Anime image generation API

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 https://api.fastgencloud.com/v1/images/generations \
  -H "Authorization: Bearer $FASTGEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
      "model": "krea-2-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

krea-2-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)

Unfiltered and uncensored

This endpoint applies no content filter. Your prompt, negative prompt, reference images and LoRAs reach the model verbatim, nothing is rewritten or injected, and outputs are not scanned or blocked. What your product allows is your call.

The one automatic rule is the minor-safety floor: a prompt that pairs a minor or age reference with sexual content is refused for that request only. Nothing else is filtered and the account is never touched by moderation.

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.

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.