The Outstanding AI meme, with you and two friends as the band

How to make an Outstanding video yourself

You do not need this page to make one. This is how the video is put together, with the prompts for every shot, so you can build it with any picture model and image-to-video model you like.

1. Step 1

   Draw one still per shot from the three photos

   Use a picture model that takes reference photos. The two band shots need all three photos, the laugh only the second and the sax only the third. Describe the office corner the same way in every still, the bookshelves, the desk, the keyboard and the mics, or the room changes between shots.

2. Step 2

   Say who stands where

   Name each person by the order you sent the photos: the person in image 1 sits in the middle at the mic, image 2 stands behind on the left, image 3 behind on the right with the sax. Say it again in the last shot, or people trade places between the first band shot and the last.

3. Step 3

   Animate each still, then cut on the sound

   Give each still to an image-to-video model with one line about what moves. Trim the clips so the cuts fall at 5.4, 11.8 and 15.15 seconds, where the trend sound cuts, lay them end to end at 9:16 with hard cuts, and add the sound on TikTok so the laugh and the solo land on time.

The shots, second by second

The prompts, shot by shot

Each shot is made in two steps. Give its still prompt to a picture model with the photos listed for that shot as references, then give the picture it draws to an image-to-video model with the motion prompt. Add these endings to every prompt: they set the look and keep the faces the same from shot to shot.

1. 0–5.4sThe band

   Photos to attach, in orderImage 1: The lead singerImage 2: The one who laughsImage 3: The sax player

   Still prompt

   Copy

   A medium-wide shot of three people about to perform together, seen from the front and framed from the desk up, so their faces are large and clear, in a cramped, cosy office corner turned into a stage. Tall wooden bookshelves crammed with old books, vinyl records, potted plants and little keepsakes cover the wall behind, a small wooden office desk stands in front with a plain black electronic keyboard on it, microphones on black stands, and warm light from desk lamps. None of it has any logo, print or writing on it: the book spines, the record sleeves and the keyboard are blank. The person in image 1, in their own clothes from the photo, sits in the middle behind the desk at a microphone on a stand, one hand in a loose fist at chest height, eyes open, lips closed, face in full view. The person in image 2, in their own clothes from the photo, stands behind them on the left of the frame, eyes open, face in full view. The person in image 3, in their own clothes from the photo, stands behind them on the right of the frame with a gold tenor saxophone hanging from a strap at their chest, eyes open, face in full view. Each face comes from that person's own photo alone, never a mix of the three: the one at the microphone has exactly the face, gender and age of the person in image 1. Exactly these three people are in the picture; nobody else is in the room.

   Motion prompt

   Copy

   The person at the microphone belts out a big, soulful note, eyes squeezing shut, and pumps a fist in time with the music; behind them the other two sing along with feeling, swaying and nodding to the beat. Everyone stays in their place, the one in the middle seated at the desk. The camera holds steady, with a slight handheld drift.

2. 5.4–11.8sThe laugh

   Photo to attachThe one who laughs

   Still prompt

   Copy

   A tight close-up of the person in the reference photo, in their own clothes from the photo, singing, their head and shoulders filling most of the frame, turned slightly to one side in three-quarter view, face toward the camera and in full view, eyes closed, mouth open mid-note, lost in the song. Behind them, tall wooden bookshelves crammed with old books, vinyl records and potted plants in warm lamp light, softly out of focus, with no logo, print or writing on any of it. The picture is upright and level, their head above their shoulders. Only this one person is in the picture; nobody else is in the room.

   Motion prompt

   Copy

   They hold a long, soulful note with feeling for two seconds, then turn their face to the lens with a wide grin and break into a huge, helpless laugh, shoulders shaking, one hand coming up in front of their chest, still laughing at the end. The camera holds close, with a slight handheld drift.

3. 11.8–15.2sThe sax

   Photo to attachThe sax player

   Still prompt

   Copy

   A close-up of the person in the reference photo, in their own clothes from the photo, playing a gold tenor saxophone, their head, shoulders and the top of the saxophone filling most of the frame, seen from slightly in front, the mouthpiece at their lips, both hands on the keys, eyes closed, face toward the camera and clearly visible. A microphone on a black stand stands in the foreground at the bottom of the frame, close to the bell of the saxophone. Behind them, tall wooden bookshelves crammed with old books, vinyl records and potted plants in warm lamp light, softly out of focus, with no logo, print or writing on any of it. The picture is upright and level, their head above their shoulders. Only this one person is in the picture; nobody else is in the room.

   Motion prompt

   Copy

   They play a soaring, soulful run on the saxophone, fingers moving on the keys, swaying with it, and at the end of the phrase lower it from their lips with a satisfied look. The camera holds steady, with a slight handheld drift.

4. 15.2–18.8sFists up

   Photos to attach, in orderImage 1: The lead singerImage 2: The one who laughsImage 3: The sax player

   Still prompt

   Copy

   A medium-wide shot of three people performing together, seen from the front and framed from the desk up, so their faces are large and clear, in a cramped, cosy office corner turned into a stage. Tall wooden bookshelves crammed with old books, vinyl records, potted plants and little keepsakes cover the wall behind, a small wooden office desk stands in front with a plain black electronic keyboard on it, microphones on black stands, and warm light from desk lamps. None of it has any logo, print or writing on it: the book spines, the record sleeves and the keyboard are blank. The person in image 1, in their own clothes from the photo, sits in the middle behind the desk at a microphone on a stand, eyes open, smiling with lips closed, face in full view. The person in image 2, in their own clothes from the photo, stands behind them on the left of the frame, beaming, eyes open, face in full view. The person in image 3, in their own clothes from the photo, stands behind them on the right of the frame with a gold tenor saxophone hanging from a strap at their chest, beaming, eyes open, face in full view. Each face comes from that person's own photo alone, never a mix of the three: the one at the microphone has exactly the face, gender and age of the person in image 1. Exactly these three people are in the picture; nobody else is in the room.

   Motion prompt

   Copy

   The person at the microphone belts the last big note with their eyes closed, and all three raise a fist high in the air together on it, triumphant and overjoyed. Everyone stays in their place, the one in the middle seated at the desk. The camera holds steady, with a slight handheld drift.

Where it goes wrong

• Turn the faces toward the camera

  The concert films the laugh and the sax side-on. A picture model drawing a face side-on tends to invent a new one, so draw both close-ups in three-quarter view with the face toward the camera, and keep the turn to the lens small. Put only blurred shelves behind them: given the whole room, a picture model draws the room with the singer small in one corner of it.

• Give the laugh time to come

  Asked for a laugh, a video model laughs from the first frame. In the trend the singer holds the note for a couple of seconds and only then cracks up, so ask for the note first and the laugh after it.

• Check every face in the band shots

  In a picture of three, a picture model can lose one face and draw a stranger in its place, often keeping only the hair and the clothes. Draw the band before the song starts, eyes open and mouths closed, framed close enough that the faces are big, and compare each face with its photo before you animate: redraw any that changed.

• Nobody else in the room

  A room full of instruments is exactly where a picture model adds a drummer or a fourth singer you never asked for. Say how many people are in each still and that nobody else is in the room.

• Leave the logos and posters off

  The real room is covered in posters and stickers and the keyboard has a brand on it. Ask for blank book spines, a plain keyboard and no logo, print or writing anywhere: someone else's trademark has no place in your video.

• Only people who said yes

  Use your own photos or those of friends who agreed. The first versions starred real coaches and athletes; do not use celebrities, public figures, or anyone who has not agreed to be in the video: a realistic video of a real person made without their consent can hurt them, and platforms take it down.

• Label it as AI-generated

  Switch on TikTok's AI-generated content label before you post. A realistic clip of people performing is exactly the kind viewers ask about, and they trust a post that says so.