King Jin AI Trend: How It Works and How to Make One

By videosi team · Published 2026-11-14

The King Jin AI trend is a CapCut template, spread on TikTok from around 12 November 2026, that turns one photo into a 10-second street-style entrance. You can use the template inside CapCut, or upload a photo to the King Jin AI trend page on videosi and get the same five-shot video without the app.

This guide answers the questions people ask once they have seen the clip: how the template flow works, why results differ, what each shot shows, how it differs from the tiger-fight clips, and what to check before you post.

Key takeaways

In this guide

How does the template flow work in CapCut?

The earliest posts we found were screen-recorded tutorials with Burmese captions. They follow one pattern: open a TikTok post that carries the template, tap through to CapCut, pick a photo from your gallery and let the template fill the scene. One of those tutorials had passed 1.1 million plays by 14 November 2026, and Vietnamese creators posted their own results the day after.

The template's scene is fixed. You choose the photo and CapCut places you into the same street, corridor and skyline as everyone else. That is why the videos look so alike, and also why the photo you pick matters so much. The tutorials we checked show a template credited to a creator named GG-Bond, but we could not confirm that this is the original maker, so treat that credit as a lead rather than a fact.

What does the scene show, shot by shot?

The full clip runs 10 seconds and has five beats.

The sound used in most posts is the TikTok sound KIAT JUD DAY HARDTEKK (TikTok Version). Its artist is not verified. The lip movement in the clip does not match a song, so the audio works as a backing track rather than something you appear to sing.

Where does the name King Jin come from?

We do not know. King Jin is the label people put on the template, and posts describe it as a powerful-entrance effect. We could not confirm who "Jin" is, whether it refers to a person, a character or a song, or who first used the name. As of 14 November 2026 it works as a handle for the template and nothing more, so be wary of any article that states a confident origin story.

How is it different from the tiger-fight clips?

Many Burmese captions on King Jin tutorials talk about hitting a tiger. That confuses people, because the videos attached to those captions show the night-street lollipop entrance, a blue corridor and a skyline, not a fight. There is a separate tiger-fight AI trend going around in November 2026, and we have not confirmed any link between the two.

The practical difference is simple. If you want a street entrance with a lollipop, a corridor walk and a skyline close-up, that is King Jin, and it is what the King Jin AI trend page makes. If you want a tiger-fight clip, this is a different effect. Check the video itself, not the caption, before you search for a tutorial.

Why do results look so different between people?

The scene is the same for everyone, so the difference comes from the input. Three things matter most.

With AI generation, each render is a fresh generation of the clip, so two runs on the same photo can differ slightly. If the face drifts or the lollipop looks wrong, run it again rather than editing around it.

How do I get a better photo for it?

Use one sharp, front-facing photo, from the waist up, with even light on your face. Avoid sunglasses, hats and masks. A photo taken near a window or outdoors in soft daylight tends to beat a flash photo in a dark room.

Keep the background plain if you can. The template replaces the star of the clip with you, and a cluttered photo gives the model more to carry over by mistake. Crop out other people, since the scene already has its own crowd of bowing men. If you have two good photos, try both: it is cheaper to compare results than to guess which one will work.

What is the do-it-yourself AI route, and how does videosi compare?

The DIY route is to use a general image-to-video model yourself. You write a prompt for each shot, generate five short clips, keep the face consistent across them, cut them together, and add the sound. It works, but most of the effort goes into keeping the same face and timing across five shots, and it takes several tries.

videosi skips that. It renders the King Jin scene with ByteDance's Seedance 2.0 or 2.5 (you pick the tier), using the 10-second template clip as a motion reference and your photo for the face. The street, corridor, skyline and timing are built in, and the original sound is added after rendering. You choose only the photo and the format: 9:16, 1:1 or 16:9. The prompt is built in, and we do not publish it in full. The trade-off is that the scene is fixed: if you want a different story, the DIY route gives you more freedom.

What does a video cost on videosi?

A 10-second King Jin video is 10 credits on the Standard model at 720p; higher tiers cost more. There is no free tier, credits do not expire, and a failed render returns its credits. The Single pack is $8.90 for 10 credits, and the Trio Pack is $17.99 for 30 credits. Plans and larger packs are listed on the pricing page.

How do I post it with an AI label?

TikTok allows AI-generated videos when they are labeled. When you post, turn on the AI-generated content label in the post settings before you publish. Nothing in the King Jin video is filmed: the street, the corridor and the skyline are generated, and the bowing men are not real people, so the label is accurate and expected.

The videosi video has no watermark, so the label is your job. A short line in the caption, such as "made with AI from one photo", also helps viewers who do not see the label. You can keep the trend's original sound, or swap the track in TikTok if you prefer a different one.

Is it safe to upload photos of other people?

Use your own photo, or a photo of a friend who has agreed. The template is built around a person on a street, so it is not made for pets. videosi does not allow photos of minors, or content that puts two real people together in intimate scenes.

Beyond the rules, a good habit is to show the person the finished clip before you post it. A photo of someone else turned into a "powerful entrance" video can be funny to you and awkward to them, and the AI label does not replace asking.

How long do trends like this last?

Nobody can say for King Jin yet. The first posts appeared around 12 November 2026, and by 14 November one tutorial had passed 1.1 million plays, which puts the trend in the emerging stage. Template trends can grow for weeks or fade within days, and a trend that spreads through a single template link depends on creators keeping that link alive.

If you want in, the cheap move is to post early, while the sound and template are still new to your followers. The King Jin AI trend page is updated as the numbers change, so check it before you plan a longer series around the effect.

AI body swap guides

Have the original clip? Swap yourself into it with AI body swap, or read on:

King Jin AI Trend: The King Jin Video, Starring You

The King Jin AI trend is a 10-second CapCut template video in which a stylish person stands on a night street with men bowing around them, takes out a lollipop and walks off through a blue corridor to a skyline close-up; videosi makes it from one photo of you.

Make yours

Trending this week

All trends this week