Image to video API

How image-to-video differs from text-to-video

You supply the first frame, so composition, subject and style are already decided — the model only has to produce motion. That makes output far more controllable than text-to-video, and it composes naturally with the image models here: generate a still, approve it, then animate it.

The clip preserves the aspect ratio of your start frame. The prompt describes motion, not content.

• Describe camera and subject movement: "slow push in, hair moving in the wind"
• Static or near-static prompts produce subtle, ambient motion — often what you want for backgrounds
• The start frame carries the quality: a sharp, well-composed still animates far better than a soft one

Generate a clip

curl https://api.fastgencloud.com/v1/videos/generations \
  -H "Authorization: Bearer $FASTGEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
      "model": "wan-2.2",
      "image": "https://example.com/still.jpg",
      "prompt": "slow push in, gentle wind moving the leaves, drifting clouds",
      "duration": 5
    }'

Latency and cost

Video is the slowest and most expensive operation on the platform, and worth designing around. A 5 second clip typically takes on the order of three minutes on a warm 48 GB worker; a cold start adds more. Use a webhook rather than polling in a request handler, and tell your users it is a background job.

Billing is per second of output, so a 5 second clip costs five times the per-second rate and an 8 second clip eight times.

Parameters

model

wan-2.2

image

start frame — https URL or data URI; aspect ratio preserved

prompt

optional motion description, up to 2000 characters

negative_prompt

optional, verbatim

duration

5 or 8 seconds

loras

up to 3 WAN 2.2 LoRAs by URL ({ url, low_url?, strength })

seed

optional integer for reproducible output

webhook_url

strongly recommended for video

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.