Image Input
imageInputUpload or drag-and-drop an image to feed into the workflow. Supports PNG, JPG, WebP.
- imageThe loaded image as base64 data URL
Machine-readable reference for all node types, their inputs, outputs, and capabilities. AI agents can crawl this page to understand which creative pipeline skills are available and how to compose them into workflows.
imageInputUpload or drag-and-drop an image to feed into the workflow. Supports PNG, JPG, WebP.
audioInputUpload an audio file (MP3, WAV, OGG) to feed into audio-capable nodes.
webScraperFetches a URL and extracts images and/or text from the page. Dual output.
| scrapeMode | enum | What to extract(default: all-images) |
| maxImages | number | Max images to extract(default: 4) |
promptText input node. Type a prompt that feeds into generation or LLM nodes. Supports multi-segment prompts with + Add.
promptConstructorBuild prompts from a static template with dynamic variable slots filled by upstream text connections.
| staticText | string | Template text with {slot} placeholders |
promptConcatenatorJoins multiple text inputs into a single output with a configurable separator.
| separator | string | Separator between joined texts(default: \n) |
imageIteratorBatches multiple images and runs the downstream workflow once per image. Supports random sampling.
| mode | enum | 'all' or 'random'(default: all) |
| randomCount | number | How many random images to pick(default: 1) |
textIteratorSplits incoming text by a separator and runs the downstream workflow once per segment.
| splitMode | enum | How to split: newline, period, hash, dash, custom(default: newline) |
| customSeparator | string | Custom split character (when splitMode is 'custom') |
arrayNodeHolds a list of text items. Each item becomes a separate text output during batch iteration. Can also receive items from upstream text connections.
listSelectorDropdown picker that selects one item from a configurable set of options and outputs it as text.
| selectedIndex | number | Index of the selected option(default: 0) |
splitGridDetects a grid layout in an image and splits it into individual cells. Useful for extracting frames from contact sheets.
annotationDraw on an image using a Konva canvas — freehand, shapes, text overlays. Outputs the annotated image.
imageCompareSide-by-side comparison of two images with a draggable slider.
nanoBananaAI image generation using Gemini or Kie.ai models. Accepts prompt text and optional reference images. Supports multiple aspect ratios and model-specific parameters.
| model | string | Model ID (e.g. nano-banana, nano-banana-pro, or Kie model) |
| aspectRatio | enum | Output aspect ratio: 1:1, 16:9, 9:16, 4:3, 3:4 |
| count | number | Number of images to generate per run(default: 1) |
generateVideoAI video generation from text prompts and/or reference images using Kie.ai video models (Sora, Veo, Kling, etc.).
| model | string | Kie model ID |
| duration | string | Video duration in seconds |
| aspectRatio | enum | Output aspect ratio |
generate3dAI 3D model generation from images using Kie.ai 3D models.
llmGenerateText generation using LLMs (Gemini, OpenAI, Anthropic, Groq). Can accept images for vision tasks. Outputs text.
| provider | enum | LLM provider: google, openai, anthropic, groq |
| model | string | Model ID within the provider |
| systemPrompt | string | System instructions for the LLM |
outputDisplays the final image result. End node of a workflow branch.
outputGalleryCollects and displays multiple images in a gallery grid. Useful with iterators.
videoStitchCombines multiple video clips into a single output with transitions.
stickyNoteColored note for workflow annotations. No data connections — purely visual.