/
Generate and edit image, video, audio, stock, 3D, and rendered output.
An agentic logo generator: give it a brand brief, pick a logo style and brand colors, and it runs a multi-step pipeline that returns both a PNG and a vector SVG logo on transparent background.
Choose between an empty Image Editor node, a right-click prewired editor, and the card/sidebar actions on an existing editor document.
Build a campaign from one editable HTML master, derive placement variations, edit any page in Designer, and export production HTML and PNG assets with a manifest.
The right-hand Stock & Media slide-out has been retired along with the bottom Add-Node bar that opened it. Stock media now comes from the Stock library section of the Add tab, and your own files from
Render a connected composition as an ordered image sequence with explicit FPS, image format, quality, frame count/progress, and a reusable output.
Search stock sound effects, audition the full asset, then wire the selected sound into an audio render or video composition.
Translate every layer and keyframe into a self-contained animated SVG (SMIL <animate> tags) you can add as a vector element, copy, or download — no video file needed.
Build non-destructive image documents with multiple layer kinds, masks, clipping, adjustments, smart filters, styles, channels, paths, history, and a flexible panel workspace.
Search the current shared stock catalog card, inspect a full image preview and source/attribution metadata, then select a typed image output for the graph or canvas.
Use the shared VideoGenerationNode card for two different Add actions: create a new clip with Gen Video, or continue a connected source with Extend Video.
Generate clean vector SVGs from a prompt — choose icon, illustration or flat style, an aspect ratio, and a Gemini model — then add the result to the canvas as an SVG element or a rasterized image.
Preserve source content, replace or restore smart-object contents, and find layers by type, visibility, masks, or effects.
Create a voice profile from connected sample audio, provider, name, description, and language, then reuse that profile in voice workflows.
Generate music or sound effects from a prompt plus tag pickers — moods, genres, instruments and tempo for music; sound types, environments and actions for SFX — with model-aware duration options.
Turn flat photographs into immersive 3D walkthroughs and isometric perspectives with flowmo’s Virtual Tour Flow. See how to generate dynamic video tours from a single static image in just a few clicks
Search and select stock image, video, music, sound-effect, or 3D assets without leaving the graph.
Two image-editing nodes that change an existing image: AI Editor toggles between Remove BG and Brush Edit, while Brush Edit is the dedicated inpainting node — paint a mask, connect a text prompt, and
Create a high-keyframe video output that seeks responsively when a website scroll interaction drives currentTime.
Create a 3D model from one or more reference images or a text description, then choose topology, quality, materials, textures, and file output.
Draw time-based notes on video frames and send the annotated instructions to a compatible edit/recreation model.
Build one clip or a multi-shot video with agentic planning, QA, continuity, frame extraction, seam repair, and editable composition.
Combine a source video and new audio, choose a supported lip-sync route, and reconcile differences in clip and speech duration.
Run a card-native live video transformation from camera or a connected video source, control the live prompt, capture samples, and save versioned results.
Choose Grok Imagine 2 variants for image generation or reference edits, with explicit 1K/2K pricing.
Turn a script into spoken audio with a chosen voice and model — Google Gemini Flash TTS or ElevenLabs — plus language, emotion presets, and inline performance cues for nuanced delivery.
A one-input/one-output node that strips the background from a connected image and outputs a transparent PNG you can chain into any other image node.
Search stock imagery, inspect a full preview and source metadata, then emit the selected image to generators, editors, or the canvas.
Takes a connected video and upscales it to 1K/2K/4K with Standard or Precision mode, optional FPS boost, sharpen, smart grain, and creativity controls; outputs an upscaled video clip.
Stop spending hours in Photoshop manual-clipping products! Learn how to seamlessly blend product cutouts into high-end lifestyle backdrops with automatic shadow and lighting matching using flowmo's Pr
Search stock footage, preview motion and duration, then emit the selected clip to video generation, annotation, composition, or rendering workflows.
Inspect adjacent clips for visual or motion discontinuities and regenerate only the transition windows that fail.
Pull a first, last, or offset frame from a connected clip for thumbnails, visual references, boundary continuity, or another image workflow.
Generate or extend video with Wan 3.0, including reference limits, sound, duration, resolution, and input-video billing.
Use all current grouped tools, their shortcuts, flyout cycling, and context-sensitive options for selection, retouching, painting, vector work, navigation, and AI fill.
Make surgical, targeted edits to any photo without complex layer masks. Discover how to isolate specific elements and modify them using plain text prompts inside flowmo’s Image Manipulation Flow.
Turns text into a styled, rasterizable image layer — pick font, size, weight, alignment, transform, and fill (solid or gradient); it auto-rasterizes when connected downstream and outputs a transparent
Plan, generate, retry, and quality-check a single video clip from a prompt, frames, source video, audio, and bounded budget.
Turn source footage and an editorial brief into a planned longer edit while preserving useful material and revising only the sections that need work.
Turn a flat image into a positioned editable document with Bria or Qwen, or into independently cropped assets with Seedream; use the engine-specific text, layer, design-system, price, and editor contr
Inspect RGB channels and alpha/selection information, then use the histogram to evaluate the current composite.
Tired of generic, over-polished AI images that all look the same? Discover how to break free from default model bias using flowmo’s Anti-AI Slop Node to enforce originality and generate distinctive, a
Chain editable shot origins and revisions by exact shot references, collect them in Video Composition, apply finishing there, and render without flattening away design-system or semantic editability.
Traces a connected raster image into a layered SVG with a chosen color budget, optional background removal and edge crop, and lets you copy, download, or save the vector to assets.
Give an image agent a brief, references, research allowance, retry limit, quality target, and budget so it can plan, generate, and evaluate candidate images.
Export an f0 document as one finished HTML file per page—or raw HTML and CSS as one file—with page selection, portable or linked runtime packaging, progress/cancel controls, saved HTML assets, and reu
Mix every audio-bearing layer of a composition into one master track with fades, normalize, and master volume, then export WAV or MP3.
Choose the Image Layers engine that matches the desired output: Bria for structured ad reconstruction with editable or exact text, Qwen for tunable layered documents, or Seedream for independent cropp
Keep the editable ImageDocument while producing the PNG or exported file needed by downstream nodes, the design canvas, or download.
Render a still from an f0 document, a 3D scene/model, a direct image, or an image composition while applying the selected page/scene, scale, format, and quality settings to the saved output.
Turn connected clips, audio, images, text, and sections into an editable video composition with renderable outputs.
Open the native Video Editor from Flowgen for clip editing, audio, compositing, motion graphics, masks/effects/tracking, recording, 3D Worlds, AI, and portable or rendered output.
Use negative-scale mirroring, precise X/Y/W/H/angle controls, proportion lock, aperture-shaped Lens Blur, and Repeat edge pixels without leaving the layered Image Editor document.
Create and refine a self-contained HTML artifact in an AI-first visual editor, with exact source, reference, asset, design-system, page, poster, motion, and editor-bundle contracts.
Create a talking Digital Twin/avatar video from a selected model plus avatar/image/video source, script, voice or audio, and the format controls supported by that route.
Run the AI operations currently wired by the Flowgen Image Editor host, preview candidates, and commit the chosen result as an editable layer/document change.
Search stock music, listen to the result, verify its rights and duration, then wire the chosen track into an audio or video workflow.
Generate versioned images in Flowgen with a model-specific contract for prompt, references, aspect, resolution, negative prompt, count, prompt expansion, advanced sampling, output format, and person g
Create a coordinated shot list, generate clips, preserve boundary continuity, repair weak transitions, and assemble a longer video under explicit limits.
Connect a layer composition, video, or native document/composition and control the render engine, scene, breakpoint, format, quality, frame rate, resolution, audio, captions, encoder, and motion blur.
Open the current full-screen v2 image editor from an Image Editor node or directly from an image-producing node, edit a native layered document, and persist a PNG preview/output back into Flowgen.
Turn static images and text screenplays into dynamic AI videos in minutes using flowmo’s node-based keyframe workflow.
Open the current full-screen v2 Image Editor from a node or a right-clicked image result, edit a native layered ImageDocument, and rasterize a PNG result for the graph or design canvas.
Discover how to instantly preview full outfits on your own body using flowmo’s Virtual Try-On Flow. Combine garments, test different styles, and see how clothes fit before buying—all with a single pho
Transform connected source audio toward a connected or selected target voice while retaining a generated audio result for preview and download.
Two nodes that embed the f0 editor inside the media-gen graph. Project hosts a full hidden f0 project (website or video) fed by connected inputs and outputs a screenshot/proxy. Lite Editor is a single
Effortlessly combine multiple subjects onto any background with flowmo’s Image Composition Flow. Automatically balance lighting, harmonize color palettes, and create unified commercial graphics withou
Upload or select an HDRI/environment asset and expose it as a typed environment output for a 3D workflow.
Use Object Select in the Image Editor to highlight the object beneath the pointer, commit it with one click, select every object inside a box, combine the result with an existing selection, and refine
Learn how flowmo’s Branded Merch Flow automatically maps your logo onto entire lines of apparel and accessories with realistic fabric lighting and textures in a
Frame an image with ratio presets, straighten a horizon, and choose whether cropping preserves or deletes pixels outside the canvas.
Build sections, full websites, and video compositions with the real f0 editor embedded inside the Flowgen graph.
Use the Omni 1.1 video route with native sound, first/last frames, multiple references, and output up to 4K.
Upgrade your LinkedIn and resume with studio-quality headshots without booking an expensive photographer. Learn how flowmo’s Professional Executive Shots Flow turns casual everyday photos into sleek c
Understand when Fast browser, Full desktop, and Cloud are selectable, what source each accepts, and which settings each path currently honors.
Turn flat product photos into engaging 8-second video ads in just a few clicks. Learn how to use flowmo’s Product Video Flow to generate studio-quality motion graphics and camera sweeps from a single
Search stock 3D assets, inspect the model preview and delivery metadata, then connect the selected model to optimization or a 3D scene.
Choose the fast Flare or precise Sunburst GPT Image 2.5 route, set one of the supported canvas shapes and 1K–4K output tiers, connect up to sixteen references for an edit, and understand exactly when
Render a Layer Compose, flat video, or native document/composition to MP4 or WebM using the available browser, desktop, or cloud target, then add, replace, or download the result.
Use the native Video Editor node as a durable editable composition inside a flow, route layers/audio/compositions/mattes/design systems into it, then render or reuse its outputs.
Know which nodes open video, website, section, 3D, ad, design-system, or Designer surfaces; manage the shared editor window; and create links that reopen the correct master, page, or selection.