Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →artokun/anima-base
Anime/illustration text-to-image (ANIMA 1.0, ~2B Cosmos DiT) — use for anime, manga, illustrated characters; accepts Danbooru tags + natural language; runs/trains on <6GB VRAM; includes anime inpainting via Anima-LLLite ControlNet
Passed 24 of 24 test cases with the skill, and 11 of 24 without it.
and 23 more in the full report
14 fixed11 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am configuring the AnimaLLLiteApply_sdscripts node to use a lineart control model. By default, I might leave the boolean toggles alone. Which specific boolean widget on this node must be set to true, and what type of data does the node output to the next step?
| Checked | Without skill | With skill |
|---|---|---|
| mentions setting the preserve_wrapper boolean to true | Missed | Passed |
| mentions that the node outputs a patched MODEL | Passed | Passed |
The instructions your model reads when the skill loads.
Anima is a ~2B-parameter anime / illustration text-to-image base model from CircleStone Labs, made in collaboration with Comfy Org. It is not SDXL-lineage. The architecture is NVIDIA Cosmos-Predict2-2B-Text2Image (a DiT / flow model), trained on several million anime images plus ~800k non-anime artistic images. It suits anime, manga, and illustrated characters and styles, not realism.
Key traits:
ComfyUI loads it with standard split-file loaders, not a single checkpoint:
| Component | Node | Model file | Folder | Notes |
|---|---|---|---|---|
| Diffusion model | UNETLoader | anima-base-v1.0.safetensors | models/diffusion_models/ | weight_dtype default; ~4GB fp |
| Text encoder | CLIPLoader | qwen_3_06b_base.safetensors | models/text_encoders/ | Qwen3-0.6B base; type": "stable_diffusion" in this pack |
| VAE | VAELoader | qwen_image_vae.safetensors | models/vae/ | Qwen-Image VAE (~254MB) |
Verified from the pack's workflow JSON:
CLIPLoaderwidget values are["qwen_3_06b_base.safetensors", "stable_diffusion", "default"]. The HF model card describes standard loaders; the exact CLIPtypestringstable_diffusionis what the Aitrepreneur "Anima Base Ultra" workflow ships. Use it as-is.
The "Anima Base Ultra" pack (by Aitrepreneur) installs custom nodes and downloads all models. Models are mirrored on https://huggingface.co/Aitrepreneur/FLX/resolve/main; the official source is https://huggingface.co/circlestone-labs/Anima.
ComfyUI/custom_nodes/)| Node pack | Repo | Used for |
|---|---|---|
| ComfyUI-Manager | https://github.com/ltdrdata/ComfyUI-Manager.git | management |
| ComfyUI-Impact-Pack | https://github.com/ltdrdata/ComfyUI-Impact-Pack | FaceDetailer / EditDetailerPipe |
| ComfyUI-Impact-Subpack | https://github.com/ltdrdata/ComfyUI-Impact-Subpack | UltralyticsDetectorProvider |
| rgthree-comfy | https://github.com/rgthree/rgthree-comfy | Power Lora Loader, Fast Groups, Any Switch |
| ComfyUI-KJNodes | https://github.com/kijai/ComfyUI-KJNodes | helpers |
| ComfyUI_UltimateSDUpscale | https://github.com/ssitu/ComfyUI_UltimateSDUpscale | tiled upscaling |
| ComfyUI_tinyterraNodes | https://github.com/TinyTerra/ComfyUI_tinyterraNodes | ttN seed |
| comfyui_controlnet_aux | https://github.com/Fannovel16/comfyui_controlnet_aux | DWPreprocessor, DepthAnythingV2 |
| ComfyUI-Anima-LLLite | https://github.com/kohya-ss/ComfyUI-Anima-LLLite | AnimaLLLiteApply_sdscripts (ControlNet + inpainting) |
test cases passed, vs 11 / 24 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.