Skip to content

Anime image generation API

Anime and illustration generation on Krea 2 — a 12B diffusion transformer with a Qwen3-VL text encoder, wearing a dedicated anime style. Strong character rendering, clean line art, and prompts you write as sentences rather than tag soup.

Price
$0.006 / image
Model id
anime
Sizes
5 presets

1024x1024, 832x1216, 1216x832, 896x1152, 1152x896

Images per request
1–4

Prose prompting, not tags

Krea 2 reads prompts through a vision-language encoder, so it follows sentences: "A silver-haired girl in a red scarf walking down a snowy street at night, warm streetlights, soft snowfall, detailed background" beats a comma-separated tag list. Say the type of art, the character, the location, the clothing, the action and the style, in that order.

The only thing added to your prompt is the anime style’s own trigger phrase — that is how the style is invoked. No negatives are injected and nothing else is rewritten.

  • Full sentences, most important detail first
  • State the number of characters and their placement explicitly
  • Portrait ratios like 832x1216 suit single-character work
  • negative_prompt is accepted but only takes effect when guidance is above 1

Generate an image

curl
curl https://api.fastgencloud.com/v1/images/generations \
  -H "Authorization: Bearer $FASTGEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
      "model": "anime",
      "prompt": "A silver-haired girl in a red scarf walking down a snowy street at night, warm streetlights, soft snowfall, detailed background, cinematic lighting",
      "size": "832x1216",
      "n": 2
    }'

Parameters

model
anime
prompt
plain-language prompt, 1–2000 characters, verbatim
negative_prompt
optional, verbatim — only has an effect when guidance is above 1
size
1024x1024, 832x1216, 1216x832, 896x1152, 1152x896
n
1–4 images per request
seed
optional integer for reproducible output
steps / guidance
defaults 8 / 1 (turbo-distilled); steps 4–24, guidance 1–8
character
optional { id, strength } — characters trained on the anime family (rendered on the SDXL companion)

How the API works

Every generation is a job. The POST returns 202 with a job id immediately, so your request thread is never blocked on a GPU. You then either poll GET /v1/jobs/{id} or register a webhook_url and receive a signed callback when the job finishes.

Send an Idempotency-Key header and a retried request replays the original job instead of charging you twice. Your wallet is debited when the job is submitted and refunded automatically if it fails.

poll the job
curl https://api.fastgencloud.com/v1/jobs/$JOB_ID \
  -H "Authorization: Bearer $FASTGEN_API_KEY"

Pricing and billing

Pricing is prepaid and usage-based: you top the wallet up with a card and each job debits it. There is no subscription, no per-seat cost, and no monthly minimum.

Images above 1 megapixel are billed pro rata by pixel count — a 1.5 MP image costs 1.5x the listed rate. Failed jobs are refunded in full, automatically.

Frequently asked questions

Can I keep the same character across many images?
Yes. Train a character with the characters API against base_model "anime", then pass { "character": { "id": "chr_..." } } on generation. Character generations render on the model’s Illustrious SDXL companion, where the trained LoRA lives.
Is there a cartoon or western-comic option?
Yes — the cartoon model runs a western-comics Krea 2 finetune, which suits stylised and western-cartoon work. Both are billed at the same rate.
What is added to my prompt?
Only the anime style’s trigger phrase, which is what switches the style on. Nothing else is rewritten, and no negatives are injected.

Related

Start generating

Create an account, add a prepaid balance, and call the API with a key from the console. No subscription, no minimum, no per-seat pricing.

Get an API key