Extensions/AnimeAPI
ComfyUI Extension

AnimeAPI

AnimeAPI nodes for ComfyUI: anime image generation at $0.003 per image, no local model or GPU needed.

By animeapi-ai·Created 3 days ago·Updated 3 days ago· 0
animeapi-ai/ComfyUI-AnimeAPI
Nodes—
On cloudLocal install
Stars0
Updated3 days ago
Readme

ComfyUI-AnimeAPI

Anime image generation inside ComfyUI with AnimeAPI at $0.003 per image, one of the cheapest anime image APIs. No checkpoint to download and no GPU needed: the node sends your prompt to AnimeAPI and returns a normal IMAGE in about 4 seconds, ready for upscalers, detailers, img2img or anything else in your graph.

Prepaid balance from $5 that never expires, no subscription; new accounts get 3 free images without a card.

Install

In ComfyUI/custom_nodes:

git clone https://github.com/animeapi-ai/ComfyUI-AnimeAPI

Restart ComfyUI. There are no extra Python packages to install.

Key

Create a key at https://animeapi.ai/dashboard/api-keys (it starts with ank_) and set it before starting ComfyUI:

export ANIMEAPI_KEY=ank_your_key

You can paste the key into the node's api_key input instead, but ComfyUI then saves it inside the workflow file and in generated images' metadata, so prefer the environment variable for anything you share.

The node

AnimeAPI → AnimeAPI Generate Image

| Input | Values | Notes | | --- | --- | --- | | prompt | text | Plain English, up to 1,000 characters. | | model | anime, ultra, ultra-max | See prices below. | | orientation | portrait, square, landscape | Same price for every shape. | | seed | number | Not sent to the API. ComfyUI only re-runs a node when an input changes, so change the seed (or leave it on randomize) to get a new image for the same prompt. Each run costs one image. | | enhance | on / off | On: plain English is rewritten into tags for the anime model. Off: your own tags are sent as written. | | api_key | text | Optional; see above. |

AnimeAPI does not generate adult content. Explicit prompts are refused and not charged.

Outputs: image (IMAGE), image_url (STRING) and enhanced_prompt (STRING, what the model read).

An example in API format is in examples/animeapi_basic.json: AnimeAPI Generate Image → Save Image.

Prices

| Model | Price per image | Use it for | | --- | --- | --- | | anime | $0.003 | Characters, portraits, avatars, scenes. About 4 seconds. | | ultra | $0.01 | Long, detailed prompts; legible text in the image. | | ultra-max | $0.02 | Highest detail. |

Failed generations are refunded. Errors (wrong key, empty balance, refused prompt) show as the node's error message.

Tested

Run on ComfyUI 0.33.1 (CPU only): the example workflow produced and saved a 1280x832 image through the live API.

Licence

MIT