The DALLE-2 block is powered by OpenAI’s DALLE-2 image generation model. It is best used to create realistic images and art from a description in natural language.

The DALLE-2 block has 1 input and 1 output.

Inputs:

  • Text: This text input functions as a prompt. It should include instructions and context for AI model needs to make any computation.

Output:

  • Image: The response returns the generated image from the DALLE-2 model based on the input of instructions and prompt provided for computation.

To make more powerful prompts, try using the Combine Text block

Upon clicking the settings of the DALLE-2 block, you can configure the resolution of the image output by choosing one of the following options:

GPT-4 32k CompliantDALLE-2: Image Variation