/generate/prompt-editing

post deprecated

https://api.cloud.scenario.com/v1/generate/prompt-editing

[DEPRECATED] This API is deprecated.

Edit an image with a prompt.

Note: Please use POST /generate/custom/{modelId} endpoint instead. You can retrieve the model inputs from the GET /models/{modelId} endpoint. Use one of the following models:

model_bytedance-seedream-4-editing
model_flux-kontext-editing
model_google-gemini-2-5-flash-image-editing
model_openai-gpt-image-1-editing
model_qwen-image-editing
model_runway-gen4-image-editing

or one of your Kontext LoRA.

See https://docs.scenario.com/docs/edit-images-with-prompts for more details.

Query Params

originalAssets

string

If set to true, returns the original asset without transformation

dryRun

string

Body Params

image

string

required

The image to edit. Must reference an existing AssetId or be a data URL.

referenceImages

array of strings

List of additional reference images as a data URLs (example: "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVQYV2NgYAAAAAMAAWgmWQ0AAAAASUVORK5CYII=") or the asset IDs (example: "asset_GTrL3mq4SXWyMxkOHRxlpw").

5 additional reference images are allowed for the gemini-2.0-flash, gemini-2.5-flash and gpt-image-1 models. 3 additional reference images are allowed for the flux-kontext model. No additional reference images are allowed for the flux-kontext model if using concepts. 2 additional reference images are allowed for the runway-gen4-image model.

referenceImages

seed

number

The seed to use for the image generation.

Only available for the flux-kontext model.

strength

number

The strength

Only available for the flux-kontext LoRA model.

guidanceScale

number

The guidance scale to use for the image generation.

Only available for the flux-kontext model.

modelId

string

enum

Defaults to gemini-2.5-flash

The model to use. Can be "gemini-2.0-flash", "gemini-2.5-flash", "gpt-image-1", "flux-kontext", "runway-gen4-image" or "seedream-4".

Allowed:

format

string

enum

Defaults to png

The format of the generated image(s)

This parameter is only supported for the gpt-image-1 model.

Allowed:

aspectRatio

string

enum

Defaults to auto

The aspect ratio of the generated image(s). Supported for: gemini-2.5-flash, gpt-image-1, flux-kontext, runway-gen4-image, seedream-4. Will default to auto for other models and unknown ratios.

Notes:

gemini-2.5-flash supports Landscape: 21:9, 16:9, 4:3, 3:2 • Square: 1:1 • Portrait: 9:16, 3:4, 2:3 • Flexible: 5:4, 4:5 • auto.
gpt-image-1 supports 1:1, 3:2, 2:3, auto (unknown ratios fall back to auto).
runway-gen4-image supports 1:1, 4:3, 3:4, 16:9, 9:16, auto (unknown ratios fall back to auto).
seedream-4 supports 1:1, 4:3, 3:4, 16:9, 9:16, 2:3, 3:2, 21:9, auto.

inputFidelity

string

enum

Defaults to low

When set to high, allows to better preserve details from the input images in the output. This is especially useful when using images that contain elements like faces or logos that require accurate preservation in the generated image.

You can provide multiple input images that will all be preserved with high fidelity, but keep in mind that the first image will be preserved with richer textures and finer details, so if you include elements such as faces, consider placing them in the first image.

Only available for the gpt-image-1 model.

Allowed:

quality

string

enum

Defaults to high

The quality of the generated image(s).

Only available for the gpt-image-1, flux-kontext, runway-gen4-image and seedream-4 models.

Allowed:

concepts

array of objects

Flux Kontext LoRA to style the image. For Flux Kontext Prompt Editing.

concepts

numSamples

number

The number of samples to generate

Maximum depends on the subscription tier.

compression

number

The compression level (0-100%) for the generated images. This parameter is only supported for the gpt-image-1 model with the webp or jpeg output formats, and defaults to 100.

prompt

string

required

The prompt to edit the given image.

mask

string

You can provide a mask to indicate where the image should be edited. The black area of the mask will be replaced, while the filled areas will be kept as is.

Must reference an existing AssetId or be a data URL.

Only available for the gpt-image-1 model. Will be ignored for other models.

Responses

200200 response

269269 response