Image editing API

What instruction editing replaces

Traditional editing endpoints need a mask: you segment the region, send it alongside the image, and the model repaints inside it. Qwen-Image-Edit takes an instruction instead — "replace the background with a marble surface", "make the jacket red", "put the subject from image 2 into image 1".

That removes the entire masking step from your product, which is usually the hardest part of the UI to build well.

• Object edits — add, remove, replace or recolour something in the frame
• Background replacement without segmenting the subject
• Style transfer across the whole image
• Composition — combine subjects or elements from up to three references

Edit an image

Reference images can be public https URLs or inline data URIs. URLs are strongly preferred: the whole request body has to stay under about 4 MB.

curl https://api.fastgencloud.com/v1/images/edits \
  -H "Authorization: Bearer $FASTGEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
      "model": "image-edit",
      "image": "https://example.com/product.jpg",
      "prompt": "place the product on a polished marble surface with soft studio lighting"
    }'

Writing instructions that work

Edit models follow imperative, concrete instructions best. Name the thing you want changed and state the target state.

• Prefer "replace the background with a sunlit kitchen" over "make it nicer"
• One change per request beats three changes stacked into one sentence
• If an edit is too subtle, raise steps to 20–30 and guidance to about 4 — the default is the fast distilled setting
• Reference images by position when you pass several: "the person from the first image, wearing the jacket from the second"

Parameters

model

image-edit

image / images

one reference, or an array of 1–3

prompt

the edit instruction, 1–2000 characters, verbatim

size

optional; defaults to the supported size closest to the first reference

steps

optional, 1–50; default is the fast distilled setting

guidance

optional; default 1.0 distilled, ~4 at higher step counts

seed

optional integer for reproducible output

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.