Make images and videos in your ComfyUI graphs
Treza is a node pack for ComfyUI. Its nodes turn a prompt into a picture or a video clip, or run one of your Treza pipelines, and hand the result to the rest of your graph. The renders run on Treza's servers, so they need no GPU or model downloads on your machine.
Free to add. You pay only for what you make.
Set it up in ComfyUI
Install the nodes
ComfyUI 0.3.45 or newer, on your own machine or a hosted ComfyUI that lets you add custom nodes.
- 1
Install Treza
In ComfyUI-Manager, search the custom nodes for Treza and install it. With comfy-cli, run the command below. Or clone the repository into ComfyUI's custom_nodes folder.
comfy-clicomfy node install treza - 2
Or clone it
Run this inside ComfyUI's custom_nodes folder.
gitgit clone https://github.com/treza-labs/treza-comfyui treza - 3
Add your Treza API key
Make a key on the Treza API keys page with the pipelines:read, pipelines:write and pipelines:run permissions. It starts with treza_live_. Save it as the only line of a file named treza_api_key.txt in ComfyUI's user folder, or set the TREZA_API_KEY environment variable before you start ComfyUI. The key is never a node setting, so it is not saved into workflows you share.
Key fileComfyUI/user/treza_api_key.txt - 4
Restart ComfyUI and open a template
The nodes are under Treza in the node menu. Three starter workflows come with the pack and show in the template browser under treza: text to image, text to video, and image to video.
What the nodes do
- 1
Treza Generate Image
Write the prompt and pick a shape. Connect up to four pictures as references to restyle them or keep a character. It returns an IMAGE for the rest of your graph, with the file's link, the price and the model.
- 2
Treza Generate Video
Write the prompt, pick a shape and a length, and choose whether it has sound. Connect a picture as the first frame, or the last frame on models that take one. It returns a VIDEO you can pass to Save Video.
- 3
Treza Run Pipeline
Starts a pipeline you built in Treza with the inputs you pass in, and returns the link to what it made. The Treza Load Image and Treza Load Video nodes turn that link into an IMAGE or a VIDEO.
- 4
Treza Balance
Shows the credits left on your Treza account. Free.
Graphs to start from
Each one is a Treza node wired to the nodes ComfyUI already has.
A picture from a prompt
Treza Generate Image, then Save Image. Each account gets 5 free images a day.
A clip from a prompt
Treza Generate Video at 16:9 and 4 seconds, then Save Video.
Your own picture, animated
Load Image, or any graph that ends in an IMAGE, into the first_frame input of Treza Generate Video, then Save Video.
Your pipeline as one node
Treza Run Pipeline with a topic in its inputs, then Treza Load Video and Save Video.
Questions
What does it cost?
The nodes are free. Renders spend prepaid credits from your Treza balance, with no subscription. Every render node has a max_cost_usd setting: set it, and Treza prices the render first, and when the price is higher the node stops and nothing is spent. Left at 0, a render runs at its quoted price as long as your balance covers it.
Will queueing the graph again charge me twice?
No. ComfyUI reuses a node's last result while its settings are unchanged, so the same graph queued again does not render again. Change the seed to make a new render.
What happens when I press Cancel?
The render is cancelled in Treza too. A step that already finished is not refunded.
Do I need a GPU?
No. The models run on Treza's servers and the node downloads the finished file, so the Treza nodes work on a laptop. The rest of your graph still runs on your machine.
Do I need an API key?
Yes. ComfyUI runs graphs without you signing in, so the nodes use a key from the API keys page instead of Google. Delete the key there to cut ComfyUI off.
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, Cursor, Codex, Hermes Agent, Blender, n8n, Zapier, Dify, Gumloop and on trezalabs.com.
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->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->LangChain
Python tools that let an agent make images and videos, with a price cap.
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->ComfyUI is a trademark of Comfy Org. Treza is an independent product and is not affiliated with or endorsed by Comfy Org.
Setup steps from ComfyUI Docs: Comfy Registry, ComfyUI Docs: Workflow templates, Treza for ComfyUI on GitHub.