Blog
Guides, cases and tricks: how to shoot AI videos where actors never break character.
Guides
Video → prompt: extract a director's shot list from any clip, then re-shoot it
Actoria's From video feature watches a clip and writes back a timestamped, beat-by-beat prompt — for 5 tokens. We fed it a 45-second scene from a classic action film and ran the raw result on three models. Full prompt and the exact token bill inside.
September 8, 2026 · 5 min read
Guides
Wan 3.0 is live in Actoria: native sound, 30-second takes, 10 references
The newest Wan generation is now a model option in Actoria: text-to-video and image-to-video with native audio, single takes up to 30 seconds, up to 10 reference images per scene, 720p and 1080p — and it's the cheapest sound-capable model in the selector.
September 1, 2026 · 4 min read
Guides
How to make an AI video with your friends (without uploading anyone's photo)
A step-by-step guide to group AI videos: verify your own face, invite friends by link, compose a scene with several people and animate it — consent included.
August 19, 2026 · 4 min read
Guides
Image-to-video vs text-to-video: which workflow actually gives you control
Text-to-video is a slot machine; image-to-video is a storyboard. A practical comparison of the two workflows — cost, control, consistency — and when to use each.
August 19, 2026 · 2 min read