←  LabX Co Open the app →
LabX Co · canvas.labxco.com

LabX Flow

An AI-native creative studio. Generate image, video, and audio on an infinite node canvas, design finished artwork in a vector editor, and let AI agents create alongside you — all in one browser workspace.

ImageVideoAudioDesignAgents
What it is

Three tools most teams juggle separately — in one place.

Prompt-to-media generation, a real design editor, and an API for AI assistants share one account, one asset library, and one credit balance. Create a shot, refine it, compose it into a finished deliverable, and share it — without leaving the tab.

Generate

The Canvas

A node graph where each node turns a prompt, references, or upstream nodes into an image, video, or audio clip.

Compose

The Design studio

A vector editor for turning generated assets into posters, ads, decks, and diagrams — export-ready.

Automate

Agent API

A self-describing API so an AI assistant can generate media and author fully-editable designs on your behalf.

The Canvas

Action-first generation on an infinite node canvas.

Every node walks the same short path — decide what you're making, how, with which model, then generate. Nodes wire together, so one output feeds the next.

01
Type

Image, video, or audio.

02
Function

General, Edit, Animate, Transition…

03
Model

Only models valid for that function.

04
Settings

Aspect ratio, resolution, duration.

05
Generate

Result lands on the node.

Purpose-built functions

General (text→media), Edit, Animate (image→motion), Transition & Stitch between frames, and Act & Speak — a character that moves and lip-syncs.

Nodes that connect

An image node feeds a video node; a character feeds a talking clip. Outputs flow downstream, so a whole campaign lives on one board.

Multi-step composers

Showcase (a product → a full ad set), Storyboard (a scene per beat), and Carousel (consistent slides) build sequences in one pass.

References & keyframes

Guide results with reference images, interpolate between a start and end frame, or use reference-to-video — the controls adapt to each model.

Video timeline

Layer overlays, captions, and transitions over a clip, then render — a lightweight editor built into the node.

Explorable 3D worlds

Turn a prompt or image into a walkable 3D environment and capture frames from it back onto the canvas.

Media & libraries

A wide stable of models, plus assets you reuse.

The model catalogue is configurable — leading image, video, and audio engines side by side — and your recurring people, products, and brands are saved once and reused everywhere.

Images

Generate & edit with reference images, masks, and custom aspect ratios.

Video

Async jobs with live progress — plus talking avatars & lip-sync from an image + audio.

Audio & voice

Text-to-speech with a multi-voice screenplay syntax for scripted dialogue.

Characters

Clone a person's likeness + voice from a photo and a short clip — reuse them across shots.

Products & Brands

Saved product shots and brand profiles — colours, fonts, tone — that steer every generation.

Utilities

One-click background removal, upscaling, and logo extraction on any asset.

Design studio

A real vector editor to finish the job.

Drop your generated assets onto artboards and build the actual deliverable — social posts, ads, posters, multi-slide decks, and diagrams — then export or share it.

Artboards & elements

Shapes, text, images, gradients, shadows, and freeform SVG paths — with layers, grouping, snapping and isolate mode.

Decks & diagrams

Multi-slide presentations, flowcharts and org charts with smart connectors that stay attached, and data tables.

Export anywhere

Ship to PNG, SVG, or PDF, or present full-screen — pixel-accurate to what's on the artboard.

Share & collaborate

Public view links, per-slide comments, and role-based collaboration — invite a client or a teammate to edit.

AI agents

An AI assistant that creates for you.

A full REST API mirrors the app, so an agent authenticates with a key and does the work — generating media, wiring up projects, and authoring complete, editable designs. One call to a self-describing guide teaches it the whole system.

Self-describing API

The agent guide endpoint returns the whole system — endpoints, models, credits — so an agent learns it in one request.

Designs from a brief

The agent writes a compact layout spec — like HTML — that compiles into real, editable vector layers: generated imagery, uploads, brand fonts, multi-colour type.

Render, revise, deliver

It renders a flat proof server-side to QC, revises in place (no duplicates), and hands back a public share link.

Command it anywhere

Because the API is the interface, an agent can take a message — say, over WhatsApp — and return a finished, editable design.

Platform

Built to run in a browser, for a team.

Web-based

Nothing to install — runs in the browser, with a cloud backend and per-user auto-save.

Accounts & credits

Tiered access — unlimited internal use, or metered by a credit balance for members.

Configurable models

An admin-driven catalogue & pricing — new AI models are added without shipping code.

In one line

Prompt it, refine it, design it, and share it — or hand the brief to an agent and get a finished, editable deliverable back.

Open LabX Flow  ·  canvas.labxco.com