Make images and videos in Langflow

lfx-treza adds Treza components to Langflow. Drop Treza Image or Treza Video into a flow, or switch on Tool Mode and give them to an Agent, and get back the finished file's link and what it cost.

lfx-treza on PyPI

Free to add. You pay only for what you make.

Set it up in Langflow

Add the components

Self-hosted Langflow 1.13 or newer, where you can install Python packages.

  1. 1

    Install it

    Install the bundle in the Python environment Langflow runs in, then restart Langflow. The components appear under Treza in the components menu.

    pip
    pip install lfx-treza
  2. 2

    Add your Treza API key

    Make a key on the Treza API keys page with the pipelines:read, pipelines:write and pipelines:run permissions. Paste it into a component's Treza API Key field, or save it as a Langflow global variable named TREZA_API_KEY so every component picks it up.

  3. 3

    Drop in a component

    Treza Image and Treza Video take a prompt and a shape and return the finished file's link, the price and the model. Set Max Cost (USD) to stop anything pricier: Treza quotes the render first, and over the cap nothing starts.

  4. 4

    Or give it to an Agent

    Switch on Tool Mode in the component's menu and connect it to an Agent's Tools input. The agent writes the prompt; the key and Max cost stay as you set them on the canvas.

What the components do

  1. 1

    Treza Image and Treza Video

    A picture or a clip from a prompt. Pictures can start from reference pictures in your Treza library, and clips can open or end on one.

  2. 2

    Treza Run Pipeline

    Runs a pipeline you built in Treza, with new inputs as JSON, and returns everything it made.

  3. 3

    Treza Get Run

    Looks a render up by its IDs. A clip that takes longer than the component waits comes back as still running, not as an error, and this picks it up. Free.

  4. 4

    Treza Balance

    The credits left on your Treza account. Free.

Flows to start from

Each one is a Treza component plus the components you already use.

A clip from a chat

Chat Input into an Agent with Treza Video in Tool Mode, Max Cost $1, and the clip's link in Chat Output.

A picture, then the clip

Treza Image feeds its link to Treza Video's First Frame URL, so the clip opens on the picture.

Your pipeline as a tool

Treza Run Pipeline in Tool Mode with your pipeline's ID, so the agent passes in the topic and replies with the finished video.

A batch from a file

Rows from a file loop through Treza Image, one picture per row, each under the same Max cost.

Questions

What does it cost?

The bundle is free and MIT licensed. Renders spend prepaid credits from your Treza balance, with no subscription. Treza prices each render first, and over your Max cost the component returns the reason and nothing is spent.

Can an agent raise the price cap?

No. Max cost and the API key are fields on the canvas, not inputs the agent fills in. With no cap set, a render runs at its quoted price as long as your balance covers it, so set one on components you give to an agent.

Which Langflow does it work in?

One where you can install a Python package into Langflow's environment. We tested it on self-hosted Langflow 1.13.3.

Do my videos and credits carry over between apps?

Yes. Every app signs in to the same Treza account, so your library, your pipelines and your balance are the same in ChatGPT, Claude, Muse, Gemini, Mistral Vibe, Cursor, Codex, Hermes Agent, Blender, n8n, Zapier, Dify, Langflow, Flowise, Gumloop and on trezalabs.com.

Do I need an API key?

Not where the app can sign in for you: it sends you to Treza to sign in with Google and approve access, and no key goes into the chat or a config file. Apps that only take a key, and tools that run without a person, use a scoped key from the API keys page.

Treza in other apps

ChatGPT

In ChatGPT's plugin directory. Add it and mention @Treza in any chat.

Set it up->

Claude

A custom connector in the Claude app, or the Treza plugin in Claude Code.

Set it up->

Muse

Ask Muse to build a Treza connector, or add Treza to Muse Code.

Set it up->

Gemini

A custom app in the Gemini app, or a server in Antigravity CLI.

Set it up->

Mistral Vibe

A custom connector in Mistral Vibe, formerly Le Chat.

Set it up->

Cursor

One click adds Treza to Cursor's agent.

Set it up->

Codex

From the plugin catalog in the ChatGPT app, or one command in Codex CLI.

Set it up->

Hermes Agent

A few lines in ~/.hermes/config.yaml and one login command.

Set it up->

Blender

An add-on that turns your camera view into AI renders and video clips.

Set it up->

n8n

A verified node that makes images and videos inside your workflows.

Set it up->

Zapier

Steps that make images and videos in your Zaps. In beta.

Set it up->

Dify

A tool plugin that makes images and videos in your workflows and agents.

Set it up->

ComfyUI

Nodes that make images and videos in your graphs, with no GPU needed.

Set it up->

LangChain

Python tools that let an agent make images and videos, with a price cap.

Set it up->

LlamaIndex

A tool spec that lets an agent make images and videos, with a price cap.

Set it up->

CrewAI

Tools that let the agents in a crew make images and videos, with a price cap.

Set it up->

Vercel AI SDK

TypeScript tools that let a model make images and videos, with a price cap.

Set it up->

Flowise

A Custom MCP tool for Flowise agents, signed in with an API key.

Set it up->

Gumloop

A custom MCP server that lets your agents make images and videos.

Set it up->

Any MCP client

One URL for every client that speaks Streamable HTTP MCP.

Set it up->

Langflow is a trademark of Langflow. Treza is an independent product and is not affiliated with or endorsed by Langflow.

Setup steps from lfx-treza on GitHub, Langflow Docs: Bundles.