EGAKU AIBêta
CreateEASYToolsGalerieTarifsJournalNouveautésDiscord
Accueil / Journal / Turn a Photo into a Video with AI: One Free Video Every Week
how-to5 min de lecture·2026-10-26

Turn a Photo into a Video with AI: One Free Video Every Week

Turn a photo or illustration into a short AI video on EGAKU AI. A step-by-step image-to-video guide with motion prompt tips. One free video every week on the free plan.

E
par EGAKU AI Team
image-to-videophoto-to-videoai-videoillustrationbeginnerfree
Essayez-le sur EGAKU, gratuit pour commencer→

What image-to-video actually does

Pick one photo or illustration, describe how it should move, and you get a short clip a few seconds long. That is image-to-video. Hair catching the wind, steam rising from a cup, the camera drifting slowly closer: a little motion is often all a still image needs to stand out in a feed or a portfolio.

On EGAKU AI you can do this with EGAKU β 1.5, our own video model. It is built on an open-source video model and tuned in-house.

How to make your first clip

  1. Open the generator and switch to the Video tab.
  2. Choose image-to-video and upload the photo or illustration you want to animate.
  3. Select EGAKU β 1.5 as the model.
  4. Write a short description of the motion and press generate.

That is the whole flow. The rest of this guide is about getting a better result on the first try.

One free video every week

On the free plan, you get one free video every 7 days with EGAKU β 1.5 at standard quality, up to 15 seconds. The first one is always available; later ones come from a monthly allowance shared by the whole site. If a video can't be made for some reason, the free video is given back rather than used up, so a failed attempt doesn't cost you your try.

After that, videos use credits:

  • A 5-second clip costs roughly 60–70 credits.
  • Longer clips, up to 60 seconds, are made in scenes. A 30–60 second video costs about 70–80 credits.

New accounts also get 50 free credits.

Prompt tips: describe the motion, not the picture

The model can already see your image. What it needs from you is how things should move.

  • Start with a good image. Sharp and well lit beats dark and blurry every time.
  • Describe motion. Instead of "a woman in a red coat on a street", write "her hair moves in the wind, the camera slowly pushes in".
  • One main action per clip. A turn of the head, a slow walk, or a camera move. Stacking several actions into one short clip tends to look busy.
  • Keep the face visible. If your subject is a person, avoid motions where they turn away or cover their face.

Example: a photo of a man in his thirties reading on a café terrace, with the prompt "he turns a page, leaves drift past in the background, camera holds still".

Illustrations, Japanese signs and longer videos

  • Illustrations: gentle motion works best. Try a blink, a breeze through hair or clothing, or clouds moving across the sky, rather than large body movements.
  • Street scenes with Japanese text: EGAKU β 1.5 is tuned for Japanese text on signs, so signage in shopfronts and alleys holds up reasonably well as the scene moves.
  • Longer clips: plan scene by scene. Decide what happens in each shot first, then build it up in the storyboard.

Using photos of real people

Only animate photos you have the rights to, and only of people who have agreed to it. For safety, some modes may refuse photos of real people. If that happens, an illustration or an image you generated yourself is a good alternative.

Ready to try it? Open the generator, pick a photo, and make your first clip for free.

Essayez par vous-même

Créez-le avec l’outil présenté dans cet article. Crédits offerts à l’inscription.

Ouvrir l’outil, c’est gratuit

Plus d’articles

how-to

Camera Path: Draw a Camera Move on an Image and Turn It into a Video

7 min de lecture · 2026-11-05

how-to

Corriger un plan de votre court métrage IA en 3D

5 min de lecture · 2026-11-15

how-to

AI Short Film Generator: Turn a Few Sentences into a Multi-Shot Video with Movie Board

7 min de lecture · 2026-11-05

how-to

Reference to Video: Combine Images, Clips and Audio into One AI Video

6 min de lecture · 2026-11-03