Text nodes

Text nodes carry words: an idea or prompt you write by hand, or text an AI generated or read from an image or audio. They often feed image and video generation upstream.

What they're for

Text plays two main roles on the canvas: as a prompt or script linked into downstream image / video nodes to shape their generation, or as the output of a text generation task itself (AI continue, rewrite).

Create and generate

• Choose Text in the Add node menu to create a text generation node, then type in it or have the AI continue or rewrite the text;
• Link the text node's output into an image / video node, and its text merges with that node's own prompt for generation;
• What you write by hand in a text node is never machine-translated; it stays exactly as you wrote it.

Reading images and speech to text

Open the Text category from the + beside a neighboring node to create nodes whose output is text:

• The + beside an image node → Text: creates a text generation node that can read the image, for example to describe the picture or write a prompt from it;
• The + beside an audio node → Text: speech to text, pulling the words out of a clip.

Both are paid generations, and you see the credit estimate when you create them.