The generation of videos by artificial intelligence takes a new approach with this generative AI which, for its part, draws its material from databases of images and clips.
Take a good look at the following video. We posted it on YouTube, on a channel dedicated to artificial intelligence. It is in English, but it is easy to display the French subtitles.
This is a small clip that tells how, over the years, the video game market has come to surpass that of Hollywood. The essential point is that this 2 minute 42 second clip was made entirely from a simple request: ” The videogame market has become bigger than Hollywood (The video game market has overtaken Hollywood). It was enough to type this simple request for the application I envy :
- write an appropriate video script;
- go in search of images and videos able to illustrate this point;
- make the requested video.
In the free version we used, the video has a time limit, but if you opt for a paid version, you can produce a 15-minute clip!
This 2 minute 42 second video was generated from a simple query: “the video game market has surpassed Hollywood”. © Invideo.io
Master the art of the “prompt”
If you want your video to have a strong originality, you can, as for ChatGPT or Midjourney, write an extended prompt with lots of details:
- what is the target audience?
- the clip style (minimalist, professional, energetic, etc.);
- the desired duration;
- the destination media (depending on whether you choose Youtube, Facebook or Linkedin, the approach will be different), etc.
Here as elsewhere, the more detailed the “prompt” is, the more original the final video will be.
A different approach to the usual generative video AIs
Some may find fault with the clips produced by default (in the free version). Thus, in the present case, the mention “IStock” appears superimposed on certain visuals. It turns out that Invideo draws its material from such databases of images and clips. It would be necessary to adopt a paid subscription (20 dollars per month minimum) for such mentions to disappear.
Moreover, in the current version, the voices are in English and it would therefore be necessary to re-record a French voice instead. However, such an application can save valuable time for those who manage a thematic channel and need to update it regularly.
Classic-looking videos by default
It should be noted that this approach differs from that of applications like Pika Labs or Gen-2, which for their part, from a text, invent a video, usually of astonishing quality. As a reminder, these applications are presented, with examples of clips, on these pages:
The downside of such apps being that they are currently limited to very short durations (three or four seconds).
Invideo does not bother to create animations: it assembles existing images or videos and therefore creates a relatively classic clip. However, it is possible from Invideo to modify the prompt or the parameters of the video (including the sentences of the script or certain images and clips that we can replace with those that we submit), and to regenerate the clip. In short, the application already appears to be quite mature.
Remember that we are still at the beginning of this new era of artificial intelligence and that this approach opens up another potential for video generation.