The 'Wan 2.1 Text to Video' workflow is designed to transform text prompts into dynamic video content using the Wan 2.1 model. This workflow leverages a series of specialized nodes in ComfyUI, including KSampler, CLIPTextEncode, and VAEDecode, to interpret textual descriptions and generate corresponding video sequences. By utilizing the CLIPLoader and UNETLoader nodes, the workflow ensures that the text prompts are accurately encoded and decoded into visual representations, while the VAELoader and EmptyHunyuanLatentVideo nodes manage the latent video space and video generation process. The final output is crafted using the CreateVideo and SaveVideo nodes, which compile the generated frames into a cohesive video file.
This workflow is particularly useful for content creators and digital artists looking to quickly prototype video concepts based on narrative descriptions. The use of the Wan 2.1 model allows for high-quality video production with nuanced interpretations of complex prompts. The workflow's structured approach to model loading and video size configuration ensures that users can efficiently transition from text input to video output, making it a practical tool for both experimental and professional video generation projects.
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 "Wan 2.1 текст в видео" (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("text_to_video_wan_api.json");
wf.setInput("6", "text", "a fox moving quickly in a beautiful winter scenery nature trees mountains daytime tracking camera"); // CLIPTextEncode
const job = await client.run(wf);
await job.getOutputs("50")[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
