Skitify: AI videos and images from a text prompt, scene by scene
Skitify is an AI video maker and image generator built around one input.
Write what you want to see, choose photo or video, pick a model such as
Seedance, Kling or GPT Image, set the aspect ratio and duration, and press
Generate. Photos can go in with the text: a first frame to start the clip
from, or references for what should be in it.
Every video lands in a project made of scenes. Next scene starts from the
last frame of the previous one, so the story continues instead of starting
over, and each scene keeps its takes: re-generate and choose the one that
stays in the video. Then reorder, trim and split the scenes in the browser,
add transitions and subtitles, and export one MP4.
An object is a few photos of one person, pet or thing saved under a name:
attach it and the model keeps it looking the same. Tokens are spent only on
generating, and the price is on the Generate button before you press it.
Skitify needs JavaScript to run. Open https://skitify.net/ in a modern
browser to generate AI videos and images from a text prompt.