Become a founding member. Book a call with the founders for member pricing and perks.
/real-swap in your agent.Put any character into real phone footage. The camera, light and grain stay real.
Swap the person in a real clip for any character, and keep the clip real.
Why the extra steps: video models like Seedance refuse a lot of clips that show a real person's face, and famous faces almost always. This board hides the person first, so the clip goes through.
Hiding the person also means the original face never leaks into the swap, so the new face comes only from your refs. Only the person is regenerated, so the background, camera, light and grain stay the original footage. And nothing of the real person ends up in what you make.
Talking clips keep their lips: a face mesh tracks the jaw, lips, eyes and brows, and the original voice guides the mouth, so expressions carry over while the face stays hidden.
Swap the person, the world around them, or both, from the same mask.
How it runs: the board masks the person, keeps the motion with a depth pass and the face mesh, then swaps in your character from your refs. Every step and its cost is on the board.
# How Real Swap works (v3: hide the person, keep the room, mesh the mouth) Real Swap puts your character into a real clip and keeps everything else real: the camera, the light, the grain and the room. Raj is the worked example, swapped into a clip of AI Michael at his desk. Swap in your own clip and your own character. **Why the person disappears first.** Show a video model a clear person and it copies what it sees: their face shape, their hair, their clothes. So before Seedance sees anything, this board hides the whole person inside a colored depth shape and leaves the real room around it. The shape carries the motion, a thin face mesh on its head carries the mouth, and your character sheet carries the look. This is the method from Sirio Berati's open-source Genjutsu workflow (MIT), built as one board. 1. **Your clip** (Import, Video Trim). One continuous shot, one person, knees up or closer, hands mostly away from the face. Trim it to the window you want (4 to 8 s works well). The Mute node makes a silent copy for the model; set its scene length to your window (seconds x 24) and the Audio split range to match (0-7 for 7 s). 2. **The sound** (Audio split, Audio Pad). Your clip's own audio, kept on the side and put back at zero offset at the end, so nothing drifts. 0 credits. 3. **The mask** (Segment Mask). One word, person. SAM 3 tracks the whole body every frame. Scrub it: if a hand drops out for a frame, the model invents a new hand. 4. **The depth** (Depth Map, colored). Warm is close, cool is far. That is the motion without the face. 5. **The composite** (Masked Composite, free). Depth only where the person was, the real room everywhere else. Grow 30 covers hair and edges; largest region only stops specks turning into extra people. 6. **The face mesh** (Face Mesh, free). Hiding the head also hides the mouth, so Seedance used to hand back a character with his mouth shut while you talk. Face Mesh tracks the face in your clip (478 points a frame) and draws the jaw, lips and eyes as thin lines onto the composite. The model gets the mouth shapes without ever seeing your face. Keep its Lips setting on face (the lips drawn in the same thin blue as the rest of the mesh): with the default coral outline, Seedance paints coral lips onto your character. Check its tracking report: every frame should have a face. 7. **The swap** (Seedance 2.5, reference mode). @Video1 = the composite with the mesh, @Image1 = your character sheet, generated audio off. The prompt is short and blunt: replace the whole person, keep the real background, take the role from the clip, not the clothes. The prompt also says the mesh lines are guidance only and never appear in the take. Write the model's misses into the prompt as "never" lines and rerun only this node. 8. **The finish** (Video Editor + Side by side). The swap with your clip's original audio, and original | depth + mesh | swap to judge it. What still breaks: hands crossing the face, two people in one shot, very fast turns. The mouth follows the mesh from your clip, so it opens and closes with your original audio, but it is not frame perfect. Short clips can come back a touch short: the Seedance card warns you when it does. Costs: every paid step shows its price before it runs. Mask + depth are a few dozen credits; Seedance is most of the bill and scales with the seconds.
Real outputs from this skill's nodes.
Connect once. Ask any time.