Wire text, image and vision models into reusable workflows. The canvas defines what the agent can do. The Brain decides how to use it at runtime.
Made with Zyvro
Published workflows, each shown as what went in and what came out.
Nodes
Every capability you can drop on the canvas.
Text InputInput
Static text or runtime input
Image InputInput
Uploaded image or runtime input
Merge TextUtility
Concatenate upstream texts
LLMModel
Text completion via Ollama
Generate ImageModel
Text -> image via Gemini
Edit ImageModel
Edit an image with a prompt
Remove BackgroundModel
AI two-pass matte, or programmatic color-range removal
Rotate ImageUtility
Rotate an image by 90-degree steps
Flip ImageUtility
Mirror an image horizontally or vertically
Vision / JudgeModel
Analyze image(s) with a VLM
BrainAgent
Agent that calls connected nodes as tools
Workflow ToolsAgent
Gives a Brain the MCP tools: list, inspect and run your other workflows
PreviewOutput
Render a result in the node
3D Voxel PreviewOutput
Cube or sphere textured with the connected images
OutputOutput
Mark a workflow result