This workflow restores archival or degraded footage in one pass using an LTX 2.3 backbone guided by a Dearchive LoRA. It starts by decoding your clip with LoadVideo and reading timing/size data via GetVideoComponents, then routes frames through the restoration core before re-encoding to a clean MP4 with SaveVideo. The defaults are tuned to reduce common archive artifacts such as heavy grain, flicker, scratches, and compression noise, while keeping the original framing and timing intact.
Under the hood, two custom nodes (IDs: 14beb77c-6207-496b-9559-1eeb98b2ee76 and 5784f1cc-cf8c-4289-9c5b-2e837048198f) implement the LTX 2.3 model pass and apply the Dearchive LoRA. GetVideoComponents feeds FPS and resolution forward so the SaveVideo node can encode at the correct timing, helping maintain temporal consistency. If the custom nodes expose a LoRA weight/strength parameter, you can fine-tune the level of restoration: higher values push stronger cleaning, lower values retain more original texture.
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 this workflow (TypeScript)
import { Comfy } from "@comfyorg/sdk";
const client = new Comfy({ apiKey: "comfyui-..." });
const wf = await client.workflows.fromFile("workflow_api.json");
const job = await client.run(wf);
await job.getOutputs("<output-node-id>")[0].toFile("output.png");The 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
