{
  "model_type": "anisee",
  "architecture": "Cosmos-Predict2-2B (Anima Derivative)",
  "parameters": "2B",
  "license": "circlestone-labs-non-commercial",
  "base_model": "circlestone-labs/Anima",
  "base_model_relation": "finetune",
  "author": "SeeSee21",
  "pipeline_tag": "text-to-image",
  "training": {
    "steps": "~20000",
    "dataset": "curated anime dataset",
    "adapter_co_training": "lightly co-trained (per Anima guidelines)"
  },
  "prompting": {
    "style": "tags + natural-language (mixed prompts supported)",
    "negative_prompt_support": "full",
    "recommended_prefix": "masterpiece, best quality, score_7, highres, illustration,",
    "tag_rules": {
      "case": "lowercase",
      "separator": "spaces (not underscores)",
      "score_tags_exception": "score_7, score_8, etc. use underscores",
      "artist_tags": "must be prefixed with @ (e.g. @artistname)"
    }
  },
  "variants": {
    "base": {
      "file": "anisee.safetensors",
      "size": "~4.18 GB",
      "comfyui_path": "ComfyUI/models/diffusion_models/",
      "recommended_settings": {
        "steps": 40,
        "cfg": 4.5,
        "sampler": "er_sde",
        "scheduler": "simple",
        "resolution": "832x1216 (portrait, ~1 MP)"
      },
      "alternative_samplers": [
        "euler_a",
        "dpmpp_2m_sde_gpu"
      ]
    }
  },
  "planned_variants": {
    "aio": {
      "description": "All-in-one checkpoint (Model + Text Encoder + VAE in one file)",
      "status": "planned"
    },
    "turbo_4step": {
      "description": "4-Step Turbo variant distilled with CDM (Continuous-Time Distribution Matching)",
      "paper": "https://byliutao.github.io/cdm_page/",
      "status": "planned (pending Base validation)"
    }
  },
  "components": {
    "text_encoder": {
      "file": "text_encoders/qwen_3_06b_base.safetensors",
      "description": "Anima / Qwen3 0.6B text encoder",
      "comfyui_path": "ComfyUI/models/text_encoders/"
    },
    "vae": {
      "file": "vae/qwen_image_vae.safetensors",
      "description": "Qwen-Image VAE (inherited from Anima)",
      "comfyui_path": "ComfyUI/models/vae/"
    }
  },
  "comfyui_paths": {
    "diffusion_models": "ComfyUI/models/diffusion_models/",
    "text_encoders": "ComfyUI/models/text_encoders/",
    "vae": "ComfyUI/models/vae/",
    "upscale_models": "ComfyUI/models/upscale_models/"
  },
  "requirements": {
    "custom_nodes": [
      "ComfyUI-Easy-Use",
      "ComfyUI_UltimateSDUpscale",
      "ComfyUI-Lora-Manager",
      "ComfyUI-QwenVL",
      "rgthree-comfy"
    ],
    "optional_upscale_model": {
      "file": "4x-UltraSharp.pth",
      "sources": [
        "https://openmodeldb.info/models/4x-UltraSharp",
        "https://huggingface.co/Kim2091/UltraSharp"
      ]
    }
  },
  "supported_vram": "8GB+",
  "links": {
    "civitai": "https://civitai.red/models/2628747/anisee",
    "gallery": "https://anisee.anisee.workers.dev/",
    "base_model": "https://huggingface.co/circlestone-labs/Anima",
    "cdm_paper": "https://byliutao.github.io/cdm_page/",
    "author": "https://huggingface.co/SeeSee21"
  },
  "notes": [
    "Drop-in replacement for anima-preview3-base.safetensors.",
    "Uses the same Qwen text encoder and Qwen-Image VAE as Anima.",
    "Tag rules: lowercase, spaces (not underscores), except score_7 etc. Artist tags prefixed with @.",
    "Official ComfyUI workflow included in workflows/ with auto Quality Prefix and Qwen3-VL Prompt Enhancer.",
    "AIO and 4-Step Turbo (CDM) variants planned for future releases."
  ]
}