| license: mit | |
| WIP model for research purposes. Still in progress. 18 days of 1xH100 from scratch. | |
| Install instructions | |
| Copy nanosaur_support folder to custom_nodes in ComfyUI | |
| Copy diffusion model, text encoder and VAE to model folders in ComfyUI | |
| Start ComfyUI | |
| Drag nanosaur_workflow.json onto ComfyUI | |
| Tags or natural language. | |
| Model responds well to prompt emphasis like (character:2) or (artist:2) | |
| Lora training: | |
| uv run cache_lora.py --dataset-dir /path/to/images_and_txt_caption_files --batch-size 4 | |
| uv run train_lora.py --cache-path cache/lora_latents.pt --batch-size 1 --rank 16 --alpha 16 |