Make an AI Selfie Gesture Video from one close photo of the person who will talk and gesture. A second photo can be another view of that same person. The preview is a community example, and the page does not offer a menu of hand signs.
AI Selfie Gesture Video is an indoor close-up of one person talking and making hand signs. Photo 1 is that person. An optional second photo is another view of the same person, not a second speaker. The prepared reference supplies the close framing, the signs, the timing and the audio, and the result is a vertical clip you can download without filming the gestures or typing a prompt. There is no menu for picking a different sign.
Add a close photo, choose the full clip or the opening, then check the hands before you download.
STEP 1
Photo 1 is the person who talks and gestures in the AI Selfie Gesture Video. Photo 2 is optional and must be the same person, not a second speaker.
STEP 2
Original keeps the full reference. Economy and Standard keep the first 14.9 seconds, including the opening signs. Read the credit estimate beside Generate.
STEP 3
Open the result in My creations. Watch the signs you actually generated, play the sound, and do not expect a gesture menu.
The video and stills are one community example of AI Selfie Gesture Video. Your face, hands and outfit can look different.
Photo 1 should show the face, the hair and the outfit clearly, because the framing stays close. Photo 2 is optional and must be the same person, useful when another angle shows the hands or the clothes. It does not add another face. A tiny crop gives AI Selfie Gesture Video less of the hands to follow.
The full reference is about 29.8 seconds. Original plays the whole talking close-up. Economy and Standard keep a 14.9 second highlight from the start, so the opening hand signs stay and the later signs do not. The video and stills are frames from one community example. You cannot pick a different sign from a list. The signs are the ones in the prepared clip.
Original restores the reference audio for the full AI Selfie Gesture Video, and the output length rounds the 29.8 second source to 30 seconds. Economy and Standard restore only the audio from the opening highlight. The credit estimate beside Generate shows which length you are about to buy. The photos do not become a new voice or a caption.
The person comes from your photos. The close-up, the signs and the audio stay with the AI Selfie Gesture Video reference.
The second photo is another angle of the same person. It does not add a partner.
There is no prompt box for a different gesture, a caption or a second speaker. The prepared signs stay.
Original is the full close-up. The other modes stop after the opening highlight and use that opening audio.
The close photo, the hand signs, the highlight and the sound.
One close photo of the person is required. A second photo is optional and must be the same person. It is not a second speaker. Two photos is the maximum.
No. There is no gesture menu and no prompt field for a different sign. Economy and Standard keep the opening signs. Original continues through the later signs in the same prepared clip. Watch the preview if you need to know which signs are in the opening.
Original plays the full reference, about 29.8 seconds, and the output length rounds that to 30 seconds. Economy and Standard keep a 14.9 second highlight from the start. The later talking is only in Original. The credit estimate beside Generate matches the mode you select, and short modes keep only the opening audio.
Yes. The reference has audio, and the result restores the track for the segment you generate. You do not upload a song or record a new line. Listen before you share the clip.
No. AI Selfie Gesture Video keeps this close-up and these signs. The optional photo cannot be a different person. For a wider room and more of the body, use AI Room Gesture Video. For a full-body dance, use AI Hip Sway Dance.
The signs come from the reference, not from a pose you upload. Your photo guides the face, hair and outfit. Hands in the result can still look different from both your photo and the example. Check them before you download.
AI Room Gesture Video is a wider room selfie and can take two extra views of the same person. This page stays on the close-up and the hand signs. Use the preview here when the face and the signs are the point.
The generator shows a credit estimate for the mode and resolution you select. An account with enough credits is required. Plan details live on the Pricing page. The 30 second mode and the 14.9 second highlight are different lengths, so compare both quotes.
My creations holds the finished clip. Play it with sound, check the face and the hands, and use the download control on that result.
Add a close photo, review the AI Selfie Gesture Video estimate, and start from the generator.
