IVE Looks Can Kill AI: The Trio Dance Challenge, Starring You
You take the centre spot in the Looks Can Kill trio, from the wide arm opening to the hands-on-face finish. One photo is enough, and two friends can join.
Updated : Page published.
1Add up to 3 photos, one person each
Photo 1 · You, in the centre spot
What you'll get
Front-facing, well-lit selfies work best. One face per photo.
2Place
3Choose quality
By generating you confirm you have permission to use the people in your photos. Terms
No subscription needed · Ready in about 3 minutes · Failed renders are free
The IVE Looks Can Kill AI dance is a 15-second clip of you, with up to two friends, doing the chorus of the Looks Can Kill dance challenge IVE started in October 2026, with the song on it; videosi makes it from one photo of you.
- Fast facts
- First seen
- Stage
- Just starting
- Started on
- TikTok
- Sound
- Looks Can Kill — IVE
- Meaning
- The IVE Looks Can Kill trend is the dance challenge set to the chorus of IVE's October 2026 single Looks Can Kill, and its AI version puts you, and up to two friends, into the trio routine.
- Related trends
- Jisoo Addicted Dance AI, BABYMONSTER Deserve AI, KATSEYE Animal Dance AI, AI Dance
Page updates
- November 3, 2026 — Page published.
The IVE Looks Can Kill AI prompt and model
IVE Looks Can Kill AI is made with Seedance 2.0 / 2.5 (you pick the tier) by ByteDance. The prompt behind it has 5 parts, and the timing is what makes or breaks it.
- Model
- Seedance 2.0 / 2.5 (you pick the tier)
- Mode
- Photo + motion reference to video
- Length
- 15 seconds, 9:16 or 16:9
- Input
- 1–3 photos
- Centre swap The instruction replaces the centre dancer outright with you, so the model edits the clip instead of only borrowing from your photo.
- Side spots The left and right dancers become your friends' photos, or ordinary stand-ins in plain clothes when you upload only one photo.
- What must go The pink, red and lavender vinyl outfits and each original hairstyle are named, because anything unnamed tends to stay.
- Place Either the original stage with the light-bulb sign, or one new place that every frame moves into.
- Rules Three adult dancers, no celebrity face, one face per person, five fingers, no lip-sync, no added text or watermark.
Replace the woman in the centre of Video 1, in the hot-pink vinyl halter crop top and hot-pink vinyl flared trousers, with the person from your photo.…
Why it goes wrong when you do it yourself
- With three dancers in a row, a plain prompt often copies one face onto two or three people.
- Unless the vinyl outfits are named, the shiny pink or red trousers can stay on your body.
- In the last seconds all three run up to the lens, which is where faces drift toward the original singers.
- Asked only in words, a video model invents generic K-pop moves instead of this chorus routine.
IVE Looks Can Kill AI examples
How to make your IVE Looks Can Kill AI video
Upload your photo
Add one sharp photo of you for the centre spot. Add one or two friends' photos for the left and right spots if you like.
Pick a place
Keep the original stage with the light-bulb sign, or move the trio to a dance studio or a street at dusk.
Generate
Press Generate. The 15-second trio video is rendered for you, with no prompt to write.
Post it
Download the MP4. The Looks Can Kill sound is already on it, so you can post it to TikTok or Reels, labelled as AI.
What is the IVE Looks Can Kill AI trend?
Updated · videosi is an independent tool. It is not affiliated with TikTok, Instagram, YouTube, or with the owners of any trend, song, game or brand named on its pages.
The Looks Can Kill dance comes from Looks Can Kill, the title track of the IVE mini-album of the same name. IVE posted the challenge on its official accounts on 12 October 2026, a week before the song was pre-released on 19 October; the mini-album followed on 26 October 2026.
Korean press call the point move the "sniper dance", a hand-gun gesture, and by 28 October 2026 the challenge videos had passed 100 million combined views. Other idols, actors and dancers joined in, and IVE posted more versions: a trio clip on a dark stage in pink, red and lavender vinyl outfits, posted on 20 October, had 2.8 million views when we checked on 3 November 2026.
Fan covers in practice rooms, offices, streets and bedrooms followed, mostly dancing the "Looks can kill, we're so lethal" chorus. The first AI versions we found were posted on 22 and 24 October 2026, and our trend radar marked the AI search terms as just emerging on 27 October.
The AI version on videosi puts you in the centre spot of that trio clip and, if you add photos, two friends on the left and right. You get a 15-second video of the chorus with the same moves and the song already on it. videosi is independent and is not connected with IVE or Starship Entertainment.
IVE Looks Can Kill AI: shot by shot
- 0–1.5 s
Wide opening
You stand close to the camera with both arms thrown wide, then drop back into the line of three.
- 1.5–4.5 s
Hands in a line
All three dance in a row, quick hand moves at chest height on the "da-da-da" while the lights flash blue.
- 4.5–6.5 s
Centre step
You step forward alone with a hip sway and a hair flip while the side dancers keep the beat.
- 6.5–12 s
Sweeps and points
Arm sweeps overhead, a point up and out, then steps back into formation for the last line.
- 12–15 s
Hands-on-face finish
All three run up to the lens and frame their faces with their hands, then wave.
Tips for a better result
Show your outfit
A photo from head to at least the hips gives the model your clothes for the full-body stage shots.
Keep faces clear
Use sharp, well-lit photos with no sunglasses, hat or hair across the face, because all three run up close at the end.
One person per photo
Each photo should show only the person for that spot. Group photos make the model guess who goes where.
Fitted clothes read best
Tops and trousers that show the arms and legs keep the moves clear. Long coats and big bags hide them.
Good to know before you make a IVE Looks Can Kill AI video
- The video always shows three adult dancers. Without the extra photos, the left and right dancers are ordinary strangers, not IVE members and not anyone you know.
- The moves come from one 15-second trio clip. The examples on this page are real solo covers by other people, not videosi renders, so your result is the trio version, not a solo.
- The song is on the clip, but there is no lip-sync, and fast hand moves near the face can come out soft. This effect has not been test-rendered yet, including the studio and street places.
- videosi is independent and is not connected with IVE or Starship Entertainment. The song remains the property of its owners, so a platform may mute or limit a repost.
IVE Looks Can Kill AI: questions
What is the IVE Looks Can Kill AI dance trend?
The IVE Looks Can Kill AI dance trend puts you into the dance challenge IVE started on 12 October 2026 for its single Looks Can Kill. videosi makes a 15-second version from one photo of you, in the centre of a three-person line-up, with the same chorus moves and the song on it.
What does Looks Can Kill mean?
Looks Can Kill is the title track of the IVE mini-album released on 26 October 2026, and the trend is the dance challenge set to its "Looks can kill, we're so lethal" chorus. The phrase means a glance is powerful enough to knock someone out, which the hand-gun "sniper dance" move acts out. On videosi the IVE Looks Can Kill AI dance page turns that challenge into a 15-second video of you.
What song is used in the Looks Can Kill dance videos?
The song is Looks Can Kill by IVE, pre-released on 19 October 2026, and videosi adds the same 15 seconds of its chorus from the official trio clip to every IVE Looks Can Kill AI video. The sound is mixed in after the render, so nobody lip-syncs.
How do I make the IVE Looks Can Kill AI dance from a photo?
To make the IVE Looks Can Kill AI dance on videosi, upload one photo of yourself, add up to two friends' photos if you want, pick one of 3 places and press Generate. You get a 15-second trio video with the song already on it. There is no prompt to write and no choreography to learn.
Can I do the Looks Can Kill dance alone?
Yes, the videosi IVE Looks Can Kill AI dance works with one photo: you take the centre spot and two ordinary stand-in dancers fill the left and right spots for all 15 seconds. To dance it with friends, add their photos as Photo 2 and Photo 3. The result is always a trio, never a solo.
Is there an IVE Looks Can Kill AI generator or website?
Yes, videosi has an IVE Looks Can Kill AI generator on this page: one to three photos in, a 15-second dance video out, with no prompt and no app to install. It works in a phone browser. videosi is independent and is not connected with IVE or Starship Entertainment.
Is there a TikTok filter or CapCut template for the Looks Can Kill dance?
You do not need a TikTok filter or CapCut template for the IVE Looks Can Kill AI video on videosi, because your photo gives you the finished 15-second clip. As of 3 November 2026 we had not found a widely used template for this trend, and we have not tested any. The videosi file is an ordinary MP4.
What AI model and prompt make the IVE Looks Can Kill AI video?
videosi makes the IVE Looks Can Kill AI video with ByteDance's Seedance 2.0 or 2.5, and you pick the tier. A 15-second official trio clip guides the moves while your photos replace all three dancers. The prompt names each original outfit and hairstyle to remove, which plain prompts in other tools tend to miss.
How much does the IVE Looks Can Kill AI video cost, and is it free?
The IVE Looks Can Kill AI video on videosi is not free: there is no free generation for this effect. A 15-second video on Standard at 720p is 13 credits, and an account's first video costs 10. Better models and higher resolutions cost more. Credit packs start at $6.99 for 10 credits and never expire. A failed render returns its credits automatically.
Will the AI make me look like an IVE member?
No, the videosi IVE Looks Can Kill AI dance keeps your own face, hair and clothes in all 15 seconds and does not copy any member's look or vinyl outfit. Nobody in the result keeps the face of an IVE member. If yours does not look like you, use a sharper, well-lit photo with no sunglasses or hat and try again.
Can I use someone else's photo?
You can use someone else's photo on the videosi IVE Looks Can Kill AI page only if they are an adult and have agreed to it. The 15-second video shows three friends dancing side by side. Do not upload photos of children or of people who have not agreed, and label the result as AI when you post it.
Can I make the Looks Can Kill dance with ChatGPT, Sora, Veo or Kling?
You can try the Looks Can Kill dance in general video models, but you would have to supply the clip and the wording yourself, while the videosi IVE Looks Can Kill AI page already includes the 15-second reference and sound. Described only in words, a three-person routine usually comes out with invented moves or the same face on several dancers.
Is the Looks Can Kill dance still trending?
As of 3 November 2026 the Looks Can Kill dance challenge is still being posted, and its AI versions, like the one on videosi, are just emerging: our trend radar marked the AI search terms on 27 October 2026. The challenge itself started on 12 October and passed 100 million combined views by 28 October, and new fan covers were still appearing on 2 November.
Trending this week
All trends this week
Make your IVE Looks Can Kill AI video
Upload two photos and press Generate. 13 credits, refunded if it fails.
Get the next trend first
One email when new trends land on videosi, about once a week. Unsubscribe in one click.
See videosi first on Google
Add videosi as a preferred source and our trend pages show up first in your Top Stories and AI answers on Google.