The Create node is useful for building workflows that generate, edit and convert different media formats. The Create node will generate one output for each input, just like every other node in Runchat. This means if you provide a list of prompts, the node will generate a list of output media in parallel. Generated images are displayed in a grid in both Editor view and App view. The node has several parameters that will be displayed whenever they are required by the generative model.

​
Prompt

Use the prompt input to describe what you want your image to look like. Newer, larger models are better at following prompts than older, smaller and cheaper models. When using image-to-image models your prompt is still used to describe the qualities of the overall image and can not be used as “direction” for how to change the image (”change the shoe to red” etc). For these use cases, consider using Fal models that support this kind of control using the API Node.

​
Image / Images / Video

Provide an image / images / video to generate media from. The image parameter is only displayed if you using a model that requires an input image (e.g. 3D or video generation, or other custom models on fal).

​
Mask

Some models (e.g. Flux 1.1 Pro Fill) allow you to specify a region of the image to edit. You can set this with the mask input.
When you generate multiple images, video or 3D models with the Create node these will be displayed as a grid. You can drag and drop any image from this grid onto the canvas to create a new node and work with this image directly.