This ComfyUI workflow compares video upscaling techniques using the Topaz Starlight Precise 2.5 model against its predecessors. The primary focus is on enhancing video resolution to 4K while minimizing artifacts and preserving sharpness. The Topaz Starlight Precise 2.5 model is designed to produce clearer and more detailed output, making it a preferred choice for high-quality video enhancement. By utilizing nodes such as LoadVideo, SaveVideo, and TopazVideoEnhance, this workflow provides a streamlined process for users to upscale their videos efficiently.
Key differences between the Topaz Starlight Precise 2.5 model and earlier versions include improved artifact reduction and sharper image quality. The workflow leverages advancements in AI-driven video processing, offering a significant upgrade in terms of visual fidelity. Users can expect a noticeable improvement in video clarity and detail, making this workflow ideal for professionals seeking high-resolution outputs for various applications.
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 "Video Upscale: Topaz Starlight Precise 2.5" (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("api_topaz_starlight_precise25_api.json");
const job = await client.run(wf);
await job.getOutputs("4")[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
