Midjourney v7 launches with voice prompting and faster draft mode — why is it getting mixed reviews?
1 min read
Summary
Midjourney has released an updated version of its AI image generator, Midjourney v7, which offers a new way to prompt the model to create images.
As well as the option to type in a text prompt or attach an image, users can now speak to the model and it will produce text prompts to create an image.
It is believed that Midjourney might be using a speech-to-text model from another provider.
The new version also introduces a “draft mode”, which creates images more rapidly than its predecessor, with the images being of a lower quality but can be enhanced.
To access the draft mode and voice input, users initially have to create a personalised style for the midjourney v7.
Some users have been left disappointed with the new release, feeling that it doesn’t offer significant enough updates when compared to the previous version, Midjourney v6.