Image To Image
Apply image transformations to a provided image.
The default Gateway used in this guide is the public
Livepeer.cloud Gateway. It is free to use but
not intended for production-ready applications. For production-ready
applications, consider using the Livepeer Studio
Gateway, which requires an API token. Alternatively, you can set up your own
Gateway node or partner with one via the ai-video channel on
Discord.
Please note that the exact parameters, default values, and responses may vary between models. For more information on model-specific parameters, please refer to the respective model documentation available in the image-to-image pipeline. Not all parameters might be available for a given model.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
Uploaded image to modify with the pipeline.
Hugging Face model ID used for image generation.
Text prompt(s) to guide image generation.
Encourages model to generate images closely linked to the text prompt (higher values may reduce image quality).
Degree to which the generated image is pushed towards the initial image.
A LoRA (Low-Rank Adaptation) model and its corresponding weight for image generation. Example: { "latent-consistency/lcm-lora-sdxl": 1.0, "nerijs/pixel-art-xl": 1.2}.
Text prompt(s) to guide what to exclude from image generation. Ignored if guidance_scale < 1.
Number of images to generate per prompt.
Number of denoising steps. More steps usually lead to higher quality images but slower inference. Modulated by strength.
Perform a safety check to estimate if generated images could be offensive or harmful.
Seed for random number generation.
Degree of transformation applied to the reference image (0 to 1).
Response
Response model for image generation.
The generated images.
Was this page helpful?