I Love the Smiths trend

It is the elevator scene from the 2009 film (500) Days of Summer remade with AI: one person stands in an office elevator with headphones on, the person next to them hears the music and says "I love the Smiths", has to say it again, sings a line of the song and walks out, and the first person is left stunned. Since early November 2026 people have been posting AI versions with other faces in the two parts. Oakgen's template puts the two people from your photos in it.

Yes. "I Love the Smiths", the "500 Days of Summer elevator scene", the "Tom and Summer" elevator meet-cute and "I said I love the Smiths" are names for the same trend, and many posts use the hashtag #ilovethesmithstrend. This template follows the full 24-second scene, from the headphones coming off to the walk-out.

The band is The Smiths and the song is "There Is a Light That Never Goes Out", from their 1986 album The Queen Is Dead. In the film it plays through the headphones, and the line the speaker sings, "To die by your side, such a heavenly way to die", is from its chorus. Some people search for the trend as the "There Is a Light That Never Goes Out AI trend".

The speaker says "I love the Smiths", the listener asks "Sorry?", and the speaker repeats "I said I love the Smiths" and says the listener has good taste in music. After a short surprised reply from the listener, the speaker sings a line, says "I love them" and walks out, and the listener mutters "Holy shit."

An AI-made fan version with look-alikes of two famous musicians in the elevator. This template is an unofficial fan-style format, not connected to the film, its studio, The Smiths or anyone shown, and neither look-alike is kept in your video.

Yes. The Listener and the Speaker each need a photo, because the motion guide replaces both people with grey silhouettes, so neither of them is kept.

Photo 1 is the Listener, on the left with the headphones, who stays in the elevator at the end. Photo 2 is the Speaker, on the right, who says "I love the Smiths" and walks out. To swap parts, swap the photos. Any pair works: two friends, a couple, coworkers or a person and a pet.

There is no gown or costume: each person wears the outfit, hair and accessories from their own photo. The template adds one prop, a plain pair of black over-ear headphones for the Listener, which come down around the neck early on.

Yes. Your video keeps the clip's original soundtrack, voices and music, whoever is in the photos. You do not record anything, and the voices are not changed to sound like the people in your photos.

The scene's dialogue, separated from the music, is sent to the video model with each part of the scene, so the lines are timed to the right face; the music itself is never sent. These are instructions to a model, so check the close-ups and re-run if the lips clearly drift.

Yes. Either part can be a dog, a cat or another pet: it keeps its own species, coat and markings and follows the same head turns and walk. The scene reads best when the Speaker is a person, because the Speaker has most of the lines.

Your own, or photos of people who agreed to be in the video. Do not upload photos of actors, musicians or anyone who has not consented, and label AI videos clearly when you share them.

24 seconds in 16:9 landscape, in two shots: a close two-shot in the elevator for about 20 seconds, then a wide shot as the doors open and the Speaker walks out.

No. It is the AI reference clip the trend comes from, used as the motion and timing reference, not an Oakgen result. Its two people are never reused.

4,939 credits per 720p video. The quote includes both photo preparations and the complete video. Check it before generating.