
Game Asset Generation
Generates game images, 3D models, voices and sound effects locally or via APIs.
Install
npx skills add htdt/godogen --skill asset-gen -g -a claude-code -y- Repository
- htdt/godogen7.3k
- Category
- Media
- Updated
- 19d ago
- License
- MIT
- Context cost
- Lightabout 1,296 tokens
- Runs scripts
- Yes, review before use
What it does
Generate game assets, locally and free by default with godogen_assets: images and transparent PNGs (Qwen-Image), textured GLB models (TRELLIS.2), rigged humanoids with generated moves and lip-synced speech, sound effects and voice lines. Paid APIs cover what the local tools can't make, Gemini / xAI Grok images, animated sprites from video, Tripo 3D, Gemini TTS voice acting, Lyria music. Use whenever a game needs generated art or audio.
Asset Generator
Assets come from godogen_assets: local generators on this machine's GPU, one command per task, free. Its checkout here is ${GODOGEN_ASSETS}, and its docs are the reference; this page is the TL;DR plus what the game needs on top. Read ${GODOGEN_ASSETS}/README.md once (conventions, a character start to finish, checking results), and a part's README up to How it works before first using its tool.
| Command | Makes | README in the checkout |
|---|---|---|
qwen-image | PNG from text; rgba: real transparency; edit -i ref.png: image-to-image | image/ |
gen3d | textured GLB from an image | mesh/ |
mia-rig | Mixamo-rigged humanoid from a GLB | rig/ |
add-moves, gen-moves | idle/walk/run/jump onto a rig; custom moves from text prompts | motion/ |
grip-prop | a prop made holdable; add-moves --hold puts it in a character's hand | motion/ |
lipsync | speaking mouth + lip-synced clip from a voice line | lipsync/ |
stable-audio | sound effects, seamless ambience loops | sfx/ |
qwen-tts | voice lines from a description, or cloned from a reference line | voice/ |
A character: qwen-image rgba (T-pose) → gen3d → mia-rig --fingers --anim none → add-moves, with gen-moves for custom moves and lipsync for speech. Props stop after gen3d; one a character holds goes on through grip-prop and add-moves --hold, never by an offset tuned in the engine.


