Search Results for "python voice synthesis"

ML Sharp is a research code release that turns a single 2D photograph into a photorealistic 3D representation that can be rendered from nearby viewpoints. Instead of requiring multi-view input, it predicts the parameters of a 3D Gaussian scene representation directly from one image using a single forward pass through a neural network. The core idea is speed: the 3D representation is produced in under a second on a standard GPU, and then the resulting scene can be rendered in real time to...

Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch. The main novelty seems to be an extra layer of indirection with the prior network (whether it is an autoregressive transformer or a diffusion network), which predicts an image embedding based on the text embedding from CLIP. Specifically, this repository will only build out the diffusion prior network, as it is the best performing variant (but which incidentally involves a causal transformer as...

A simple pic resizer working with drag and drop. Drag and drop an image file on a shortcut to the program, input width or height, confirm, find your resized image in the same folder with new dimensions in the file name.

This add-on demonstrates how motion graphs can be created in Blender in order to create a variety of arbitrary length character animations from a small set of character motions. This add-on implements motion graphs as described in Motion Graphs paper by Kovar, Gleicher, and Pighin from SIGGRAPH 2002. The add-on can import set of motion captured BVH files and construct a motion graph based on some given parameters. This motion graph can be stored in memory and used until Blender is...

Gnome/GTK animated floating face, always on top/on all desktops, voice synthesizer by espeak (by system() call, not libs), STDIN text entry, in reply to: http://gul.uc3m.es/pipermail/gul/2010-July/012630.html. Kinda office-assistant - for gnome.

A modular audio programming language, designed to write applications quickly. Its main goal is real time audio processing, but it should be used for any kind of development.