The model is the easy part. What building Dantiva taught me
Dantiva turns a photo into a short video. You pick a template, upload a picture, and a few minutes later you get an eight second clip with sound. It runs on Google's models, it lives on a website and inside Telegram, and it is my first product that takes real money from strangers. This is what the build looked like from the inside, including the parts that went wrong. What it is Under the hood…
Dantiva is a product that turns a photo into a short video using Google's models. The user selects a template, uploads a picture, and receives an eight-second clip with sound after a few minutes. The project is built on Google's models - Veo 3.1 for video generation, Gemini image model for picture creation and editing, and another Gemini model for rewriting user prompts.
Additional features include accounts, tokens, templates, a library of results, projects, legal center, an admin panel, and support/refunds. The product primarily targets Russian-speaking users who want a video with themselves in it, such as birthday greetings, trends, or new avatars. The target audience normally uses foreign cards and VPNs, making payments in rubles and providing proper receipts a significant advantage. The product runs on Google's models and lives on a website and inside Telegram.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
