Today’s AI applications feel magical. But the UX is still similar to regular software. Forms, buttons, etc. The next wave will look completely different. Instead of using software, we’ll see totally new interfaces that feel as natural as working with another person.
MULTIMODAL AI
-
Image Generation Feature Rolls Out for Select Characters
By
–
Image generation is only available for a small set of Characters for now. We plan to roll out this feature more widely as we experiment and incorporate feedback from the community.
-
Character.ai Launches Image Generating Characters Feature
By
–
Introducing Image Generating Characters! Image Generating Characters generate images as you talk to them, offering a more engaging and immersive experience. Try them at http://
character.ai -
Stable Diffusion’s Reasonable Interpretation of My Image
By
–
Base stable diffusion has a decent guess about me
-
Google Launches LaMDA AI in Test Kitchen App
By
–
Test out our emerging generative AI technology with the AI Test Kitchen. In the future, we’ll bring new experiences featuring text-to-image generation. Get the app from the Play Store (
https://
goo.gle/3zzphsA) or App Store (
https://
goo.gle/3sSKFFr) to experience LaMDA now! (5/5) -
Imagen Video and Phenaki: Text-to-Video Generation Advances
By
–
Meet Imagen Video and Phenaki, two research approaches for text-to-video generation.
— Google AI (@GoogleAI) 2 novembre 2022
By combining diffusion & sequence learning techniques, we can generate videos that are super-res at the frame level and coherent in time. (4/5)https://t.co/O7gGzb9knWhttps://t.co/Uc0krTyTvk pic.twitter.com/Op4tonX2iwMeet Imagen and Phenaki, two research approaches for text-to-video generation. By combining diffusion & sequence learning techniques, we can generate videos that are super-res at the frame level and coherent in time. (4/5) https://
imagen.research.google/video/ https://
phenaki.video -
AudioLM: AI Framework Generates Realistic Speech and Piano Music
By
–
We introduced a new framework, AudioLM, that learns to generate realistic speech and piano music by listening to audio only ↓ (3/5)
-
Google’s Generative AI Tools for Creative Expression
By
–
Generative AI has the potential to help us expand our creativity and express ourselves in new, artistic ways. Our Senior Research Director, @douglas_eck
, will be sharing the tools we’re building to generate text, audio, images, and videos ↓ (1/5) -
6.4M AI-Generated Images Map Reveals Human Interests
By
–
Worth exploring: a map of 6.4M million images generated by AI, grouped by what the AI considers to similar images.
— Ethan Mollick (@emollick) 1 novembre 2022
Why you might want to explore it: it shows you what kinds of images humans are interested in; it teaches new prompts; & has surprising art.https://t.co/t1oUai8HJNWorth exploring: a map of 6.4M million images generated by AI, grouped by what the AI considers to similar images. Why you might want to explore it: it shows you what kinds of images humans are interested in; it teaches new prompts; & has surprising art.