Skip to main content
POST
Generate creative variations of an image
Generate creative variations of one source image. The call returns 202 Accepted with a job id; poll GET /images/variations/{id} for the result. The image takes exactly one of image_id, url, or base64 + mime_type. Requires the images.transform scope.

Example: one source per mode

The 202 response is the async job handle:
202 Accepted
Send exactly one source mode in image. target — what the variations may change — is everything (default), person, object, or scene. creativity is subtle or creative (default). variation_instructions (what to change) and preservation_instructions (what to keep) are optional free text, ≤ 2000 characters each. num_outputs (1–4) defaults to 1 and each output is billed. There is no resolution parameter — the output resolution is inherited from the source.

Credits

Each output costs 5 credits at 1K, scaling with the source image’s resolution tier (1K ×1, 2K ×2, 4K ×4) and multiplied by num_outputs. See Pricing.

Errors

Authorizations

Authorization
string
header
required

Organization API key as a bearer token: Authorization: Bearer samsa_sk_....

Body

application/json

POST /images/variations body (SAM-816 / S8.4 — ADR §8, §10).

Generate creative variations of ONE source image (the app's Gemini 3 Pro variations flow). The source is exactly one of image_id (an image in your organization's context), an https url, or base64+mime_type. The output resolution is inherited from the source (there is no resolution param); each output is billed at 5 x resolution_multiplier credits (1K:1x, 2K:2x, 4K:4x) where the multiplier is the source image's resolution tier. target and creativity are lowercase public aliases of the internal Gemini variation controls; num_outputs defaults to 1 (the app default is 4).

image
PublicImageEditSource · object
required

The source image: exactly one of image_id, url, or base64+mime_type.

target
enum<string>
default:everything

What the variations may change: everything (default), person, object, or scene.

Available options:
everything,
person,
object,
scene
Example:

"everything"

creativity
enum<string>
default:creative

How far the variations may deviate from the source: subtle or creative (default).

Available options:
subtle,
creative
Example:

"creative"

variation_instructions
string | null

Optional free-text guidance for WHAT to change (<= 2000 chars).

Maximum string length: 2000
Example:

"Try different background colors and lighting"

preservation_instructions
string | null

Optional free-text guidance for WHAT to keep (<= 2000 chars).

Maximum string length: 2000
Example:

"Keep the product label and shape unchanged"

num_outputs
integer
default:1

Number of variations to generate (1-4). Defaults to 1 (the app default is 4); each output is billed.

Required range: 1 <= x <= 4
Example:

1

webhook_url
string | null

Optional https webhook notified once on terminal status (signed per the webhook signature scheme; see the webhooks docs).

Example:

"https://example.com/webhooks/samsa"

Response

Successful Response

Shared 202 body for the transform-op submits (SAM-813 / S8 wave).

Every POST /images/<op> returns the async job handle {id, status, estimated_credits}. The initial status is pending (the job is queued), with ONE exception: background-removals and vectorizations answer an owned-image_id cache hit (a ready result already exists for that image) with status: "completed" and estimated_credits: 0 — no new job is queued, the completed webhook event is emitted immediately for a supplied webhook_url, and the result is already available from the op's GET .../{id} endpoint. The other transform ops (img2img, variations, resizes, upscales) always start pending.

id
string<uuid>
required

The job id — poll the op's GET .../{id} endpoint.

status
enum<string>
required

Initial status: pending (job queued — enter the polling flow), or completed with estimated_credits: 0 when background-removals / vectorizations serve an owned-image cache hit (the result is immediately available).

Available options:
pending,
processing,
completed,
failed,
cancelled
Example:

"pending"

estimated_credits
integer
required

Credits this job is expected to cost — 0 on a cache-hit completed response.

Example:

5