We're going to be taking SpeechT5 apart with @juancopi81 in the Hugging Face discord at 17:00CET. Come be a part of the fun! o/ https://
discord.com/events/8795489
62464493619/1074631980232228885
…
MULTIMODAL AI
-
SpeechT5 Deep Dive Workshop on Hugging Face Discord
By
–
-
ChatGPT Next Stage: From Text-to-Image Generation Evolution
By
–
Yeah, I think this is the way. First stage was txt-to-image, next stage is ChatGPT for image generation.
-
Midjourney AI Misinterprets Rock Image as The Rock
By
–
Indeed, in most stories that people shared, there were instances in which the technology spewed misinformation or otherwise failed. My favorite: architect Nidhi Hegde fed Midjourney an image of a rock & asked it to “make the rock gold.” It spit out a golden torso of @TheRock
. -
Reinforcement Learning Optimizes Computer Vision Model Performance
By
–
5). Vision meets RL – uses reinforcement learning to tune computer vision models with task rewards; observes large performance boosts across multiple CV tasks such as object detection and colorization.
-
Language Quantized AutoEncoders Enable Few-Shot Image Classification
By
–
6). Language Quantized AutoEncoders (LQAE) – an unsupervised method for text-image alignment that leverages pretrained language models; it enables few-shot image classification with LLMs.
-
pix2pix3D: 3D-Aware Conditional Generative Model for Image Synthesis
By
–
3). pix2pix3D – a 3D-aware conditional generative model extended with neural radiance fields for controllable photorealistic image synthesis. https://t.co/Xkmw0NJieC
— DAIR.AI (@dair_ai) 20 février 20233). pix2pix3D – a 3D-aware conditional generative model extended with neural radiance fields for controllable photorealistic image synthesis.
-
Electron Microscope Photograph of Two Cells in Love
By
–
Electron microscope photograph of 2 cells in love with each other. #StableDiffusion2 #AIart
-
VR and Stable Diffusion Creating Impressive Creative Results
By
–
La gente haciendo ya cosas muy chulas combinando VR y Stable Diffusion. Y fijaos que esto aún no está usando modelos 3D, sino texturas planas. Y aún así el resultado es bastante interesante. https://t.co/DUeUIbE4Sq
— Carlos Santana (@DotCSV) 20 février 2023La gente haciendo ya cosas muy chulas combinando VR y Stable Diffusion. Y fijaos que esto aún no está usando modelos 3D, sino texturas planas. Y aún así el resultado es bastante interesante.
-
Real-time 3D renders from 2D drawings: ChatGPT for 3D assets
By
–
3D renders (and images) based on a 2D drawing, editable in real-time.
— AI Breakfast (@AiBreakfast) 19 février 2023
Incredible.
This could be the ChatGPT for 3D assets ↓ pic.twitter.com/FBuxAo9Pss3D renders (and images) based on a 2D drawing, editable in real-time. Incredible. This could be the ChatGPT for 3D assets ↓
-
Free extension adds layers to GPT with voice and data
By
–
This is a pretty simple, free extension. The voice tech is old, but it shows how easy it is to add layers to GPT. Digital faces, custom voices, and customized data to pull from (the complete works of a particular author, for instance) can all be easily added layers to create an