Switchx Image To Image

This documentation is valid for the following list of our models:

• beeble/switchx-image-to-image

Try in Playground

Model Overview

SwitchX is an image-to-image compositing model by Beeble that replaces a scene element while preserving the original subject, with automatic subject detection and seamless relighting to match a reference image. Does not support tools/function calling.

Setup your API Key

If you don’t have an API key for the AI/ML API yet, feel free to use our Quickstart guide.

API Schema

post

Body

application/json

modelstring · enumRequiredPossible values:

image_urlstring · uriRequired

URL of the source image to recomposite. Allowed formats: JPEG, PNG, WEBP. Source must not exceed 2,770,000 total pixels.

alpha_urlstring · uriOptional

URL of the alpha mask. Required when alpha_mode is "custom" or "select"; ignored for "auto" and "fill". A mask video for video-to-video, a mask image for image-to-image.

reference_image_urlstring · uriOptional

URL of the reference image defining the target look and lighting for the replaced region. Allowed formats: JPEG, PNG, WEBP. At least one of reference_image_url or prompt must be provided.

alpha_modestring · enumOptional

Subject masking strategy: "auto" (AI auto-detects the subject), "fill" (no masking), "select" (propagate a mask from one keyframe), or "custom" (frame-by-frame mask supplied via alpha_url). Defaults to "auto".

Default: autoPossible values:

max_resolutioninteger · enumOptional

Maximum output resolution (longer side) in pixels: 720 or 1080. Defaults to 1080. 1080 costs more than 720.

Default: 1080Possible values:

alpha_keyframe_indexintegerOptional

Frame index (0-based) whose mask is propagated when alpha_mode is "select" on a video. Defaults to the first frame. Ignored for image generation and for the auto, fill, and custom modes.

seedinteger · max: 4294967295Optional

Random seed (0–4294967295) for reproducibility. Omit for a random seed. The seed used is always returned in the response.

promptstring · max: 2000Optional

Text description of the desired output to guide the generation (max 2000 characters). At least one of prompt or reference_image_url must be provided.

Responses

200

Successful response.

application/json

post/v1/images/generations

cURLJavaScriptPython

curl --request POST \
  --url 'https://api.aimlapi.com/v1/images/generations' \
  --header 'Authorization: Bearer <YOUR_AIMLAPI_KEY>' \
  --header 'Content-Type: application/json' \
  --data '{"model": "beeble/switchx-image-to-image", "image_url": "https://example.com/input.jpg", "prompt": "Describe what you want the model to generate."}'

200

Successful response.

{
  "data": [
    {
      "url": "https://cdn.aimlapi.com/generations/hedgehog/1749730923700-29fe35d2-4aef-4bc5-a911-6c39884d16a8.png",
      "b64_json": null
    }
  ],
  "meta": {
    "usage": {
      "credits_used": 120000,
      "usd_spent": 0.06
    }
  }
}

Quick Example

Let's generate a new image using the one from the flux/dev Quick Example as a reference — and make a simple change to it with a prompt.

Python

import requests
import json  # for getting a structured output with indentation 

def main():
    response = requests.post(
        "https://api.aimlapi.com/v1/images/generations",
        headers={
            # Insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>:
            "Authorization": "Bearer <YOUR_AIMLAPI_KEY>",
            "Content-Type": "application/json",
        },
        json={
            "model": "beeble/switchx-image-to-image",
            "image_url": "https://raw.githubusercontent.com/aimlapi/api-docs/main/reference-files/t-rex.png",  # URL of the reference picture
            "prompt": "Add a bird to the foreground of the photo.",
        }
    )

    data = response.json()
    print(json.dumps(data, indent=2, ensure_ascii=False))

if __name__ == "__main__":
    main()

JS

Response

{
  "images": [
    {
      "url": "https://cdn.aimlapi.com/squirrel/files/panda/qMuknweKekEYlj9-RdUNt_f0706e451d674554a4c03f2489cf7d5a.jpg",
      "content_type": "image/jpeg",
      "file_name": null,
      "file_size": null,
      "width": 1184,
      "height": 880
    }
  ],
  "timings": {},
  "seed": 3959063143,
  "has_nsfw_concepts": [
    false
  ],
  "prompt": "Add a bird to the foreground of the photo."
}

Reference Image	Generated Image

More generated images

Example #2: Combine two images

This time, we’ll pass two images to the model: our dinosaur and a solid blue mug. We'll ask the model to place the dinosaur onto the mug as a print.

Our input images

Python

import requests
import json  # for getting a structured output with indentation

def main():
    response = requests.post(
        "https://api.aimlapi.com/v1/images/generations",
        headers={
            # Insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>:
            "Authorization": "Bearer <YOUR_AIMLAPI_KEY>",
            "Content-Type": "application/json",
        },
        json={
            "prompt": "Place this image with the t-rex on this mug from the second image as a print. Make it look fit and natural.",
            "model": "beeble/switchx-image-to-image",
            "image_url": [     # URLs of two reference pictures
                "https://zovi0.github.io/public_misc/flux-dev-t-rex.png", 
                "https://zovi0.github.io/public_misc/blue-mug.jpg"
            ]
        }
    )

    data = response.json()
    print(json.dumps(data, indent=2, ensure_ascii=False))


if __name__ == "__main__":
    main()

JS

Response

{
  "images": [
    {
      "url": "https://cdn.aimlapi.com/squirrel/files/lion/rXRknU80d-8ywPnLBq4G8_59b65fe44d8046a38ab9e524a5a8b61c.jpg",
      "width": 1184,
      "height": 880,
      "content_type": "image/jpeg"
    }
  ],
  "timings": {},
  "seed": 1068148133,
  "has_nsfw_concepts": [
    false
  ],
  "prompt": "Place this image with the t-rex on this mug from the second image as a print. Make it look fit and natural."
}

"Place this image with the t-rex on this mug from the second image as a print. Make it look fit and natural."