Google launches ImageFX, a standalone AI image generator

We’re deep in the middle of the AI wars, with every major company either launching their own AI developments or using AI in some significant way. For tasks like AI image generation, we’ve come to rely on Midjourney and Stable Diffusion to generate images out of text prompts. But now, Google is upgrading Bard to allow AI image generation and releasing its own ImageFX image generation tool.

While Google Bard’s AI image generation capabilities are definitely big news, Google is also releasing a standalone AI image generation tool called ImageFX. Like other AI image generators, you can enter a text prompt to generate an image. ImageFX sets itself apart by introducing “expressive chips,” which let you quickly explore other variations of your original idea.

Images generated with ImageFX are marked by SynthID (a digital watermark added directly into the pixels of the image) and include IPTC metadata, showing people more information on these AI-generated images.

ImageFX is powered by Imagen 2 (and so are the image generation capabilities of Google Bard), which in turn is powered by Google DeepMind’s latest text-to-image advancements via a diffusion-based model. Imagen 2 is also being updated to deliver high-quality images and to keep images free of distracting visual artifacts.

Google is also making updates to MusicFX. MusicFX now gets higher-quality audio and faster music generation thanks to improvements made to the MusicLM model.

ImageFX and MusicFX are part of Google’s AI Test Kitchen. Users in the US, Kenya, New Zealand, and Australia can try them out in English.

Have you tried out ImageFX? How has your experience been? Let us know in the comments below!