ExBifrost.Api.Images (ex_bifrost v0.1.0)

API calls for all endpoints tagged Images.

Summary

Functions

image_edit(connection, model, image, opts \\ [])

Edit an image Edits an image using a text prompt and optional mask. Request must be sent as multipart/form-data with at least model, prompt (unless type is background_removal), and image (or image[]).

image_generation(connection, image_generation_request, opts \\ [])

Generate an image Generates images from text prompts using the specified model.

image_variation(connection, model, image, opts \\ [])

Create Variation Creates variations of an image. Request must be sent as multipart/form-data with model and image (or image[]). Does not support streaming.

Functions

image_edit(connection, model, image, opts \\ [])

@spec image_edit(Tesla.Env.client(), String.t(), String.t(), keyword()) ::
  {:ok, ExBifrost.Model.ImageGeneration200Response.t()}
  | {:ok, ExBifrost.Model.BifrostError.t()}
  | {:error, Tesla.Env.t()}

Parameters

connection (ExBifrost.Connection): Connection to server
model (String.t): Model identifier in format provider/model
image (String.t): Image file to edit. Use field name image for a single file or image[] for multiple files.
opts (keyword): Optional parameters
- :prompt (String.t): Text prompt describing the edit. Required unless type is background_removal.
- :mask (String.t): Optional mask image for inpainting (transparent areas indicate regions to edit)
- :type (String.t): Type of edit operation
- :n (integer()): Number of images to generate
- :size (String.t): Size of the output image
- :response_format (String.t): Format of the response
- :stream (boolean()): When true, stream the response via Server-Sent Events
- :background (String.t): Background type for the image
- :input_fidelity (String.t): How closely to follow the original image
- :partial_images (integer()): Number of partial images to generate when streaming
- :quality (String.t): Quality of the output image
- :output_format (String.t): Output image format
- :num_inference_steps (integer()): Number of inference steps
- :seed (integer()): Seed for reproducible editing
- :output_compression (integer()): Compression level (0-100%)
- :negative_prompt (String.t): What to avoid in the edit
- :user (String.t): User identifier for tracking
- :fallbacks ([ExBifrost.Model.Fallback.t]): Fallback models to try if primary model fails

Returns

{:ok, ExBifrost.Model.ImageGeneration200Response.t} on success
{:error, Tesla.Env.t} on failure

image_generation(connection, image_generation_request, opts \\ [])

@spec image_generation(
  Tesla.Env.client(),
  ExBifrost.Model.ImageGenerationRequest.t(),
  keyword()
) ::
  {:ok, ExBifrost.Model.ImageGeneration200Response.t()}
  | {:ok, ExBifrost.Model.BifrostError.t()}
  | {:error, Tesla.Env.t()}

Generate an image Generates images from text prompts using the specified model.

Parameters

connection (ExBifrost.Connection): Connection to server
image_generation_request (ImageGenerationRequest):
opts (keyword): Optional parameters

Returns

{:ok, ExBifrost.Model.ImageGeneration200Response.t} on success
{:error, Tesla.Env.t} on failure

image_variation(connection, model, image, opts \\ [])

@spec image_variation(Tesla.Env.client(), String.t(), String.t(), keyword()) ::
  {:ok, ExBifrost.Model.ImageGeneration200Response.t()}
  | {:ok, ExBifrost.Model.BifrostError.t()}
  | {:error, Tesla.Env.t()}

Create Variation Creates variations of an image. Request must be sent as multipart/form-data with model and image (or image[]). Does not support streaming.

Parameters

connection (ExBifrost.Connection): Connection to server
model (String.t): Model identifier in format provider/model
image (String.t): Image file to create variations of. Use field name image for a single file or image[] for multiple (first image is used).
opts (keyword): Optional parameters
- :n (integer()): Number of variations to generate
- :size (String.t): Size of the output images
- :response_format (String.t): Format of the response
- :user (String.t): User identifier for tracking
- :fallbacks ([ExBifrost.Model.Fallback.t]): Fallback models to try if primary model fails

Returns

{:ok, ExBifrost.Model.ImageGeneration200Response.t} on success
{:error, Tesla.Env.t} on failure