​

Node Inputs

The “Generate Image” node offers various inputs that allow users to customize the image creation process:

• prompt: Text input where users can describe the image they want to generate. For example, “A beautiful sunset with mountains and a river flowing in the background.” This description is used by the AI to create the image.
• num images (Optional): An integer input that determines how many images the user wants to generate for each prompt. The default value is 1, but users can request up to 10 images.
• image size (Optional): An enumerated input that lets users select the resolution of the generated images. The available sizes are 256x256, 512x512, and 1024x1024 pixels, with the default being the highest resolution (1024x1024).

​

Node Output

• image urls: After the node processes the inputs, it outputs a list of URLs. Each URL points to a generated image corresponding to the input prompt.

​

Node Functionality

The “Generate Image” node harnesses the power of AI, specifically an advanced model like DALL-E 2, to transform written descriptions into visual images. Once provided with a textual prompt describing a scene, the node processes this information and guides an AI to craft a corresponding image. Users can specify the quantity and size of the images they desire, and the node will produce a list of URLs where the resulting pictures can be accessed and viewed.

​

When To Use

This node is particularly useful in scenarios where visual representation is needed quickly and creatively without the need for a human artist. It can be beneficial for content creators, marketers, educators, or anyone who requires illustrative material to convey a concept. Whether it’s for creating visuals for social media, educational materials, storyboarding, or just exploring the intersection of AI and creativity, the “Generate Image” node offers a convenient and innovative solution.