Make the I'm so sorry trend with one photo of you and your partner. Choose a scene, then create a 15-second vertical clip with environmental sound and instrumental music, without spoken audio.
1Add your photo
2Quality & length768p · 15s · 9:1660 credits
No subscription · Ready in about 3 minutes · Not charged if it fails
Only upload a photo of yourself and another consenting adult. Do not upload someone’s image without their permission.
From the Feed
Height Reversal is the fifth chip and the default; the four alternate scenes use one couple photo and different preset settings: a lakeside sunset, a football stadium, a city sidewalk at golden hour, or a bright stairwell. These four examples follow Height Reversal in chip order. Pick a scene that suits the photo and the joke you want to share. The generator makes one 15-second vertical clip with environmental sound and instrumental music, including a shrinking boyfriend video setup and a height reversal couple video option.
Make the Couple VideoThree Steps
Keep Height Reversal, the default, or choose Sunset Surprise, Stadium Switch, City Date, or Stairwell Shift. Read the scene description and pick the preset that fits the couple photo you plan to upload.
Select one clear photo showing you and another consenting adult together. Make sure both faces are visible. This page accepts one photo and offers preset scenes, so choose an image that works with one of the listed settings.
Create the 15-second 9:16 clip with environmental sound and instrumental music. After generation, add any captions or separate audio in your posting app; the generated clip has no human voice, and you cannot upload a song here.
Scene 01 · Sunset Surprise
Warm sunset reflections set the scene.
Sunset Surprise places the couple beside a lake, with warm reflections on the water and one person noticeably taller at the start. The preset supplies the lakeside scene for this I'm so sorry trend video; you cannot replace it with a custom location.
Scene 02 · Stadium Switch
Bright stadium lights frame the couple.
Stadium Switch specifies a couple in the stands of a brightly lit football stadium, with one person taller in the opening setup. Pick this scene for a sports setting; your uploaded photo supplies the couple, and the chip selects the stadium scene.
Scene 03 · City Date
Golden hour brings the sidewalk scene to life.
City Date shows the couple on a lively city sidewalk at golden hour, with one person clearly taller than the other. The urban setting gives the I'm so sorry trend a date-night look while keeping the height difference as the visual setup. This height reversal couple video uses a preset street scene rather than a lawn, lake, stadium, or indoor stairwell. The location is selected from the available presets.
Scene 04 · Stairwell Shift
A bright indoor setting keeps the couple in focus.
Stairwell Shift places the couple side by side in a bright indoor stairwell, with one person much taller than the other. The plain, enclosed setting keeps attention on the changing height relationship rather than an outdoor backdrop. Select the chip to make this version of the I'm so sorry trend. It is the last alternate scene in the preset list, and the scene cannot be rewritten with a custom prompt.
Straight Answers
The I'm so sorry trend page turns one couple photo and a preset scene into a short height-reversal video. Here are the practical limits before you upload.
The Trend Explained
The I'm so sorry trend is a couple-photo joke built around a height contrast: one person appears taller than the other in the visual setup. This couple photo trend video uses captions to set up the gag with a claim about a partner's height and end with an apology. This page makes a related visual clip from one photo of two consenting adults. You choose one of five scene chips, and MiniMax H3 generates a 15-second 9:16 video with environmental sound and instrumental music. The clip has no spoken voice, and you cannot upload your own song; add captions or a separate track when you post if you want them. The selected preset supplies the scene setup.
Upload one photo that shows both adults together, with their faces visible. The generator uses that image as the reference for the couple and creates the selected scene around them. This one photo relationship video uses a preset scene rather than a custom description, so choose an image that works with one of the available settings.
Choose Height Reversal, Sunset Surprise, Stadium Switch, City Date, or Stairwell Shift. Height Reversal is selected by default; the other four are the examples below. Each chip selects a preset scene, and the prompts depict a height difference, including a shrinking boyfriend video setup. The scene choices are fixed, so select the closest match instead of expecting a custom location field.
MiniMax H3 creates a 15-second vertical video with environmental sound and instrumental music. There is no human voice or spoken line, and you cannot upload a song to the generator. This AI couple photo animation turns the selected height contrast into a moving scene. If you want a particular trend audio or soundtrack, add it separately in the app where you publish the video.
Answers about the couple photo, preset scenes, video length, sound, and sharing.
Make the Couple VideoUpload one photo showing you and your partner, choose one of the five scene chips, and generate the clip. MiniMax H3 makes a 15-second vertical video from that photo and preset, creating an AI couple photo animation. Add your own captions after generation if you want to build the joke around an “I'm so sorry” reveal.
The clip turns a couple photo into a scene with a visible height contrast, following the selected preset. The default Height Reversal scene shows the couple together on a sunlit lawn in formal outfits, with one person visibly taller; it is used only when you select that chip. The generated video is 15 seconds and includes environmental sound and instrumental music, but no spoken voice.
Use one photo that shows both people together, and only upload images of yourself or adults who have agreed to be included. Choose a picture where both faces are visible so the couple is clear. The page accepts one image for each generation and does not combine multiple photos.
There are five preset chips: Height Reversal, Sunset Surprise, Stadium Switch, City Date, and Stairwell Shift. Height Reversal is selected by default. The other four scenes correspond to the examples on this page; each chip selects a scene, while the generated arrangement may vary.
No. This page lets you choose only from its scene chips and does not offer a custom prompt or location field. Select the closest preset: lawn, lakeside sunset, football stadium, city sidewalk, or indoor stairwell. The selected chip determines the scene used for the clip.
No. The generated clip includes environmental sound and instrumental music, but it has no human voice or spoken dialogue. You also cannot upload your own song. Add captions or choose separate audio in the app where you post if you want a specific line or soundtrack.
Each generated video is 15 seconds in a vertical 9:16 aspect ratio. The page does not offer a different duration or shape. That format keeps the couple scene tall on screen, and you can add captions after generation in the app where you share it.
A chat assistant can help draft captions or suggest a posting sequence, but this page generates the moving video from your photo. Upload one couple image, select a preset chip, and create the 15-second clip. The generated audio has no voice, so captions and any specific song must be added separately.
One 15-second clip costs 60 credits. You can also choose a one-time pack: 1 clip for $9.99, 3 clips for $19.99, or 5 clips for $29.99. A monthly plan starts at $12.99 and includes 400 credits. Check the pricing page for current plan details.
Videos made without a subscription can appear in the public Explore feed on Ricebowl AI. Consider that before uploading a photo, and get permission from the other adult shown in it. Only use an image you are comfortable having included in a public feed.
When posting, you can add a short caption to introduce the height difference and an apology line to frame the joke. These are optional captions you add yourself; the generated clip includes no spoken voice. For more caption and creation guidance, read the [How to Do the AI Trend guide](/hub/how-to-do-the-ai-trend).
Explore More
I'm So Sorry Trend Video
Pick one of five scene chips and make a 15-second vertical couple clip with environmental sound and instrumental music.
Make the Couple VideoOne photo • 9:16 vertical • Instrumental sound
Turn One Couple Photo Into an
Make the Couple Video