Every node type available in the palette, grouped by category. Use this as a lookup, not a read-through; search the palette itself by name or description when building.
| Node | What it does |
|---|
| Prompt | A text prompt input that drives generation nodes |
| Text input | A free-text field surfaced on the published form |
| Image input | Upload a single image as a source |
| Multi Image Input | Upload multiple images at once |
| Video input | Upload a video as a source |
| Audio input | Upload an audio track as a source |
| Reference image input | Provide a reference image for style/subject conditioning |
| Pinterest Scraper | Pull images from Pinterest as inputs |
| Aspect ratio | Choose an output aspect ratio (feeds generators) |
| Number | A numeric parameter input |
| Moodboard | Collect reference imagery into a board |
| Background input | Supply a background image/scene |
| Characters | Provide character reference assets |
| Poses | Provide pose reference assets |
| Image Pool | A pool of images to draw from |
| Face Assets | Provide face reference assets |
| Brand Memory | Pull your saved brand positioning/context into the workflow |
Text
| Node | What it does |
|---|
| Text (LLM) | Run an LLM to generate or transform copy (token-billed) |
| Prompt Enhancer | Expand a short prompt into a richer, model-ready prompt |
| Node | What it does |
|---|
| Image | Generate an image (billed per image size) |
| BG Remove | Remove the background from an image |
| Crop | Centre-crop to an aspect ratio or exact dimensions |
| Rotate & Flip | Rotate 90/180/270 degrees or mirror an image/video |
| Resize | Resize an image or video, fill, fit, or stretch |
| Upscaler | Upscale an image (Topaz) |
| Node | What it does |
|---|
| Seedance 2.0 | Generate video with BytePlus Seedance 2.0 (first/last frame) |
| Seedance 2.0 Reference Image | Seedance 2.0 with reference-image conditioning |
| Grok Imagine | Generate video with xAI Grok Imagine |
| Kling 2.5 | Image-to-video with Kling 2.5 Turbo Pro |
| Kling 3.0 | Frame-interpolation video with Kling 3.0 Pro |
| Kling V3 Omni Video | Text-to-video, up to 7 reference images |
| Gemini Omni Flash | Text-to-video / image-to-video with audio (Google) |
| Gemini Omni Reference | Reference-to-video from subject/style images |
| Gemini Omni Edit | Edit an existing video with a prompt |
| Video Analyzer | Analyze a video and return a text result (Gemini) |
| Extract Frame | Pull a single frame from a video as an image |
| Video Concat | Stitch multiple clips end to end |
| Video to audio | Generate audio for a video (MMAudio) |
| Veed Subtitles | Burn styled subtitles into a video |
| Merge audio + video | Combine an audio track with a video track |
| Node | What it does |
|---|
| Lyria 3 | Music generation, Clip (30s) or Pro (full song) |
| Node | What it does |
|---|
| Bundle | Collect fanned-out images into a single set |
| Text Iterator | Loop over text values to fan out generations |
| Image Iterator | Loop over images to fan out generations |
| Image Randomizer | Randomly pick from a set of images |
| Garment Classifier | Sort images into N labeled buckets (one LLM call per class) |
| Node | What it does |
|---|
| Download | Download connected images and videos |
| Sticky Note | A free-form annotation on the canvas (not executed) |