This ComfyUI workflow leverages the Kandinsky 5.0 Video Lite model to generate high-quality videos from text prompts in both English and Russian. The workflow is designed to produce visually compelling content while maintaining a lightweight footprint, making it accessible for users with varying hardware capabilities. The key nodes used in this workflow include the SaveVideo node and a specialized MarkdownNote node, which together facilitate the seamless transition from text input to video output. The Kandinsky model is optimized for generating videos at resolutions like 768x512, with options for 5-second or 10-second durations, depending on the user's needs. This flexibility in output length and quality makes the workflow particularly useful for creating quick video content for social media or marketing purposes.
API
Use this workflow from code
Every Comfy workflow is a JSON graph. The payload below is this workflow, exactly as ComfyUI runs it — fetch it from the URL, keep it in version control, or load it in ComfyUI and run it node by node.
Run it from TypeScript or Python with the Comfy SDK. The same code targets Comfy Cloud or a ComfyUI you host yourself — only the base URL changes.
// Install (beta)
npm i @comfyorg/sdk
// Run "Kandinsky 5.0 Video Lite Text to Video" (TypeScript)
import { Comfy } from "@comfyorg/sdk";
const client = new Comfy({ apiKey: "comfyui-..." });
// This workflow, exported in API format (see note below)
const wf = await client.workflows.fromFile("video_kandinsky5_t2v_api.json");
const job = await client.run(wf);
await job.getOutputs("11")[0].toFile("output.png"); // SaveVideoThe SDK takes a workflow in API format: open this workflow in ComfyUI and use File → Export Workflow (API).
Comfy Cloud API access requires a plan with an API key.
FAQ
