asset synthesis implemented in bevy and burn, view the live demo
| Input | Output |
|---|---|
![]() |
![]() |
- editor
- native mcp server
- wasm demo
- quantize-aware kernels
| input | output | |
|---|---|---|
| β | image | 3d |
| β | image | foreground |
| β | image | pbr |
| β | text | 3d |
| β¬ | text | image |
| β¬ | image | composite-3d |
| β¬ | many-3d | composite-3d |
| β¬ | image | 4d |
| β¬ | video | 4d |
| β¬ | text | audio |
| β¬ | video | audio |
# burn_synth CLI
cargo install burn_synth
# bevy_synth app
cargo install bevy_synth
# burn_synth MCP stdio server
cargo install burn_synth_mcp# burn_synth: run image -> GLB synthesis
burn_synth mesh \
--quality balanced \
--input docs/output_chair_bg_removed.png \
--output /tmp/chair.glb
# bevy_synth: launch interactive app
bevy_synth --quality balanced
# burn_synth_mcp: start MCP stdio server
burn_synth_mcp- see
docs/SETUP.mdfor full setup and model import/runtime details - supported models:
- foreground: RMBG-1.4, RMBG-2.0
- synthesis: TripoSG, Trellis2
note: pre-trained model weights have separate license
- 16GB VRAM

