anima-base

1# ANIMA 1.0 (Anima Base Ultra) Text-to-Image Workflows
2 
3## Overview
4 
5Anima is a ~2B-parameter anime / illustration text-to-image base model from CircleStone Labs, made in collaboration with Comfy Org. It is not SDXL-lineage. The architecture is NVIDIA Cosmos-Predict2-2B-Text2Image (a DiT / flow model), trained on several million anime images plus ~800k non-anime artistic images. It suits anime, manga, and illustrated characters and styles, not realism.
6 
7Key traits:
8- Accepts Danbooru-style tags and/or natural language in the same prompt.
9- Very low VRAM. It generates and trains on <6GB VRAM and runs on any PC that can run SDXL/Illustrious.
10- License: CircleStone Labs Non-Commercial License, with NVIDIA Open Model License terms on the weights and derivatives. Generated images are usable commercially per the model card. Verify the current license text before relying on this.
11 
12ComfyUI loads it with standard split-file loaders, not a single checkpoint:
13 
14| Component | Node | Model file | Folder | Notes |
15|-----------|------|-----------|--------|-------|
16| **Diffusion model** | `UNETLoader` | `anima-base-v1.0.safetensors` | `models/diffusion_models/` | weight_dtype `default`; ~4GB fp |
17| **Text encoder** | `CLIPLoader` | `qwen_3_06b_base.safetensors` | `models/text_encoders/` | Qwen3-0.6B base; **`type": "stable_diffusion"`** in this pack |
18| **VAE** | `VAELoader` | `qwen_image_vae.safetensors` | `models/vae/` | Qwen-Image VAE (~254MB) |
19…