Latenta
● All capabilities online

Every idea,
wired to a result.
Visually.

Latenta is a node canvas for AI image, text and video work — connect a prompt to a generator to a preview, press Run, and watch the whole graph fill in.

Magic-link sign-in · Free to start · Runs in your browser
Harbor study ● Saved ▶ Run
Text Prompt ■ Prompt
text
Prompt
A quiet harbor at dawn, soft mist over the water
Generate Image ■ Image
prompt image
generated image Done
01

Capability nodes, not model soup

Generate Image, Edit Image, Generate Video — semantic building blocks. Models and keys live server-side; when a better model ships, your graphs just get better.

02

An assistant that wires for you

Describe the workflow you want and watch it land on the canvas, node by node. Every reply is one undo step — experiment without fear.

03

Your library, everywhere

Workflows autosave to your library as you edit. Open them from any browser — same graph, same results, cached runs included.

Simple, token-based pricing.

Tokens buy runs · Top up anytime
Free
$0 / month

Everything you need to try the canvas — build, wire and preview without limits.

→ 100 tokens each month → Full node-graph editor → Cloud workflow library
Start free
Max
$39 / month

For heavy pipelines — video-scale token budgets for the busiest weeks.

→ 5,000 tokens each month → Best for heavy video work → Top-ups available
Go Max
A token runs one image generation · video runs cost more · plan tokens reset monthly and don't roll over, top-up tokens never expire