Category
AI video effects: the effects going around on social media, made from a selfie
The tilting world, the creature at your back, the stadium chanting your name, the vanishing act, the clones: these effects circulate on TikTok and Instagram, and each one has a ready-made workflow here. A selfie or a phone clip goes into a Media node, a video model does the rest.
Every page shows the real canvas, its instructions and its actual renders, with the cost in credits before you click. The face stays yours from one variant to the next: that is the point these workflows were built to hold.
What you can do here
- Recreate an effect seen on social media without editing software
- Keep your own face in a generated video
- Get two or three variants of the same effect to choose from
- Start from a selfie when you have no video
- Know the exact price before generating
The tools in this category 19 tools
The lead of the music video
One clip, one photo, and you are the one in front of the crowd.
A reference clip gives the movement, the camera and the cuts; your photo gives the lead. Two Seedance 2.5 nodes render the clip with you in the middle of a crowd you describe. The real workflow is visible here without an account.
Interactive demoThe tilting world
The room turns, you do not
One selfie and two Seedance 2.5 nodes: you stand in the middle of a café or a bedroom, and the whole room turns around you while you stay upright. The real workflow, with both renders, is visible here without an account.
Interactive demoThe crowd chants your name
Your name on the big screen
One selfie and two Seedance 2.5 nodes: your face on the giant screen of a stadium or a concert, and the crowd chanting your name. The real workflow, with both renders, is visible here without an account.
Interactive demoThe creature behind you
Do not turn around
One selfie and two Seedance 2.5 nodes: you face the camera, a colossal creature reveals itself behind you, a dragon in the city or a beast in the mist. The real workflow, with both renders, is visible here without an account.
Interactive demoThe eye dive
Straight through your pupil
One selfie and two Seedance 2.5 nodes: extreme close-up on your eye, then the camera passes through the pupil and comes out in a city or an ocean. The real workflow, with both renders, is visible here without an account.
Interactive demoThe zoom from space
From orbit to your street
One selfie is enough: two Seedance 2.5 nodes generate the continuous descent from Earth orbit down to you, in the street or on a rooftop. The real workflow, with both renders, is visible here without an account.
Interactive demoThe outfit walk
One stride, one outfit
One selfie and two Seedance 2.5 nodes: you walk toward the camera and your outfit changes with every step, through the seasons or across countries. The real workflow, with both renders, is visible here without an account.
Interactive demoYour future job
One selfie, two lives
Your selfie goes to two Wan 3.0 nodes that show you in two jobs: an astronaut on a spacewalk, a chef in the middle of service. You pick the job, it is not drawn at random. Workflow visible here, no account needed.
Interactive demoStop time
The world freezes, you do not
Your phone clip goes to three Wan 3.0 nodes that freeze everything else: the crowd mid step, the cafe terrace, a flock of pigeons suspended in mid air. The whole workflow is visible here without an account.
Interactive demoBecome a giant
Your selfie, building sized
Your selfie goes to three Wan 3.0 nodes that make you the size of a building in a real street: you step over the traffic, you sit on a rooftop, you lift a bus between two fingers.
Interactive demoClone yourself on video
You, by the dozen
Your phone clip goes to three Wan 3.0 nodes that multiply you: five copies repeating your gesture a beat late, copies at every scale, a whole crowd of you.
Interactive demoVanish
Three ways to disappear
Your phone clip goes to three Wan 3.0 nodes that make you disappear three ways: the clothes collapse on the floor, the body turns to dust, you reappear one step away.
Interactive demoDancing photo
A video's moves on your photo
A dance video and a full-length photo: Kling 3.0 Motion Control has the person in the photo replay the choreography, face and outfit kept. The same dance on two characters. The whole workflow is visible without an account.
Interactive demoYou inside a video game
Three worlds, the same person
A clip of you shot on a phone enters the canvas, and Wan 3.0 renders the same person, the same move, inside a video game level. Temple ruins, cube world, neon rooftop with the HUD: the whole workflow is visible without an account, with all three renders.
Interactive demoAI meme video
Memes come alive in your street
Two selfies, a photo of your street and your meme images: a 30-second vlog in one single take where memes sip coffee at the terrace and cross at the light behind you. The full workflow is visible here without an account.
Interactive demoASMR squish effect
The rigid object that squashes like jelly
One photo of an object is enough: the sneaker squishes like memory foam, in extreme close-up, with the compression sound generated inside the video. The full workflow is visible here without an account.
Interactive demoFashion transition
One outfit melts, the new one takes its place
The outfit melts from top to bottom into glossy liquid, and the new one solidifies in its place. The transition of fashion reels, computed between a first and a last frame. Full demo visible without an account.
Interactive demoPut yourself in
Three photos of you, and you are in the shot
Three photos of you are enough to end up pressed against a rock while a cyclops hunts for you. The Camera node shoots the still and the video through the same lens.
Interactive demoManga fight
A fight played on stage, filmed from the crowd
A manga fight played by real actors on a vast stage, filmed from the crowd, phones up and pyrotechnics firing. Everything is photographic, the manga lives in the costumes.
Interactive demoFrequently asked questions
Do I need a video, or is a photo enough?
Most effects start from a single selfie: the model generates the movement. Those that replay your own gesture, freeze time, clone yourself, disappear, need a filmed clip of a few seconds.
Does the face stay recognisable?
Yes, that is what the instructions of these workflows lock. The renders on each page are the demo's own, generated from a single selfie, and they show what the model keeps and what it approximates.