name: anima
display_name: ANIMA 1.0 (Anime Base)
family: anima
kind: txt2img
description: >-
  ANIMA 1.0 — a ~2B DiT anime/illustration text-to-image base model (built on
  NVIDIA Cosmos-Predict2-2B). Danbooru tags + natural language, runs and trains
  on <6GB VRAM. Includes an Anima-LLLite inpainting / ControlNet workflow.
vram: "<6GB"
workflow: workflow.json
skill: anima-base
launch_args: []
sources:
  patreon: https://www.patreon.com/posts/157355820
  model: https://huggingface.co/circlestone-labs/Anima
  mirror: https://huggingface.co/Aitrepreneur/FLX
notes:
  - Run the generated installer from your ComfyUI root (the folder containing
    custom_nodes/ and models/).
  - Anime inpainting uses the kohya-ss ComfyUI-Anima-LLLite node (AnimaLLLiteApply_sdscripts).
  - Turbo LoRA preset is the shipped default — 12 steps, CFG 1.0, er_sde/simple.
post_install:
  - Restart ComfyUI (or use ComfyUI-Manager → Install missing custom nodes for
    any node Python deps).
  - Load workflow.json.