The LTX-2.3: Image to Video workflow is designed to transform static images into dynamic video sequences with enhanced motion consistency and detailed visual fidelity. By leveraging the LTX-2.3 model from Lightricks, this workflow excels in maintaining the integrity of fine details while transitioning from image to video format. It also offers robust support for portrait formats, ensuring that videos retain their intended aspect ratios and compositions. The workflow integrates several key nodes, including LoadImage for importing the initial image, and SaveVideo for exporting the final video output. Additionally, the b94257db-cdc1-45d3-8913-ca61e782d9c1 node is crucial for processing and enhancing audio quality, thereby enriching the overall video experience.
Technically, this workflow operates by first loading an image through the LoadImage node, which serves as the foundational input. The LTX-2.3 model then applies sophisticated algorithms to generate a sequence of frames that smoothly transition from the initial image. This is achieved by interpreting the core actions and visual details specified in the prompts, allowing for a coherent narrative flow. The SaveVideo node finalizes the process by compiling these frames into a cohesive video file. This workflow is particularly useful for creators looking to add dynamic elements to still images, whether for storytelling, marketing, or artistic 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 "LTX-2.3: 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_ltx2_3_i2v_api.json");
const asset = client.assets.fromFile("input.png");
wf.setInput("269", "image", asset); // LoadImage
const job = await client.run(wf);
await job.getOutputs("75")[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
