Anima 1.0 Aesthetic (SD.Next Diffusers Conversion)
Diffusers-format conversion of Anima 1.0 Aesthetic for use with SD.Next.
Anima is a 2 billion parameter text-to-image model created via a collaboration between CircleStone Labs and Comfy Org. It is focused on anime concepts, characters, and styles, and on non-photorealistic illustration in general; it is not intended for realism. The Aesthetic version is fine-tuned for better consistency and a higher quality default art style.
Original model: circlestone-labs/Anima (split_files/diffusion_models/anima-aesthetic-v1.0.safetensors)
Architecture
- Transformer: CosmosTransformer3DModel (2B params, 28 layers)
- Text Encoder: Qwen3-0.6B (replacing Cosmos T5-11B)
- LLM Adapter: Custom cross-attention adapter bridging Qwen3 to the transformer
- VAE: AutoencoderKLWan
Recommended Settings
- 30-50 steps, CFG 4-5
- Resolutions between 512x512 and 1536x1536
Prompting
- Trained on Danbooru-style tags, natural language captions, and combinations of both. Tags are lowercase with spaces instead of underscores; score tags are the only tags that use underscores.
- The Aesthetic fine-tune strips quality tags from its training captions, so quality tags are unnecessary in the positive prompt; "masterpiece, best quality, " is safe to leave in.
- Recommended negative: "worst quality, low quality, score_1, score_2, score_3, artist name, blurry, jpeg artifacts, chromatic aberration"
- Artist tags require an @ prefix (e.g. "@artist name"); without it the effect is very weak.
- Outputs with too much noise, artifacts, or detail can be tamed by lowering the CFG, removing score_* tags, or adding "anime coloring" to the prompt.
License
CircleStone Labs Non-Commercial License v1.2 (see LICENSE.md). As a derivative of Cosmos-Predict2-2B-Text2Image, the model is also subject to the NVIDIA Open Model License. The non-commercial restriction applies to the model weights, not to generated images.