Nanosaur-1.2B-Preview-Latest

The original trainer of the model, well9472/Metal63 throughout the project's lifetime would keep deleting the model repo due to an unknown reason. As a silent observer of the project progress, I'm uploading my latest saved checkpoint of the project here to perserve a promising open source image model even if it's original creator have abandoned it. It's also still potentially useful as a toy model for training practice.

Nanosaur 1.2B is a custom pretrained from scratch arch with (will be updated once I scour back arch info- basically a custom arch, Gemma3 270m and a custom VAE called PS-VAE from what I remember), using a mixed 621/Danbooru dataset. So this is actually the first model of 1-3B param range that was trained on e621 since NoobAI XL. Money roughly spent before it was discontinued was somewhere around 1k-3k dollars, with H100 support from Lodestone Rock.

Original README.md:

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