Generative
-
MinD-Video model creates high-quality videos from your brain activity
MinD-Video is a new technology that can generate high-quality videos from brain signals.…
-
Make-An-Animation: a U-Net based diffusion model for 3D human motion generation
Make-An-Animation is a new text-to-motion generation model that creates realistic and diverse 3D…
-
DragGAN: edit images by simply dragging some points on them
DragGAN (Drag Your GAN) is an interactive method for editing GAN-generated images by simply dragging some…
-
How Stability AI is advancing open-source AI with StableStudio
Stability AI, a leading company in the field of generative AI, has announced…
-
Nvidia’s new high resolution text-to-video synthesis with Latent Diffusion Models
The AI Lab of Nvidia in Toronto launched a text-to-video generation model that uses…
-
DreamPose: fashion image-to-video generation via Stable Diffusion
DreamPose is a new method that generates fashion videos from still images, through…
-
NeRF-Supervised, a novel technique for training stereo models
Google introduced NeRF-Supervised, a new framework for training deep stereo networks without requiring any…
-
Painting with sound and emotion: the Frida synesthesia
A new model that uses sound and speech to guide the robotic painting…
-
Text2Video-Zero: text-to-video diffusion models without any training or optimization
Text2Video-Zero is a new low-cost approach to produce videos from text prompts without the…
-
Ultra Fast ControlNet with Hugging Face Diffusers
Ultra Fast ControlNet with Hugging Face Diffusers is a new technology that allows…