Search Results for "self learning ai"

Implementation of Make-A-Video, new SOTA text to video generator from Meta AI, in Pytorch. They combine pseudo-3d convolutions (axial convolutions) and temporal attention and show much better temporal fusion. The pseudo-3d convolutions isn't a new concept. It has been explored before in other contexts, say for protein contact prediction as "dimensional hybrid residual networks". The gist of the paper comes down to, take a SOTA text-to-image model (here they use DALL-E2, but the same learning points would easily apply to Imagen), make a few minor modifications for attention across time and other ways to skimp on the compute cost, do frame interpolation correctly, get a great video model out. ...

HunyuanVideo is a cutting-edge framework designed for large-scale video generation, leveraging advanced AI techniques to synthesize videos from various inputs. It is implemented in PyTorch, providing pre-trained model weights and inference code for efficient deployment. The framework aims to push the boundaries of video generation quality, incorporating multiple innovative approaches to improve the realism and coherence of the generated content. Release of FP8 model weights to reduce GPU...

Implementation of Recurrent Interface Network (RIN), for highly efficient generation of images and video without cascading networks, in Pytorch. The author unawaredly reinvented the induced set-attention block from the set transformers paper. They also combine this with the self-conditioning technique from the Bit Diffusion paper, specifically for the latents. The last ingredient seems to be a new noise function based around the sigmoid, which the author claims is better than cosine...

Text2Video is a software tool that converts text to video for more engaging learning experience. I started this project because during this semester, I have been given many reading assignments and I felt frustration in reading long text. For me, it was very time and energy-consuming to learn something through reading. So I imagined, "What if there was a tool that turns text into something more engaging such as a video, wouldn't it improve my learning experience?" I created a prototype web...

DeepFaceLab is currently the world's leading software for creating deepfakes, with over 95% of deepfake videos created with DeepFaceLab. DeepFaceLab is an open-source deepfake system that enables users to swap the faces on images and on video. It offers an imperative and easy-to-use pipeline that even those without a comprehensive understanding of the deep learning framework or model implementation can use; and yet also provides a flexible and loose coupling structure for those who want to...

This paper proposes a new GAN architecture for video generation with depth videos and color videos. The proposed model explicitly uses the information of depth in a video sequence as additional information for a GAN-based video generation scheme to make the model understands scene dynamics more accurately. The model uses pairs of color video and depth video for training and generates a video using the two steps. Generate the depth video to model the scene dynamics based on the geometrical...