Two photos, one tiny table

First time in a fancy cafe AI video generator

In the first time in a fancy cafe video, one person sits on top of the little metal table without realising it is a table, while someone effortlessly cool sits down beside them. Add two photos and get that awkward café moment in ten seconds of vertical video.

Seedance 2.0 Mini · 480p · 10 seconds · 9:16 · 200 credits

A little inspiration

What it makes

A few seconds. A whole new scene. Explore the details that give this idea its character.

480p · 10s · 9:16
01

Perched on the table

The first-timer sits on the tiny table with a coffee.

480p · 10s · 9:16
02

The calm regular

Someone walks in and sits on the ledge like it is nothing.

480p · 10s · 9:16
03

The realisation

The first-timer works out which one was the table.

480p · 10s · 9:16
04

Acting casual

Both sit side by side and nobody mentions it.

Make my first time in a fancy cafe video

Made for your next idea

A simpler way to make something memorable

Pay for the take

See the credit cost before you generate. Failed generations are refunded.

One credit balance

Use your credits across the creative tools in your account.

Room for a longer story

Change duration, resolution and framing without leaving the editor.

Choose your model

Try available models with the same photos. Pricing updates with your settings.

Make my first time in a fancy cafe video

The short answer

First time in a fancy cafe AI video generator

You sit on the tiny table, the regular sits on the ledge. Two photos, ten seconds, vertical. In the first time in a fancy cafe video, one person sits on top of the little metal table without realising it is a table, while someone effortlessly cool sits down beside them. Add two photos and get that awkward café moment in ten seconds of vertical video.

Open the video studio

What the first time in a fancy cafe video is

The first time in a fancy cafe video is a short comedy skit set in a minimalist concrete café. One person perches on top of a small wall-mounted metal table without realising it is a table. Someone stylish walks in, puts a coffee on the neighbouring table and sits on the ledge with total calm. The first-timer slowly works it out, climbs down and sits beside them pretending nothing happened. The humour is the awkwardness of not knowing the unwritten rules of a fashionable place. This page is an independent, original take on that kind of skit and is not affiliated with the creators of any original clip.

What to expect from the result

Every generation is a new model output. The timing of the realisation, how the first-timer climbs down and how the cups sit on the tables can differ between runs, and small objects are the hardest detail for a video model to keep exact. If a run misses the joke, generate again with the same photos. Watch the clip at full size with sound on before posting.

release.first-time-in-a-fancy-cafe.problemTitle

release.first-time-in-a-fancy-cafe.problemBody

release.first-time-in-a-fancy-cafe.highlights.0.title

release.first-time-in-a-fancy-cafe.highlights.0.body

release.first-time-in-a-fancy-cafe.highlights.1.title

release.first-time-in-a-fancy-cafe.highlights.1.body

release.first-time-in-a-fancy-cafe.highlights.2.title

release.first-time-in-a-fancy-cafe.highlights.2.body

release.first-time-in-a-fancy-cafe.highlights.3.title

release.first-time-in-a-fancy-cafe.highlights.3.body

Three simple steps

From photo to finished clip

01

Upload two photos

Put the cool regular in slot one and the confused first-timer in slot two. Sharp, well-lit portraits where each face is clearly visible work best.

Pick two photos the model can use. There are two photo slots. Use a sharp, well-lit picture of each person where the face is large and looks toward the camera. A head-and-shoulders photo works well. Put the person who stays calm in slot one and the person who sits on the table in slot two, and use the swap button if you mixed them up. Avoid group photos, because each slot should show one person.

02

Generate the 10 seconds

The concrete café, the table mix-up and the camera are fixed, so every run lands on the same awkward joke with your two faces.

Cost and settings. The default is a ten-second 480p vertical clip, which is 200 credits at 20 credits per second. The settings panel under the uploaders lets you change length, resolution and model, and the credit estimate beside the generate button updates before you confirm. Failed jobs return their credits automatically.

03

Download and post

Save the vertical MP4 and post it to TikTok, Reels or Shorts. Add a track you are allowed to use in the app if you want music.

Find your pace

Give your story room to move

Start with the default length for this scene. Available durations and the final credit estimate depend on the model and settings you choose in the editor.

Sound and music

The generation asks for quiet café ambience and footsteps, not a commercial song. The result is not guaranteed to match any particular track. If you want the sound people use for this trend, download the MP4 and add a track you are allowed to use inside the platform you post to.

LengthA good fit for
4 secondsOne clear gesture, reveal or visual punchline.
8 secondsA small sequence with space for an emotional turn.
10 secondsScene defaultAn unhurried moment, with more time for movement.

These are creative pacing suggestions. Check the editor for the lengths supported by your selected model. A longer clip can give an action more time to unfold, but it does not guarantee a better likeness or a cleaner transition. Choose the smallest format that gives your idea enough space, then review the complete result before deciding whether another take would be useful.

An open creative starting point

The direction behind the scene

This is the prepared prompt for this feature. Use it as a starting point, or add an optional idea in the editor to make the scene your own. Your reference photos guide the cast; the model interprets the movement and atmosphere.

first time in a fancy cafe AI video
Vertical clip with the two consenting adults from the reference photos. Setting: a minimalist concrete café with a raw grey concrete wall, a long concrete ledge along it, and small round stainless-steel pedestal tables mounted to the wall on a curved metal arm. The second person, the first-timer, wears a cream short-sleeved shirt, black trousers and white sneakers and is perched cross-legged on top of one of the little round metal tables, holding a paper coffee cup in both hands, looking nervous and confused about how this café works. The first person, the calm regular, wears a dark oversized suit and black boots, walks in from the right, sets a paper coffee cup on the neighbouring pedestal table, sits down on the concrete ledge and looks away with cool, unbothered calm. The first-timer glances sideways, realises he or she has been sitting on the table, climbs down clumsily with the cup, puts the cup on the table and sits on the ledge next to the regular, trying to act casual and staring straight ahead. Locked-off medium shot at eye level, soft diffused daylight, quiet café ambience with faint footsteps and no music. Keep both faces consistent with their reference photos. No on-screen text, no captions, no logos, no watermark, no social media icons.

Thoughtful casting

Start with the right photos

Choose your own images or photos you have permission to use. A clear face, even light and a simple crop give the model a useful reference. Make sure everyone pictured is comfortable with the fictional scene and with the way you plan to share it.

What this template makes

The scene is fixed on purpose so you do not have to write a prompt: a raw concrete café, small round pedestal tables on the wall, a first-timer in a cream shirt perched on one, a calm regular in a dark oversized suit who sets a cup down and sits on the ledge, and the realisation. It runs ten seconds vertically at 480p and asks for quiet café ambience, not a song. The setting and the outfits are the same every time. If you want a different venue or clothing, use the open video studio and describe it yourself.

release.first-time-in-a-fancy-cafe.audienceTitle

release.first-time-in-a-fancy-cafe.audienceBody

Before you upload

Your photos. Your decisions.

01

Choose deliberately

Selecting a photo starts its upload. Check the file and your permission to use it before choosing it in the editor. The image preview helps you confirm which reference you selected; it does not mean the image remains only on your device.

02

Understand the process

Creating a video requires sending the reference images and scene direction through the generation service and its selected provider. Review the privacy policy for information about how uploads, generated files and account information are handled.

03

Share with context

Review the entire result before you download or publish it. Let the people pictured see the clip, respect their preferences, and make the fictional, AI-generated nature of the scene clear when viewers might otherwise mistake it for a real event.

Share it with context

This is an AI-generated scene made from reference photos, not footage of a real place. Only use photos of yourself or people who agreed to take part, and label the clip as AI-generated when it could be mistaken for real footage.

Privacy

Pricing

Subscribe for monthly credits, or buy a one-time credit pack.

Basic

$9.90/mo

For trying ideas and short clips

  • 450 credits / month
  • ≈2 Seedance Mini 8s clips / month

Pro

Popular
$29.90/mo

For creators publishing every week

  • 1,500 credits / month
  • ≈9 Seedance Mini 8s clips / month

Max

$79.90/mo

For high-volume production

  • 4,700 credits / month
  • ≈29 Seedance Mini 8s clips / month

Questions, answered

A few things worth knowing

What is the first time in a fancy cafe trend?

A short comedy skit: one person sits on a tiny wall-mounted table in a minimalist café without realising it is a table, while a stylish stranger sits down calmly beside them. It spreads as the awkward first-timer moment.

How do I make a first time in a fancy cafe video with AI?

Upload two photos, one for the calm regular and one for the first-timer, press generate and download the ten-second vertical MP4. The café and the beats are prepared for you, so there is no prompt to write.

Which photo goes in which slot?

Slot one is the calm regular who sits on the ledge. Slot two is the first-timer who sits on the table. If you mixed them up, use the swap button before generating.

Can I use my friend or my partner?

Yes, as long as they agreed to appear in the video. Pick a sharp photo of each where the face is clearly visible.

Can I change the café or the outfits?

Not on this page: the concrete café and the outfits are the same every time. Open the video studio if you want to write a different venue or clothing.

What does it cost?

Ten seconds at 480p is 200 credits at the default rate of 20 credits per second. The exact amount is shown on the generate button before you confirm.

Does the video include music?

It includes generated café ambience, not a commercial song. Add a track you have the right to use after downloading the MP4.

Do you keep my photos?

Choosing a photo uploads it so the video service can use it as a reference. See the privacy policy for storage and provider handling.

A portrait that gives the model room to work

Choose a sharp image with one clearly visible face. Avoid sunglasses, heavy filters and cropped foreheads. Keep some shoulder and background space so movement has room to develop. Use fictional characters or people who have agreed to the transformation.

Review more than the first frame

Play the full clip. Check the face, hands, clothing and background through the middle and ending. A good opening image does not guarantee continuity. Change one setting at a time when making another take.

Prepare the video for sharing

Download the finished MP4 and check it in your editor. Add captions where they do not cover faces. If you add music, use audio you own or are allowed to use on the destination platform. Generated audio does not include a licensed trend soundtrack.

Keep exploring

Where will your next idea take you?

Explore more

Find another story for your photos, compare the models, or build a scene of your own.