4CGT — 四彫画匠 (Shichō Gashō)
Anime image generation that nails anatomy, follows your prompt, and gives you the same pixel-perfect result on any machine. Every time.
All generated with 4CGT. DoRA v0.271. 42 steps. Same seed = same image on any machine.
GitHub: teenu/4cgt | Website: 4cgt.com | Sponsor: GitHub Sponsors
About
This repo hosts showcase images generated by 4CGT. The tool itself lives on GitHub.
4CGT requires third-party model assets to run. These are not included here — download them from their original sources:
| Asset | Source | License |
|---|---|---|
| NoobAI XL V-Pred 1.0 (BF16) | Laxhar/noobai-XL-Vpred-1.0 | Fair AI Public License 1.0-SD |
| DoRA stabilizers (v0.271 recommended) | Civitai: reakaakasky | See creator's terms |
| Style CSVs (Danbooru/e621) | Laxhar/noob-wiki | Apache-2.0 |
| ControlNet OpenPose SDXL | xinsir/controlnet-openpose-sdxl-1.0 | Apache-2.0 |
See the GitHub README for full setup instructions.
License
4CGT (the tool) is AGPL-3.0. Third-party assets carry their own licenses — see the table above.