# Fancy cafe video generation and media

- Input: one photo of one adult (the user, or an adult who agreed), plus an optional second photo of another consenting adult. JPG, PNG or WebP, up to 10 MB. Clear front-facing face, ideally head to toe or head to knee, even light. Pets, cartoons and group photos are not supported.
- Any adult can play either role, whatever their gender, age or build.
- Roles: the first photo always plays the first-timer who sits on the table. The optional second photo plays the regular who walks in and sits on the bench; without it, a built-in, AI-generated regular appears. One or two photos cost the same one credit.
- What changes: face, hairstyle, hair color, skin tone, build, accessories and the colors and style of the clothing come from the photo; clothing details such as layers, shoes or sleeves can change.
- What is fixed: the minimalist concrete cafe, the bench and round wall tables, every action and its timing, the fixed camera and the original sound. The user writes no prompt and cannot choose another cafe or song.
- Scene (approximate): 0–2 s perched on the small wall table, sipping coffee; 2–4 s a regular sits on the bench and puts her cup on the table beside her; 4–7 s the first-timer notices; 7–9 s climbs down holding the coffee; 9–10 s puts the cup on the table; 10–12 s sits on the bench with a casual wave.
- Model: NanoAPI genjutsu-1.0 (motion control).
- Paid output: about 12 seconds, vertical 9:16, 720p MP4 with the original sound, no on-screen text, no watermark. Users add the "POV" caption themselves when posting. Any example on the home page is a real result generated from the photo(s) shown next to it; there is a one-photo example and a two-photo example, all made from AI-generated fictional adults.
- Sound: belongs to its rights holders and is not licensed by this site; use licensed music for ads or brand accounts.
- The instructions ask the model to keep the person's face, hair, skin tone and build, including while looking down at the cup and turning to climb off the table. Exact likeness is not guaranteed; check faces, hands and clothing.
- USD packs: 1 video $9.99, 3 videos $24.99, 10 videos $69.99; no subscription or free personal preview.
- Site photos: up to 7 days. Browser drafts: 24 hours. Finished videos: 30 days. Email links: 30 days. Unused credits do not expire.
- Confirmed generation failures return the attempt's credit once; this is not an automatic refund.

Independent service, not affiliated with TikTok, CapCut, ByteDance or the people in the original clip. Content is never published automatically.

Source: https://yourfirsttimeinafancycafe.com/
Support: support@yourfirsttimeinafancycafe.com