, Stable Fast 3D
What changed
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in Image and video
See all 75| Rank | Project | Score |
|---|---|---|
| 1 | frigateLocal NVR with realtime object detection for IP cameras | 93 out of 100 |
| 2 | MoneyPrinterTurboGenerates short videos from a topic, with script, footage, voiceover and subtitles | 88 out of 100 |
| 3 | toonflow-appInfinite-canvas tool for AI short drama and comic video production | 87 out of 100 |
| #4 | InvokeAIWeb UI for diffusion image generation with inpainting canvas and node workflows | 86 out of 100 |
| #5 | ComfyUINode-graph editor for running diffusion image, video, audio and 3D workflows | 85 out of 100 |