gpu-net Goto Github PK

eavesdrop

Eavesdrop uses OpenAI's GPT-2 LLM to modify and extend movie scripts based on nouns and verbs in speach overheard by the device. Developed for HackEd2020.

fastob_api

Designed to streamline the integration of the OobaBooga Text Web UI with SillyTavern by providing a convenient means to obtain and integrate the required API key.

flask-a-graph

"Flask-A-Graph' is a Flask app that uses Stable Diffusion Pipeline to generate images based on user input prompts. The app is easy to use and perfect for anyone looking to explore the creative possibilities of deep learning image generation. Get ready to unleash your inner artist with Flask-A-Graph'!"

flask-video-editor

flutter-image-sequence-animator

A simple widget for animating a set of images with full custom controls as an alternative to using a GIF file.

flutter-webrtc_python-aiortc-opencv

Flutter WebRTC demo with Python server to perform image processing on video frames using OpenCV

flutter_imageview_360

A Flutter package which provides 360 view of the images with rotation and gesture customisations.

flutter_story_presenter

Easily display media as stories in your Flutter app with customizable features and smooth navigation! 🚀📷

flutter_tv

Flutter App for android TV

flutter_video_editor

A Flutter plugin for video editing on Android and iOS.

fluttergallery

Flutter gallery - Image, Audio, Video & File.

fluttermediaplayer

Audio Player, Video Player from Network, Assets and Local File in Flutter

footage

Write videos in Flutter.

gender_in_movies

NLP analyses of gender in movie scripts

image-to-slideshow-video-maker

The program is created to make slideshow videos from the images. you can add speech and background music with this project. thank you!

image-to-video

A Python script to make a still image appear like a video recording

imaginate

TypeScript browser extension that saves and edits images by inpainting using Stable Diffusion

immich

High performance self-hosted photo and video management solution.

instantmesh

InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

io_comfyui

Let Blender work with ComfyUI by ComfyScript.

joker-analysis-with-nlp

This GitHub repository contains a comprehensive analysis of the script from the critically acclaimed movie "Joker" . Leveraging the power of Natural Language Processing (NLP) techniques, this project aims to delve into the movie's script to gain insights, uncover patterns, and explore the narrative structure.

kohya_ss

llava-image-analyzer

Llava, Ollama and Streamlit | Create POWERFUL Image Analyzer Chatbot for FREE - Windows & Mac

lora-training-in-comfy

This custom node lets you train LoRA directly in ComfyUI!

mastodon-ai-horde-generate

A mastodon bot generating stable diffusion images as replies

media-kit

A cross-platform video player & audio player for Flutter & Dart.

model-scanner

models

A collection of pre-trained, state-of-the-art models in the ONNX format

mongodb-and-hugging-face-integration-for-movie-plot-semantic-search

Python script integrating MongoDB and Hugging Face API for advanced movie plot searches. Features MongoDB connection, environment variable management, semantic embedding generation, and a demonstration of NLP-enhanced database querying for movies based on plot descriptions.

mopa

An Blender addon uses ROMP to extract human's 3D poses from image, video or webcam and drive your own 3D character.