Anima: 2B Parameter Anime Text-to-Image Model by Circlestone Labs

Anima is a 2 billion parameter text-to-image model by Circlestone Labs and Comfy Org, focused on anime concepts and artistic styles. Available in Base, Aesthetic, and Turbo variants for ComfyUI.

A

Anima by Circlestone Labs

Text-to-ImageAnimeArtisticCosmos-Predict2

Anima is a 2 billion parameter text-to-image diffusion model created through a collaboration between Circlestone Labs and Comfy Org. It focuses on anime concepts, characters, and artistic styles, but can also handle a wide variety of non-photorealistic content. The model is trained on millions of anime images and about 800K non-anime artistic images, with no synthetic data used for training. The knowledge cut-off date for the anime training data is September 2025.

Anima model montage showcasing anime and artistic styles

Versions

VersionDescriptionRecommendation
Anima Base v1.0Pretrained, unrefined base model. Maximum flexibility, diversity, and style adherence.Train LoRAs using this version
Anima Aesthetic v1.0Fine-tuned for better consistency and higher quality default art style.Best overall quality
Anima Aesthetic v1.0bAlternate aesthetic version — pure aesthetics full fine-tune without additional style adjustment and stabilization LoRAs merged in (unlike v1.0).Niche
Anima Aesthetic v1.1Updated aesthetic-tuned variantLatest aesthetic
Anima Turbo v1.0Distilled version for fast generations. Use at CFG 1 and 8-12 steps.Recommended start — fast, stable, slightly lower quality than Aesthetic
Anima PreviewEarly preview versionDevelopment
Anima Preview 2Updated preview versionDevelopment
Anima Preview 3 BaseLatest preview built on base variantDevelopment

Installation

The model is natively supported in ComfyUI. Place files in their respective folders:

FileDestination
anima-*.safetensorsComfyUI/models/diffusion_models/
qwen_3_06b_base.safetensorsComfyUI/models/text_encoders/
qwen_image_vae.safetensorsComfyUI/models/vae/

Generation settings

  • Resolution: 512² to 1536² pixels
  • Steps: 30-50 (Base/Aesthetic), 8-12 (Turbo)
  • CFG: 4-5 (Base/Aesthetic), 1 (Turbo)
  • Recommended samplers: er_sde (neutral default), euler_a (softer lines), dpmpp_2m_sde_gpu (more creative), euler (good with Turbo/Aesthetic)
  • Scheduler tip: beta57 (ComfyUI RES4LYF custom node pack) can improve textures for more realistic/painterly looks

Prompting

The model is trained on Danbooru-style tags, natural language captions, and combinations of both.

Format

[quality/meta/year/safety tags] [1girl/1boy/1other etc] [character] [series] [artist] [general tags]

Quality tags

  • Human score based: masterpiece, best quality, good quality, normal quality, low quality, worst quality
  • PonyV7 aesthetic model based: score_9, score_8, ..., score_1
  • Use either system, both, or neither
  • Positive prefix: masterpiece, best quality, score_7, safe,
  • Negative: worst quality, low quality, score_1, score_2, score_3, artist name, blurry, jpeg artifacts, chromatic aberration

Tips

  • Use lowercase for tags, spaces instead of underscores (score tags use underscores)
  • When a tag differs between Danbooru and Gelbooru, prefer Gelbooru
  • Prompt weighting works but needs higher values than SDXL: (chibi:2)
  • Aesthetic version: Don't use score_* tags — it's already high quality, score tags push it too far into slop