v6

latestOpenAPI 3.0.3raw.githubusercontent.com2025-03-0663270.5 KB
Version1.Image

Image-to-image with prompt

Produce an image from an existing image using a text prompt.

How to control strength of generation

To preserve only roughly 35% of the initial image, pass in either init_image_mode=IMAGE_STRENGTH and image_strength=0.35 or init_image_mode=STEP_SCHEDULE and step_schedule_start=0.65. Both of these are equivalent, however init_image_mode=STEP_SCHEDULE also lets you pass in step_schedule_end, which can provide an extra level of control for those who need it. For more details, see the specific fields below.

NOTE: Only Version 1 engines will work with this endpoint.

post/v1/generation/{engine_id}/image-to-image

Path parameters

engine_idstring required

Headers

Organizationstring

Allows for requests to be scoped to an organization other than the user's default. If not provided, the user's default organization will be used.

Stability-Client-IDstring

Used to identify the source of requests, such as the client application or sub-organization. Optional, but recommended for organizational clarity.

Stability-Client-Versionstring

Used to identify the version of the application or service making the requests. Optional, but recommended for organizational clarity.

Response

Generation successful.

Example response

{
  "artifacts": [
    {
      "finishReason": "CONTENT_FILTERED",
      "seed": 1229191277
    }
  ]
}