Image Node

The Image Node holds a picture on your canvas — one you upload, or one you generate with AI. Either way, the image's content is parsed so connected chats can discuss it.

---

Supported files

• JPG, PNG, GIF, WebP

---

Uploading an image

1. Double-click the canvas and choose the image icon
2. Click Add From Computer, or drag and drop an image file onto the node
3. The AI parses the image content automatically, so any connected chat can discuss what's in it

After parsing, open the Parsed Content dialog on the node to see what the AI extracted.

---

Generating an image

1. In an empty image node, type into the prompt input — "Generate image with a description (BETA)..."
2. Pick a model from the model dropdown — models from Straico, OpenAI, and Fal AI (e.g. Flux, Imagen4, GPT Image, Nano Banana)
3. Choose a size preset: Square 1:1, Landscape 16:9, or Portrait 9:16
4. Click Generate ⏎

While generating, a Stop button lets you cancel. The finished image appears in the node with a badge showing which model made it.

Image generation requires an API key for at least one supported provider. Set your default generation models in Settings → Default Models.

---

Image-to-image

Connect one or more Image nodes into an image node as reference inputs:

1. Draw a connection from an existing Image node into your image node
2. The node automatically switches to an edit-capable model
3. Write a prompt describing the change and click Generate ⏎

Image nodes only accept Image-node inputs — you can't connect text, web, or document nodes as generation references.

---

After generation

• Click the prompt indicator to open the Prompt dialog, which shows the prompt used, the model, and a Copy Prompt button
• A model badge on the node shows which model produced the image
• The Parsed Content dialog shows the AI's description of the image, which is what connected chats receive as context

---

Use cases

• Research — drop in charts or diagrams from papers; the parsed content lets a connected chat explain or compare them.
• Writing — generate a mood or scene image to anchor a piece of descriptive writing.
• Studying — upload textbook figures and ask a connected chat to walk you through what they show.
• Content creation — iterate on thumbnails and social images with size presets, then refine with image-to-image passes.
• Planning — sketch or screenshot a layout, upload it, and have the AI critique or list next steps.