Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.comfy.org/llms.txt

Use this file to discover all available pages before exploring further.

Make sure your ComfyUI is updated.Workflows in this guide can be found in the Workflow Templates. If you can’t find them in the template, your ComfyUI may be outdated. (Desktop version’s update will delay sometime)If nodes are missing when loading a workflow, possible reasons:
  1. You are not using the latest ComfyUI version (Nightly version)
  2. Some nodes failed to import at startup
Anima is an open text-to-image model by CircleStone Labs in partnership with Comfy Org. With 2 billion parameters, it is designed to generate high-quality anime and non-photorealistic images — ideal for characters, scenes, and concept art. Model highlights:
  • Anime and artistic illustration focus — tuned for non-photorealistic art styles
  • ComfyUI native support — loaded with standard UNETLoader, CLIPLoader, and VAELoader nodes
  • Qwen-3 0.6B text encoder — provides strong language understanding and prompt adherence
  • No input image needed — pure text-to-image generation
  • Compact footprint — 2B diffusion model, runs comfortably on consumer GPUs
Related links:

​
Available workflows

Anima provides two workflows — the base version for standard use and a preview version for early access. Both workflows use a Subgraph node to manage the text-to-image generation pipeline. You can open the subgraph to inspect or customize the internal nodes.

Learn about Subgraph

This workflow uses Subgraph nodes for modular processing. Check out the Subgraph documentation to learn how to customize and extend the workflow.

​
Anima Base v1: Text to Image

Download Workflow

Download JSON or search “Aima Base v1” in Template Library

Run on Comfy Cloud

Open in Comfy Cloud

​
Get started

  1. Update ComfyUI to the latest version or use Comfy Cloud
  2. Go to Template and search for Aima Base v1
  3. Select the Aima Base v1: Text to Image workflow
  4. Download any missing models (see model downloads), enter your prompt, and click Queue

​
Example output

Anima Base v1 example output

​
Anima Preview: Anime Text-to-Image Generation

Download Workflow

Download JSON or search “Anima Preview” in Template Library

Run on Comfy Cloud

Open in Comfy Cloud

​
Get started

  1. Update ComfyUI to the latest version or use Comfy Cloud
  2. Go to Template and search for Anima Preview
  3. Select the Anima Anime Text-to-Image Generation workflow
  4. Download any missing models (see model downloads), enter your prompt, and click Queue

​
Example output

Anima Preview example output

​
Anima model downloads

You can find all model files at circlestone-labs/Anima on Hugging Face.

anima-base-v1.0.safetensors

Diffusion model (2B) for Anima Base v1.

qwen_3_06b_base.safetensors

Text encoder (Qwen-3 0.6B) shared by both workflows.

qwen_image_vae.safetensors

VAE shared by both workflows.
Model storage location 
📂 ComfyUI/
├── 📂 models/
│   ├── 📂 diffusion_models/
│   │   └── anima-base-v1.0.safetensors
│   ├── 📂 text_encoders/
│   │   └── qwen_3_06b_base.safetensors
│   └── 📂 vae/
│       └── qwen_image_vae.safetensors

​
Preview model

If you are using the Preview workflow, download the preview diffusion model instead:

anima-preview3-base.safetensors

Diffusion model (2B) for Anima Preview.
Preview model storage location 
📂 ComfyUI/
├── 📂 models/
│   └── 📂 diffusion_models/
│       └── anima-preview3-base.safetensors

​
Limitations

  • No realism — the model is intentionally designed for anime and illustration styles; realistic renderings are out of scope
  • Weak text rendering — high-resolution text and complex typography may not render clearly
  • Plain styling — the base model produces simpler compositions; advanced artistic styles may require refinement or fine-tuning