Search Results for "which"

Implementation of Phenaki Video, which uses Mask GIT to produce text-guided videos of up to 2 minutes in length, in Pytorch. It will also combine another technique involving a token critic for potentially even better generations. A new paper suggests that instead of relying on the predicted probabilities of each token as a measure of confidence, one can train an extra critic to decide what to iteratively mask during sampling.

...By representing motion information as dense point trajectories and integrating them into the latent space of an image-to-video model, the project produces videos with more precise and controllable motion behavior than many existing methods. Wan-Move is particularly notable for eliminating the need for additional motion encoders, instead directly infusing motion cues into spatiotemporal features, which simplifies both training and inference.

...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 scheduler for larger images. The big surprise is that the generations can reach this level of fidelity. Will need to verify this on my own machine. Additionally, we will try adding an extra linear attention on the main branch as well as self-conditioning in the pixel space. The insight of being able to self-condition on any hidden state of the network as well as the newly proposed sigmoid noise schedule are the two main findings.

...In the paper, they also present a way to condition the video generation based on segmentation mask(s). You can easily do this as well, given you train a VQGanVAE on the sketches beforehand. Then, you will use NUWASketch instead of NUWA, which can accept the sketch VAE as a reference. This repository will also offer a variant of NUWA that can produce both video and audio. For now, the audio will need to be encoded manually.

Implementation of NWT, audio-to-video generation, in Pytorch. The paper proposes a new discrete latent representation named Memcodes, which can be succinctly described as a type of multi-head hard-attention to learned memory (codebook) key/values. They claim the need for less codes and smaller codebook dimensions in order to achieve better reconstructions.