How to use Face Mesh
- Add a video as the source.
- You can also add more videos if you want to guide the result. This is optional.
- Adjust the settings, or keep the defaults.
- Choose Open in a workflow. Sign in, check the credit estimate on the board, then run it.
- Connect the result to the next step on the board, such as an editor or another model.
Inputs explained
- Video (face tracked here) (required)
- Set the video (face tracked here) used by this model. Type: video.
- Base Video (draw onto; blank = the clip) (optional)
- Set the base video (draw onto; blank = the clip) used by this model. Type: video.
- Where to look for the face (optional)
- Set the where to look for the face used by this model. Type: text. Options: auto, full, center. Default: "auto".
- Lip lines (optional)
- Set the lip lines used by this model. Type: text. Options: coral, face, off. Default: "coral".
- Quality (CRF, 12 best … 30 smallest; blank = 18) (optional)
- Set the quality (crf, 12 best … 30 smallest; blank = 18) used by this model. Type: number.
Tips before you run
Start with the default settings and change one input at a time. Keep the result you like on your board so the next step can use it.
If you add a reference file, use a link the workflow can read. Check the inputs and credit estimate on the board before starting a run.
Face Mesh pricing
Face Mesh is free to run on Wireflow.
See Wireflow plans and credits
Face Mesh API
Run Face Mesh from your own code with the Wireflow API. Open it in a workflow, then call the run endpoint with that workflow's ID and poll for the result. Agents can run it through MCP.
# Model: Face Mesh. Open a workflow first.
# Replace YOUR_WORKFLOW_ID with the ID in its /flow/ URL.
curl 'https://www.wireflow.ai/api/v1/workflows/YOUR_WORKFLOW_ID/run' \
-H 'Authorization: Bearer YOUR_WIREFLOW_API_KEY' \
-H 'Content-Type: application/json' \
-d '{"nodeIds":["model"]}'
# Response (202):
# {"data":{"executionId":"...","status":"running",
# "poll":"/api/v1/workflows/executions/.../poll"}}
# GET the returned poll path with the same Authorization header.Read the run API docs or connect your agent.
Working with this model
What it is for
A talking character swap needs the mouth. Real Swap hides the source head so Seedance cannot copy the face, and that also hides the jaw and the lips: the take comes back with the right character and a mouth that does not move.
Face Mesh puts the motion back without the face. It finds the face in every frame of Video and draws its mesh as thin lines: the face in thin blue, the lips in coral (see Lip lines below), the eyes in green. Wire the hidden-head composite into Base Video and the mesh is drawn there, exactly where the hidden face was.
Recipe: keep the mouth moving in a Real Swap
- Run the Real Swap prep as usual, up to the composite that hides the head.
- Face Mesh: the trimmed source clip into Video, that composite into
Base Video, and Lip lines set to Match face lines (
face). - Read Tracking report on the card before any paid run. Frames with no face get no mesh, and the mouth goes still there.
- Wire Mesh Video into Seedance's reference video port in place of the composite. In the prompt, say that the mesh lines are motion guidance only and must not appear in the video.
Tested on a Seedance take with the default coral lip lines: the swapped mouth
follows the source, but Seedance paints thick coral lips in every frame. That
is why step 2 sets face; a take with face has not been run yet.
Outputs
- Mesh Video: the base (or the clip) with the mesh drawn on, same size, frame rate and length, with that clip's audio.
- Landmarks (JSON url): every frame's 478 face points, x and y from 0 to 1 of the frame, for anything that wants the raw tracking.
- Tracking report: how many frames had a face, and which did not, with a
one-line summary such as
no face in 3 of 130 frames: frames 12-14.
Where it looks for the face
- auto (default): the whole frame, and on a miss the centre of the frame (the middle half across, the top 65 percent down), where a seated speaker usually is.
- full: the whole frame only.
- center: the centre only, for a small speaker in a wide shot.
It tracks one face per frame. For a clip with two people, crop to the speaker first.
Lip lines
- Coral (
coral, default): the lip contour as a thicker coral line, the original drawing. - Match face lines (
face): the lip contour in the same thin blue as the rest of the face. Use this for a person swap: Seedance reads a coral contour as coral lips and paints them in. - Off (
off): no lip contour at all. The face lines around the mouth still move with it.
Limits
The base must have the same size, frame rate and frame count as the clip, or the run is refused with both numbers (make the base from the same trimmed clip). Clips over 30 seconds or over 2160 pixels on the long side are refused, as are HDR clips and inputs over 500 MB. A clip with no face in any frame is refused. The same inputs and settings always give the same files.
Credit: the technique and the mesh drawing are adapted from the open-source Genjustsu workflow by Sirio Berati (MIT license), using Google's MediaPipe Face Landmarker.
This node is free: it quotes and charges 0 credits.
Face Mesh FAQ
What is Face Mesh?
Face Mesh is a Wireflow workflow tool. Track the face in a video frame by frame (Google MediaPipe Face Landmarker) and draw its mesh as thin lines: the face tessellation in thin blue, the lips in coral (see `lips`) and the eyes in green.
Is Face Mesh free?
Yes. Face Mesh is free to run on Wireflow.
Can I use Face Mesh commercially?
Yes. What you make with Face Mesh on Wireflow is yours to use for personal and commercial work, subject to the model maker's own terms. Our terms of service have the details.
Does Face Mesh have an API?
Yes. Save a workflow with Face Mesh, then call the Wireflow run API with its workflow ID. The API tab above has examples you can copy, and agents can run it through MCP.
How do I use Face Mesh?
Set the inputs above and choose Open in a workflow. Sign in to save your board, then check its credit estimate before you run.