Make an AI Room Gesture Video from one photo of the person who will gesture in the room. Up to two more photos are other views of that same person. The preview is a community example, and the extra photos are not a partner.
AI Room Gesture Video is a room selfie in which one person dances and gestures. Photo 1 casts that person. Photos 2 and 3 are optional views of the same person, so the outfit can be seen as they turn. The prepared reference supplies the room, the gestures, the timing and the audio, and the result is a short vertical clip you can download without filming the room or typing a prompt. The extra photos do not add a partner, and there is no caption field.
Add the person, add extra views only of that person, then check the gestures before you download.
STEP 1
Photo 1 casts the person in the room. Include the face and the outfit that should carry the gestures.
STEP 2
Photos 2 and 3 are optional angles of the same person. Leave them empty if you only have one picture. Do not use them for someone else.
STEP 3
All three modes keep the 13 second clip. After it appears in My creations, watch the hands, play the sound, and download the file you want.
The video and stills are one community example of AI Room Gesture Video. Your face, outfit and gestures can look different.
Photo 1 should show the face, the hair and the outfit that will carry the room. The optional photos are other angles of that person, useful when a turn hides a sleeve or the back of the outfit. They are not a second dancer. Three photos is the maximum. A group shot does not become a cast list for AI Room Gesture Video.
The prepared reference is 13 seconds, already inside the short-mode limit, so Economy, Standard and Original each play the full room sequence and its audio. A lower-cost mode does not drop the last gesture. You do not upload the room or pick the gestures from a menu. The video and stills are frames from one community example of that room.
Because the whole AI Room Gesture Video fits the short-mode limit, every mode restores the same reference audio. The photo does not become a new voice or a caption. Resolution and the credit estimate still follow the mode you select. The duration beside Generate is the length you will receive for this 13 second clip.
The person comes from your photos. The room, the gestures and the audio stay with the AI Room Gesture Video reference.
One photo is enough. The other two slots only show the same person from another angle.
There is no prompt box for a different room, a caption or a second dancer. The prepared gestures stay.
Economy, Standard and Original all use the full 13 seconds and the same reference audio.
The three-photo limit, the room gestures, modes and sound.
One photo of the person is required. You may add up to two more photos, and each one must be another view of that same person. Three photos is the maximum. The extra photos are not extra people.
Generate with photo 1. The optional views help when a turn hides part of the outfit, but they are not required. The room and the gestures still come from the prepared reference.
No. AI Room Gesture Video keeps the gestures in the reference. There is no gesture menu and no caption field. If you want a closer talking shot and hand signs, use AI Selfie Gesture Video instead of trying to rewrite this room.
Economy, Standard and Original each use the full 13 second reference. None of them is a shorter highlight, because the clip already fits the short-mode limit. They can differ in resolution and in the credit estimate shown beside Generate. Read that estimate before you submit.
Yes. The room reference has audio, and every mode restores that track. You do not upload a song. Listen before you share the clip.
No. The room, the gestures and the timing stay prepared. There is no prompt field for a courtyard, a caption or a second dancer. Use Catel Madatorricelli Dance AI for a courtyard gesture dance, or AI Hip Sway Dance for a full-body indoor dance.
A clear photo helps the model follow the face and the outfit, but both can shift as the person turns. Extra angles can give the model more of the clothes to see. The page does not promise a perfect match. Check the result before you download it.
AI Selfie Gesture Video stays on a talking close-up and can run much longer, with a short highlight in the cheaper modes. This page is the wider room and finishes in 13 seconds in every mode. Use the preview here when you want the room in frame.
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.
My creations holds the finished clip. Play it with sound, check the person, and use the download control on that result.
Add the person photo, review the AI Room Gesture Video estimate, and start from the generator.
