AI Image

Creative Mind

API Documentation

Creative Mind is a revolutionary tool that's bringing a new twist to the realm of digital artistry, empowering users to transform text-based prompts into striking visual art. This ingenious tool harnesses artificial intelligence and requires three user-defined parameters - the prompt, the number of images, and the size of the image. The prompt, a text description of up to 1000 characters, guides the AI to craft highly accurate visuals that mirror the user's imagination in astonishing detail. Whether it's a scene from a book, a moment in a movie, or a snapshot of a place, the more detailed the prompt, the more accurate the resulting image. The 'n' property determines how many images should be generated - either 1 or 4, offering users the flexibility of a single image or a variety of interpretations. The size property lets users select from '256x256', '512x512', or '1024x1024', ensuring the final artwork fits their specific requirements. Despite its advanced functionality, Creative Mind maintains a user-friendly operation, with the ability to seamlessly display the generated images directly in the chat interface. This unique feature of Creative Mind not only redefines the capabilities of AI but also opens up a world of possibilities for creative exploration.




Example Prompts


Generate an image of a futuristic cityscape at sunset.


Create a picture of a cute puppy playing with a ball.


Show me an image of a serene mountain landscape with a waterfall.


Produce an illustration of a robot cooking dinner in a modern kitchen.


Design an image of a magical forest with glowing mushrooms and fairies.


Generate a visual representation of a steampunk-inspired airship.


Create a picture of a tranquil beach scene with palm trees and a hammock.


Show me a photo of a medieval castle surrounded by a moat.


Produce an image of a space battle between alien spaceships.


Design an illustration of an underwater city with futuristic technology.

Description for AI

Help the user generate images based on text prompts. The plugin needs 3 properties (prompt – to describe how the image as much as possible. Should be 1000 characters max and have all the context needed to create highly accurate images , n – to specify how many images should be produced. Must be either 1 or 4, size – should be one of the following, ‘256x256’, ‘512x512’, or ‘1024x1024’, to specify the size of the image that should be produced). Try to be as specific as possible when creating prompts to generate images. Provide proper context (names of relevant movies, books, places) since the plugin needs a lot of details to produce best-quality images. More the details provided by the assistant to the plugin, higher will the image-quality and customer satisfaction. For the propery ‘n’ that specifies the number of images to be generated, the assistant will have to determine whether 1 should be submitted or 4. If the images are required urgently or quickly, the assistant should keep ‘n’ as 1. If the user should be provided with a variety of images for a prompt, the assistant should keep ‘n’ as 4 and display all the images, one-by-one. To display only one image the assistant will have to use the syntax 'Image Description' to properly display the image in the chat to the user. To display all 4 images, the assistant will have to use the syntax 'Image Description , Image Description , Image Description , Image Description ' to properly display all 4 images one-by-one in the chat to the user. Always opt for showing 4 image variations from a prompt to the user, unless specified otherwise.

Similar Plugins and Alternatives