Google I/O 2024: Text-to-Image AI Model Imagen 3 Unveiled, Gets Improved Image Generation Capabilities

Technology


Google made several new announcements at its annual developer-focused Google I/O 2024 event. Among many announcements focused on artificial intelligence (AI) made during the keynote session, one was particularly surprising. The tech giant unveiled the next generation of its text-to-image AI model, Imagen 3. The new AI model was introduced just months after the release of its predecessor, Imagen 2, which came out in December 2023 and which was updated later last month. The company said the new model can generate detailed photorealistic images while closely following the prompt.

Image 3 was presented by Douglas Eck, Senior Research Director at Google DeepMind. Introducing it, he said: “Today, I'm very excited to introduce Imagen 3. It's our most capable imaging model yet. Understand written directions as people write. The more creative and detailed you are, the better. Also, this is our best model for text representation that has been a challenge for image generation models.”

The AI ​​model's ability to understand cues is said to have been greatly improved, now allowing it to closely follow the cue to capture small details and generate a faithful image. This also seems to be a common direction for most of the AI-related announcements during the event, as most of the AI ​​models are now able to better understand directions. Google added that Imagen 3 will be available in several versions where each model is optimized for a specific type of task that can range from generating quick sketches to creating high-resolution images.

To enable Imagen 3 to capture small details and specific instructions, such as camera angles or compositions in long and complex directions, Google trained the AI ​​model on images that contain detailed descriptions in their captions, allowing it to pick up nuances even smaller ones It can also generate a variety of textures and can render text-based images.

Focusing on security, every image generated by Imagen 3 will contain SynthID watermark tagging. It embeds a digital watermark directly into the pixels of the image, making it impossible to remove by cropping, sharing, or modifying the image. The AI ​​model is expected to arrive in public preview in the coming months. Right now, Google is working on adding inpainting and outpainting editing options. Imagen 3 is currently available in private preview within ImageFX for select creators. It will soon be available to the tech giant's business customers.


Affiliate links may be automatically generated; see our ethics statement for more information.

For the latest tech news and reviews, follow Gadgets 360 on X, Facebook, WhatsApp, Threads and Google News. For the latest videos on gadgets and technology, subscribe to our YouTube channel. If you want to know all about the best influencers, follow our in-house Who'sThat360 on Instagram and YouTube.

Redmi K70 Ultra spotted on 3C certification site; Tip to get the MediaTek Dimensity 9300+ SoC





Source

Leave a Reply

Your email address will not be published. Required fields are marked *