What models or add-ons do I need to run this workflow?

Install Video Helper Suite (for VHS_LoadVideo and VHS_VideoCombine) and place the LTX 2.3 LoRA by @Alissonerdx into ComfyUI/models/loras. The custom face-swap node (dc72113f-8276-4a5a-af12-85d6bec89ed5) applies the LoRA during inference, so you don’t need to manually add samplers in this template.

How do I reduce flicker or a “swimming” face across frames?

Keep the ReservedRegionFrameComposer region stable around the target face and increase feathering for smoother edges. Use a high-quality, front-facing reference image with similar lighting to the driving video. Avoid aggressive frame skipping; process every frame for best temporal consistency.

Can I keep the original audio from the driving video?

Yes, route frames through VHS_VideoCombine and enable or supply the original audio if the node configuration supports it. If your setup doesn’t mux audio in ComfyUI, export the video and add audio back in a video editor.

What should I do if the face is misaligned or too big/small?

Adjust the region size/position in ReservedRegionFrameComposer and rescale the reference face with ImageResizeKJv2. Use PrimitiveFloat/PrimitiveInt controls (and ComfyMathExpression where provided) to keep the region proportional to the video resolution, then preview a short segment before exporting.

Video Face Swap - ComfyUI Workflow

This ComfyUI workflow performs a video face swap by applying a single reference face image to every frame of a driving video, then recombining the frames into a final clip. The pipeline starts with VHS_LoadVideo to decode the source video into frames and LoadImage to bring in your reference face. A custom face-swap node (dc72113f-8276-4a5a-af12-85d6bec89ed5) drives the actual face transfer using the LTX 2.3 LoRA trained by @Alissonerdx. PrimitiveFloat and PrimitiveInt nodes expose key controls (such as effect strength, region size, or frame step), while ImageResizeKJv2 aligns the reference face scale to your target footage.

To stabilize results and keep the background intact, the workflow composites the generated face back onto each original frame with ReservedRegionFrameComposer. This node lets you define a consistent “reserved” region for the face and blend it with feathered edges, reducing temporal jitter and preserving hair, lighting, and scene motion. ComfyMathExpression is used to derive dynamic values (for example, region size from video resolution), keeping settings in sync with whatever you load. For quality checks, ImageConcanate can assemble side-by-side previews of original vs. swapped frames. Finally, the processed frames are encoded to a video using VHS_VideoCombine or CreateVideo, and the result is written out with SaveVideo.

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.

bed989744195.json

Fetching workflow JSON…

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.

SDK docs Get an API key

FAQ

Frequently Asked Questions