Node reference
Use every Flowgen input, transform, generation, editing, and output node.
Depth Map node: local monocular depth for blur and 3D relief
Estimate scene depth from one image locally with Depth Anything V2, then output grayscale, inverted, or Turbo-colored depth at source, 1K, or 2K size.
Gen Effect node: preset or custom Seedream image treatments
Apply one of 18 generative visual treatments—or a custom instruction—to a connected image with Seedream 5 Pro Edit.
Save a Page node: create or update one site entry
Bind a site collection, map typed fields, resolve stable entry identity, save a draft or published record, mirror images, and preserve concurrent versions.
List Iterator: replace the deprecated Group Repeater
Use a paired source Items List and Results List for every new repeated row workflow. Group Repeater, loop groups, and Group Batch mode are deprecated and remain available only so existing canvases can
Object Select node: click, add/remove objects, boxes, cutouts, and masks
Use Flowgen’s Object Select node to click one object, Shift-click additional objects, Alt-click objects to remove, drag a box around several, choose a tighter/looser mask, and emit both cutout and mas
Photopea node: edit a connected image and save it back to Flowgen
Open the embedded Photopea editor from an image node, use Photopea’s full editing workspace plus Flowgen image operations, and save a durable flattened result to the graph.
Crop node: free crop and exact aspect presets
Crop one connected image with normalized Left, Top, Width, and Height controls or lock the result to Square, Wide, Portrait, or Story proportions.
Bring an HTML file into Flowgen with HTML Source
Upload or select an HTML source and expose it through a typed HTML output for joining, validation, authoring, or rendering workflows.
Depth Blur node: local focus maps and lens bokeh
Create distance-aware background or foreground blur from an optional depth map, or estimate depth locally from the source image.
Current image, video, music, and generative-edit workflows
Choose from the current live model/workflow picker, including local-first segmentation and Seedream 5 Pro Gen Effect; GPT Image 1.5 and Imagen 4 are retired from new-node pickers and remain only for s
Mask Extractor node: alpha, luminance, or local subject masks
Turn image transparency, brightness, or a locally segmented foreground subject into a reusable grayscale mask.
Video to GIF node: trim, sample, resize, and loop
Convert part of a connected video into a browser-generated 256-color GIF with controlled frame rate, width, duration, and looping.
Combine with AI node: place one image layer into another
Connect a background image, foreground layer, optional matte, and source-backed instruction; choose a supported image model and review the generated composite.
Find Pages node: query a site collection or guard duplicates
Read entries from a bound site collection as a typed dataset, filter draft/live state, order and limit results, or check whether one source URL already exists.
Bring a 3D model into Flowgen with 3D Model Upload
Upload or select a 3D model and expose it as a typed model result for preview, optimization, or a 3D scene.
Video & Motion Editor node: legacy embedded video documents
Maintain existing iframe-backed video document nodes; use the native Video Editor node for new timeline, compositing, 3D, and compositor-AI workflows.
Items List: typed records, AI Fill, views, and repetition
Create typed records, fill them with a selected AI model and rich connected context, review them as a list/grid/carousel, or pair the List with a Results List to run and collect a complete row workflo
Video Depth Fog / Blur: bake depth-of-field or compose it in Video Render
Render a local depth-blurred video, pick static focus from the opening frame, or pass the effect into a downstream composition.
Rotate & Flip node: quarter turns and mirrored images
Mirror a connected image horizontally or vertically and rotate it by exact quarter turns without sending the image to a generation model.
Route current values through Lists and Transform
Build Route & Switch branches whose winning text or media value stays current through per-case returns, Result, List iterations, exposed App switches, and downstream Extract / Merge nodes.
Extract / Merge: take apart, combine, and type connected values
Use a live, pure Transform to take apart one input or bring several ordered inputs together as text, fields, or a list; add safe visual steps, inspect actual values, follow Route winners, and expose n
Effects node: 116 live GPU looks for images and video
Apply one of 116 deterministic GPU effects to an image or video with a visual thumbnail picker, effect-specific controls, position picking, live previews, and free local rendering.
Channels node: split red, green, blue, and alpha
Split a connected image into four grayscale channel images or choose one channel and publish that same selected channel on every output socket.
Generate an Interactive element in Flowgen
Use the Agentic Web card with the interactive preset to create a code-backed interactive section without enabling the motion or 3D capability flags by default.
Color Palette node: dominant swatches and reusable hex data
Extract 2–16 dominant colors from image pixels, returning both a visual swatch strip and a prevalence-ordered JSON color list.
Retired HTML Section and HTML Combine: migration guide
Understand exactly which legacy HTML nodes were retired, why existing flows still work, what replaces each node, and how to migrate without confusing the current Unified Section/Agentic Web node with
Import Media From Your Canvas Selection
Pull the image, SVG or video you already placed in the page editor straight into flowGen as a ready-made input node — no re-uploading.
Flowgen editing nodes: local adjustments, mattes, depth, comparison, and effects
Choose among 20 focused nodes for deterministic local image work, prompted masks, video mattes/GIFs, depth workflows, before/after review, and a paid generative effect.
Bring audio into Flowgen with Audio Upload
Upload audio, use a URL, choose a project asset, or replace the current source and expose it to voice, lip-sync, composition, and audio-render nodes.
Blur node: Gaussian softness or lens bokeh
Apply an even Gaussian blur or a lens-style bokeh pass with aperture shape, rotation, highlight bloom, and threshold controls.
Levels node: input points, gamma, and output range
Set master input black/white points, midtone gamma, and output black/white points on a connected image.
Merge Alpha node: apply a mask as transparency
Apply a connected grayscale mask to an image as its alpha channel, with optional inversion and feathering.
View an Items List as a grid or fullscreen carousel
Use the Grid contact sheet to scan media-heavy records, resize tiles, and open any complete item in a fullscreen carousel while preserving the same typed rows, field order, locks, and batch behavior.
Bring an image into Flowgen with Image Upload
Upload an image, paste a URL, choose one from the project Asset Browser, or replace the current source while preserving a typed image output.
Color Correction node: tone, color, and white balance
Correct exposure, brightness, contrast, saturation, vibrance, temperature, and tint in one deterministic image step.
Trim Video node: choose a frame-aware start and end
Scrub a connected clip, set its kept start and end at the playhead, review the selected range, and render or download the trimmed video.
Build a Custom Code node
The Custom Code node lets you author your own flowGen node in TSX. You declare its input/output sockets, an optional run() transform executed when you press Run, and an optional live View rendered in
Page Template node: turn a designed page into fillable fields
Detect or mark the changeable parts of one HTML page, expose stable typed sockets, fill one record at a time, and optionally register the template as a site collection.
Branch a flow with Route & Switch
Evaluate ordered cases live, force a branch manually or through Pick by name, return case-specific typed values, merge the winner on Result, or rerun an earlier stage within a strict bound.
Continue a clip with Extend Video
Use the shared video-generation card in extension mode so a connected source clip continues with a compatible prompt, model, duration, and model-specific controls.
Compare node: before/after wipe for images, masks, and video
Inspect two image, mask, or video layers with an interactive before/after wipe without running a generation or flattening the comparison.
Blend node: modes, opacity, and optional masking
Composite a second image over a base with 15 blend modes, opacity, and an optional invertible/feathered mask.
Invert node: reverse RGB color or alpha transparency
Invert either the visible RGB colors or the alpha channel of one image, making hidden pixels visible and visible pixels transparent when Alpha is selected.
Video Matte node: green-screen and on-device subject removal
Create a full matte video or a keyed subject video from chroma-key footage or local neural foreground segmentation.
Video Captions node: add supplied or transcribed captions
Connect a clip and optionally a Text source, choose whether captions are shown, then render a captioned video or pass through the original when captions are off.
Video Mask by Text retired: migrate saved Flowgen canvases
Video Mask by Text is retired because it could not reliably track a described subject through a clip; saved nodes remain visible as removal tombstones.
Use the Brain Read and Write presets
Understand the twelve visible Brain/Brand/Business/Persona/Dataset/Document Add actions and the two underlying reader/writer card contracts they configure.
Extract Output node: choose one source output without transforming it
Use a pass-through node when a multi-output source needs an explicit output selection; the incoming source-chip choice determines what continues downstream.
Shot Motion Gen node: trim, retime, reframe, and animate a shot
Apply one semantic, shot-local motion revision to an upstream shot: source windows, timing, reframe, element/camera tracks, cue markers, and entrance-hold-exit choreography.
Use a PDF Document input in Flowgen
Upload or select a PDF and expose it as a typed document source for research, context, extraction, or another compatible node.
Matte Grow / Shrink node: refine mask edges
Feather, smooth, tighten, expand, and increase the contrast of a connected matte before compositing.
Bring a clip into Flowgen with Video Upload
Upload a video, use a URL, choose project media, or replace the current source while keeping a typed video output in the graph.
Publish Site node: send a saved Website to Preview or Live
Run the same site publishing pipeline from Flowgen, using a connected Website checkpoint and an explicit Preview or Live target.
Build a site content machine: read, structure, save, query, and publish
Combine Read a Page, Page Template, Save a Page, Find Pages, Items, Route, Approval, Website Editor, and Publish Site without duplicating content or confusing HTML generation with CMS storage.
Video Analysis node: scenes, transcript, subjects, and dead parts
Analyze one video into a reconciled millisecond timeline, searchable Markdown, and structured JSON with optional visual/audio descriptions, transcription, subject tracks, and removable dead-part sugge
Video Depth Map node: bake a depth clip or pass depth into Video Render
Estimate depth frame by frame in the open browser, or carry the depth operation into a downstream Video Render composition.
Field Mapper node: reshape records for pages and post types
Map an arriving JSON record or dataset onto a website post type, the marked fields of a Page Template, or your own target field list—with direct key mappings, text templates, fixed values, and reviewa
Text Prompt Input: Feed Words Into Generators
The Text Prompt node holds the words you wire into image, video, voice and stock nodes — type your own, or let Generate Idea / Add Details draft and expand it.
Upload Your Own Image, Video, Audio, PDF, HTML or 3D Model
Source nodes let you bring your own files into a flow: drop a file into the dashed area and it uploads to storage, then exposes a typed output handle to wire into editors and generators.
Flowgen fields and wires: cards, sidebar, source order, and output selection
Read and edit each connected input in the shared card/sidebar field rows, move sources between named fields, reorder multi-source inputs, choose a source output, and route it through Extract Output wh
Retrieve Brain context with Knowledge Search
Search Brain records by a query, optional built-in/custom item-type filters, and a bounded result count, then emit both structured chunks and formatted context.
Shot Design Gen node: build or revise one editable shot
Create an origin shot or add a non-destructive design revision with editable elements, source choices, layout variants, render profiles, and a reusable poster output.
Video Alpha Over node: layer an image or clip over a background video
Position and time an image/video overlay over a background clip, optionally constrain it with a matte, then render a new video.
Resize node: scale pixels or change the canvas
Set exact output dimensions up to 8192 pixels, either scaling the image itself or changing only its canvas, with optional proportion locking.
360 Panorama node: generate and inspect an equirectangular world
Generate one 2:1 panorama, look around in the interactive sphere viewer, compare the flat equirectangular strip, and connect it as an image or environment source.
Image Upscale node: plain, on-device, and paid AI methods
Enlarge one image by 1x, 2x, 4x, or 8x with an instant browser resize, free Swin2SR super-resolution on this device, or paid Topaz/Recraft processing.
Mask by Text node: local-first prompted segmentation
Describe an object in a still image and receive a mask, using on-device OWL-ViT plus SAM2 first and a charged cloud fallback only when necessary.
Read a Page node: scrape one website into text and data
Read one public URL through the server-side page reader and return clean Markdown plus structured images, colors, fonts, links, title, and description.
Reels & Aspect node: reframe a video for a new canvas shape
Analyze a source clip and build an editable composition for a target aspect ratio using subject-following, shot-aware, or static framing.