Remove the Background of a Video with AI
Remove Background cuts a photo out; Remove Video Background does the same to a clip, frame by frame, with the hair, the fabric and the shadows handled by the model rather than a green screen. A Model 360, a UGC clip or your own shoot comes back as the subject alone, on the background you choose: transparent for your editor, white for a product page, black or green for a composite.
Updated 2 October 2026
- 1Upload the video
- 2Choose the background
- 3Generate
How it works
Upload the video
A clip from the studio or your own file. The subject can be a person or a product; no green screen needed.
Choose the background
Transparent gives a .webm file with an alpha channel, the format editing tools and Chrome read; White, Black or Green give an mp4 that plays everywhere, Safari included.
Generate
The clip keeps its length, its shape and its sound. It is priced by the second of the video you hand in.
Frequently asked questions
Which background should I choose?+
Transparent if the clip goes into an editor or over another background. White if it goes straight to a product page or social. Green if your editor keys on a colour. Note that a transparent .webm shows a black background in Safari, that is the browser, not the file.
Does it work on hair and moving fabric?+
Yes. The model reads soft edges, hair and fabric in motion, which is where a manual mask takes the longest.
How is it priced?+
By the second of the video you upload, the length of the clip is read from the file before the job starts, and a clip that cannot be read is refused rather than charged.
Which file do I get?+
A .webm with an alpha channel for Transparent; an mp4 for White, Black or Green.
Does it work on products, not only people?+
Yes. The subject can be a person or a product.
Do I need a green screen?+
No. The model handles hair, fabric and shadows from ordinary footage.
Try it yourself
Everything on this page was made in the studio. Your first designs are minutes away.
Open the studioRelated features
- Change the Background of a Video with AIPut the model of a video somewhere else, a street, a studio, a beach, with a sentence. The person, the outfit and the movement stay; the setting, the light and the shadows change.
- AI Fashion Reels: Trending Outfit Transition VideosMake trending AI fashion reels from one photo: outfit transitions as people pass, as your model walks, at a finger snap, after a jump, and more. 10-second 9:16 videos for Reels, TikTok and Shorts.
- AI Fashion Video from Reference ImagesPut your model, your garment and a place into one video: add up to three reference pictures, describe the scene, and get a 5 to 15 second fashion clip in 9:16, 1:1 or 16:9.
- Fashion Reel Templates & AI Motion DesignEighteen Motion Design templates for fashion reels: drop your photos or clips, edit the words, render a 10-second video in 9:16, 4:5, 1:1 or 16:9. One credit, every plan.
- Edit a Video with AIChange a video with a sentence, in your own words: the light, the setting, the mood, a garment. The instruction goes to the model as written; the clip keeps its length and its sound.
- AI Background Remover for Fashion and Product PhotosCut the subject out of any fashion or product photo and keep it on a transparent background: a model, a garment, a bag, a shoe, in one click, ready for your shop or your layouts.
- Edit the Outfit in a Video with AIChange the clothing in a video with a sentence: a new colour, another print, a different garment. The person, the movement and the setting stay as filmed.
- Model 360: a full turn from a front and a back photoTwo photos of your model, front and back, become a full-turn video: the model turns on the spot, or the camera circles around them. Every detail of the outfit kept, from every side.
- Reframe a Video to Any Format with AITurn a landscape clip into a vertical one, or a vertical into a square, without cropping: the subject is recentred and the missing edges are generated. One clip, every channel.
- Swap the Model in a Video with AIAnother person in the same video: give a photo of the new model, and the outfit, the movement and the setting stay exactly as filmed. One shoot, several faces.