I’m really excited about what GPT-4 Turbo with Vision enables, and can’t wait to see what you can build with these higher limits!
MULTIMODAL AI
-
New GPT Restores and Upscales Photos Up to 4x
By
–
My new GPT 'Restore & Upscale Photos' is here! ✨
— Pietro Schirano (@skirano) 12 janvier 2024
Struggling with old, blurry photos? Want larger, clearer images? 🖼️
Try this GPT for instant restoration. It can upscale your photos up to 4x and possibly more.
It even shows a before/after comparison. 🪄
No API.
Link 👇 pic.twitter.com/StsEfDNt46My new GPT 'Restore & Upscale Photos' is here! Struggling with old, blurry photos? Want larger, clearer images? Try this GPT for instant restoration. It can upscale your photos up to 4x and possibly more. It even shows a before/after comparison. No API. Link
-
AMIE Outperforms Primary Care in Diagnostic Accuracy Study
By
–
In an earlier randomized, double-blind vignette study to generate a differential diagnosis on 300+ @NEJM case challenges, AMIE showed the potential to outperform primary care practitioners in diagnostic accuracy AND showed it could be a helpful collaborator to clinicians.
-
AI Facial Expression Generation: Complexity and Limitations
By
–
How they make different facial expressions every single time? Oh boy, that's a lot of work. Let's be honest, I don't get that many expressions.
-
Midjourney v6 Impresses with Advanced Text Generation Capabilities
By
–
I’m still blown away by Midjourney v6’s abilities with text.
-
Google AI Reconstructs Music from Brain Scans Using Neural Networks
By
–
Can AI decode the music you’re listening to? Learn how Google Research reconstructed music from brain scans using deep neural networks in partnership with Osaka University → https://t.co/U4V28yr03B pic.twitter.com/QU8ghM1HHC
— Google AI (@GoogleAI) 11 janvier 2024Can AI decode the music you’re listening to? Learn how Google Research reconstructed music from brain scans using deep neural networks in partnership with Osaka University → https://
goo.gle/3NMonQE -
TensorRT Accelerates SDXL Turbo and Stable Video Diffusion
By
–
Great to see TensorRT accelerated versions of SDXL Turbo and Stable Diffusion running so well on @nvidia hardware!
-
Impressive Detailed Results But Potentially Overly Complex
By
–
I really love these but I feel they are almost too detailed! Especially the second image. But amazing results!
-
EverArtAI Launches Pose Transfer Image Description Feature
By
–
We just launched an amazing new feature on @everartai. 🚀
— Pietro Schirano (@skirano) 11 janvier 2024
it's a game-changer for Pose Transfer!
Now, upload an image and it instantly gets described.
This prompt is a great starting point, which you can further refine with our magic prompting feature! 🪄 pic.twitter.com/s2BMgXoQOpWe just launched an amazing new feature on @everartai
. it's a game-changer for Pose Transfer! Now, upload an image and it instantly gets described. This prompt is a great starting point, which you can further refine with our magic prompting feature! -
Expand Canvas and Video-to-Video AI Features
By
–
Sometimes your scene could use a little extra space—or an extra horse🐴. Expand Canvas is here for you.
— Pika (@pika_labs) 11 janvier 2024
And when that horse isn't quite 🦄 magically cute 🦄 enough, adjust the style with Video-to-Video. pic.twitter.com/l80eWpfEEtSometimes your scene could use a little extra space—or an extra horse. Expand Canvas is here for you. And when that horse isn't quite magically cute enough, adjust the style with Video-to-Video.