[Enhancement]: Support for grok-2-image

[distardao]

What features would you like to see added?

Hi, grok has grok-2-image model for image generation, how can I use it in librechat?
https://docs.x.ai/docs/guides/image-generations#image-generations

More details

Nothing more

Which components are impacted by your request?

No response

Pictures

No response

Code of Conduct

• I agree to follow this project's Code of Conduct

[danny-avila]

Just added some documentation on image generations.

https://www.librechat.ai/docs/features/image_gen

if xAI is openai-compatible, you could probably just use replacement config variables via DALLE or upcoming "OpenAI Image Tools" (though I'm not sure they provide the editing).

A dedicated MCP server for xAI image generations is also recommended

[distardao]

Thanks for your response. If I use a dedicated MCP server, how can I control the consumed balance? From my understanding, I need to declare the input and output prompt pricing in this file:

LibreChat/api/models/tx.js

Line 4 in c0ebb43

/**

[pilgrim1385]

Use OpenAI Schema In Agents

openapi: 3.1.0
info:
  title: xAI Image Generation API
  description: API for generating images based on text prompts, allowing responses in either URL or Base64 encoded formats.
  version: 1.0.0
servers:
  - url: https://api.x.ai/v1/images
    description: Main xAI API server
paths:
  /generations:
    post:
      operationId: generateImage
      summary: Generates images based on a given text prompt.
      description: Sends a prompt to the image generation model and receives the generated image(s) in either URL or Base64 format.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              properties:
                model:
                  type: string
                  description: The model used for image generation, Always "grok-2-image".
                  example: "grok-2-image"
                prompt:
                  type: string
                  description: The description of the image you want to generate.
                  example: "A cat in a tree"
                n:
                  type: integer
                  description: The number of images to generate (1-10). Always 2.
                  example: 1
                response_format:
                  type: string
                  enum: [url, b64_json]
                  description: The format in which the image(s) should be returned. "url" returns an image URL, "b64_json" returns the image in base64 encoded format. Always "url".
                  example: "url"
      responses:
        '200':
          description: A successful response containing the generated image(s).
          content:
            application/json:
              schema:
                type: object
                properties:
                  data:
                    type: array
                    items:
                      type: object
                      properties:
                        url:
                          type: string
                          description: The URL of the generated image.
                          example: "https://xai.com/generated_image.jpg"
                        b64_json:
                          type: string
                          description: The base64 encoded image data (if `response_format` is `b64_json`).
                          example: "data:image/png;base64,..."
                        revised_prompt:
                          type: string
                          description: The revised prompt generated by the model before image creation.
                          example: "3D render of a gray cat with green eyes perched on a thick branch of a leafy tree, set in a suburban backyard during the day..."
        '400':
          description: Bad request, likely due to invalid input or moderation rejection
          content:
            application/json:
              schema:
                type: object
                properties:
                  code:
                    type: string
                    example: "Client specified an invalid argument"
                  error:
                    type: string
                    example: "Generated image rejected by content moderation."
        '500':
          description: Internal server error, something went wrong on the server side.