The Hunyuan Video 1.5 Image to Video workflow is designed to transform static images into engaging videos with controlled motion and camera dynamics. This workflow leverages the Hunyuan Video model, which is renowned for its ability to maintain visual consistency while introducing smooth and natural movements to images. Key nodes in this workflow include VAEDecode, VAELoader, and the HunyuanVideo15ImageToVideo, which work in tandem to decode and process images into video format. The workflow also incorporates advanced nodes like CLIPTextEncode and CLIPVisionEncode to enhance the semantic understanding and visual encoding of the input images, ensuring the generated video is both coherent and visually appealing.
Technically, this workflow is structured into several steps, starting with model loading and image uploading, followed by prompt configuration and video size adjustments. The use of nodes like CreateVideo and SaveVideo ensures that the final output is not only generated efficiently but also stored correctly for further use. The inclusion of the EasyCache node offers an option to speed up processing at the cost of video quality, providing flexibility based on the user's hardware capabilities. This makes the workflow particularly useful for artists, animators, and content creators looking to breathe life into still images with minimal manual intervention.
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 "Hunyuan Video 1.5 Image 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_hunyuan_video_1.5_720p_i2v_api.json");
const asset = client.assets.fromFile("input.png");
wf.setInput("80", "image", asset); // LoadImage
wf.setInput("44", "text", "your prompt here"); // CLIPTextEncode
const job = await client.run(wf);
await job.getOutputs("102")[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
