Canvas guide

    Build AI Image Workflows on an Infinite Canvas

    Lay out prompts, reference images and generation nodes on one canvas, connect them, and generate with GPT Image 2, Nanobanana and the site's other models, paid with your credits.

    One canvas for every step

    Prompts, references and results stay side by side.

    Why work on a canvas?

    A single prompt box only shows your latest attempt. On the canvas every prompt, reference image and result stays where you put it, so you can compare versions, reuse inputs and branch from any result.

    Text, image and generation nodes

    Text nodes hold prompts and notes, image nodes hold uploads and results, and a generation node combines the text and images connected to it.

    Reference anything with @

    Type @ in a prompt to reference a connected image, text, video or audio node. Referenced images show as thumbnails right in the prompt.

    Batches stay together

    Generating several images at once creates a stacked group. Expand it to compare and pick a main image; a line from the group passes every image on, and a line from one image passes only that one.

    Edit images in place

    Crop, upscale, split, change the viewing angle or mask an area to redraw from an image's toolbar. Each result becomes a new node.

    Learn the canvas

    Your first canvas workflow

    1

    Add your inputs

    Create a text node for the prompt, then upload or drag in reference images. Each one becomes its own node.

    2

    Connect and generate

    Connect your text and images to a generation node, then pick a model, an aspect ratio and how many images to make.

    3

    Review and continue

    Results appear as new image nodes. Download them, save them to My Assets, or connect a result to the next step to keep refining it.

    What you can put on the canvas

    Inputs

    • Text and prompts
    • Uploaded images
    • My Assets
    • Prompt library

    Generation

    • Text to image
    • Editing with reference images
    • Batch generation
    • Retry and regenerate

    Image tools

    • Crop
    • Upscale
    • Split
    • Mask redraw

    Organize

    • Groups
    • Connections
    • Minimap
    • Export and import as JSON

    The plugin manager adds more node types, such as Markdown, SVG, HTML, 360° panoramas and sticky notes.

    Canvas vs a single prompt box

    FeatureBanana Art Lab canvasSingle prompt box
    See every version side by side-
    No coding required
    Reuse prompts and references-
    Reference several images with @-
    Batch generation
    Edit results without leaving the page-

    Looking for a ComfyUI alternative?

    ComfyUI is a free, open-source node editor that runs open models such as Stable Diffusion and Flux on your own GPU. The Banana Art Lab canvas also connects nodes, but it runs in your browser with hosted models such as Nano Banana Pro and GPT Image 2: there is nothing to install, and you pay per image with credits.

    Choose the Banana Art Lab canvas when

    • You want Nano Banana, GPT Image 2 or Seedream without a GPU or any setup.
    • You start from prompts and reference images rather than wiring samplers and checkpoints.
    • You want to work from any computer, or from Codex and Claude Code.

    Choose ComfyUI when

    • You have a strong GPU and want to run open models locally for free.
    • You need custom nodes, LoRAs, ControlNet or control over every sampling step.
    • Your workflows and files must stay entirely on your own machine.

    Join the Node Artists Community

    Thousands of artists are already creating amazing workflows. Share yours and learn from the best.

    10,000+

    Active Node Artists

    5,000+

    Shared Workflows

    500+

    Daily Creations

    Ready to build your first canvas?

    Open the canvas and start with your 15 free sign-up credits, enough for seven GPT Image 2 Saver images.