Krea 2 API

What it is good at

general-image runs a photorealism-tuned Krea 2 finetune on the 8-step turbo sampler: a 12B diffusion transformer with a Qwen3-VL text encoder, which is why it follows long, specific, plain-language prompts far better than SDXL-era models while staying cheap per image.

It is the right default when you want a believable photograph: people, product shots on a surface, interiors, landscapes and concept art. Write prompts as sentences — subject, action, clothing, setting, light, camera — rather than tag lists. For flat illustration or line art, the anime and cartoon models are tuned for that instead.

• Text to image at any of five supported aspect ratios
• Image to image — pass a source image and a prompt to restyle it (runs on the model’s SDXL companion checkpoint)
• Inpainting — regenerate a masked region and leave the rest untouched (SDXL companion)
• Trained characters: generate a person you trained with the characters API (SDXL companion, where the character LoRA lives)

Generate an image

A minimal request needs a model and a prompt. Everything else has a default.

curl https://api.fastgencloud.com/v1/images/generations \
  -H "Authorization: Bearer $FASTGEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
      "model": "general-image",
      "prompt": "photo of a ceramic pour-over coffee dripper on a walnut counter, morning window light, shallow depth of field",
      "size": "1024x1024",
      "n": 1
    }'

Parameters

model

general-image

prompt

1–2000 characters, passed to the model verbatim

negative_prompt

optional, passed verbatim — only has an effect when guidance is above 1

size

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

aspect_ratio

alternative to size — picks the closest supported size

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 } from the characters API

webhook_url

optional signed callback on completion

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.