Search Results for "depth-violet" - Page 3
Sort By:
Showing 102 open source projects for "depth-violet"
View related business solutions-
Enterprise-grade ITSM, for every businessFreshservice is an intuitive, AI-powered platform that helps IT, operations, and business teams deliver exceptional service without the usual complexity. Automate repetitive tasks, resolve issues faster, and provide seamless support across the organization. From managing incidents and assets to driving smarter decisions, Freshservice makes it easy to stay efficient and scale with confidence.
-
8 Monitoring Tools in One APM. Install in 5 Minutes.AppSignal works out of the box for Ruby, Elixir, Node.js, Python, and more. 30-day free trial, no credit card required.
-
1
HuMidi
Play MIDI like a human in ROBLOX with automatic sustain pedals.
HuMidi is a universal piano auto player for ROBLOX. It plays even the most generic MIDI file with great depth, thanks to the humanization and automatic sustain pedal generation algorithms. The pedals are generated with a thorough analysis of the MIDI data, adding more depth to your performance that no other MIDI players could! Personally have been tested in: - Visual Pianos - Starving Pianists - Digital Piano - Piano's Got Talent This tool is universal, as long as the piano in-game allows to be played on a keyboard. -
2
Stable Diffusion
High-Resolution Image Synthesis with Latent Diffusion Models
Stable Diffusion Version 2. The Stable Diffusion project, developed by Stability AI, is a cutting-edge image synthesis model that utilizes latent diffusion techniques for high-resolution image generation. It offers an advanced method of generating images based on text input, making it highly flexible for various creative applications. The repository contains pretrained models, various checkpoints, and tools to facilitate image generation tasks, such as fine-tuning and modifying the models.... -
3
OtoKeyboard - Auto Keyboard & Macro
OtoKeyboard: Boost productivity with Windows keyboard automation.
OtoKeyboard is the premier auto keyboard and macro tool for Windows, designed to save you time and eliminate digital friction. Move beyond simple text replacement and turn any repetitive task into a single-keystroke action. It's the ultimate productivity companion for professionals, gamers, and developers alike. Automate customer support replies with interactive templates; execute complex in-game combos with perfectly timed macros; or launch your entire work environment with one... -
4
PyCAPGE
PyCAPGE - Python Classic Adventure Point and Click Game Engine
...Inspired by the golden age of SCUMM games, it features a customizable 9-verb interface and robust inventory management. Key features include a Scene Manager supporting parallax scrolling, walk-behind masks, and depth-based character scaling. It implements intelligent Pathfinding to navigate complex environments automatically. The engine natively supports Multi-Character gameplay, allowing dynamic switching between protagonists. Developers can build rich narratives using the branching Dialogue System and a Cutscene Manager for scripted events. ... -
Gemini 3 and 200+ AI Models on One PlatformBuild generative AI apps with Vertex AI. Switch between models without switching platforms.
-
5
Jeeva folder utility
File/folder utility useful for comparing/mirroring directories
...--mtime (files that are newer, the same age, or older ) --diff (files whose content is identical or different) Optionally can recursively descend to a specified depth or completely down folder tree comparing corresponding folders while descending. --copy for mirroring folders, primarily for keeping mirror on another drive or frequent copying to USB stick. Short copying time. Copies only modified and/or newly created files. For both above options one can either Specify the Source and Destination folders OR Specify 2 folders (the roots of the Source and Destination folder systems) and run Jeeva from a folder somewhere below the source root. ... -
6
GromacsProSuite
Graphical User Interface for Gromacs
This tool is an integrated graphical interface that simplifies molecular dynamics simulations using Gromacs. It provides a structured, tab-based environment to set up, execute, and analyze simulations data without complex command-line operations. The software automates tasks such as topology generation, solvation, ion addition, minimization, equilibration, and production runs while executing GROMACS commands in the background. Built-in monitoring tracks CPU, RAM, and disk usage to ensure... -
7
TextureAtlas Toolbox
A powerful, free and open-source tool for TextureAtlases/Spritesheets
...Documentation Hub: https://github.com/MeguminBOT/TextureAtlas-Toolbox/tree/main/docs List of supported formats; https://github.com/MeguminBOT/TextureAtlas-Toolbox?tab=readme-ov-file#supported-formats List of supported formats (in-depth): https://github.com/MeguminBOT/TextureAtlas-Toolbox/blob/main/docs/format-reference.md -
8
Aphantasia
CLIP + FFT/DWT/RGB = text to image/video
...Direct RGB pixels optimization (very stable) depth-based 3D look (courtesy of deKxi, based on AdaBins), complex queries: text and/or image as main prompts, separate text prompts for style and to subtract (avoid) topics. Starting/resuming process from saved parameters or from an image. -
9
Stable Diffusion in Docker
Run the Stable Diffusion releases in a Docker container
...Save the user access token in a file called token.txt and make sure it is available when building the container. Create an image from an existing image and a text prompt. Modify an existing image with its depth map and a text prompt. -
Forever Free Full-Stack Observability | Grafana CloudBuilt on open standards like Prometheus and OpenTelemetry, Grafana Cloud includes Kubernetes Monitoring, Application Observability, Incident Response, plus the AI-powered Grafana Assistant. Get started with our generous free tier today.
-
10
ControlNet
Let us control diffusion models
...Rather than training from scratch, ControlNet “locks” the weights of a pre-trained diffusion model and introduces a parallel trainable branch that learns additional conditions—like edges, depth maps, segmentation, human pose, scribbles, or other guidance signals. This allows the system to control where and how the model should focus during generation, enabling users to steer layout, structure, and content more precisely than prompt text alone. The project includes many trained model variants that accept different types of conditioning (e.g., canny edge input, normal maps, skeletal pose) and produce improved fidelity in stable diffusion outputs. ... -
11
Flask-SQLAlchemy
Adds SQLAlchemy support to Flask
...It simplifies using SQLAlchemy with Flask by setting up common objects and patterns for using those objects, such as a session tied to each web request, models, and engines. Flask-SQLAlchemy does not change how SQLAlchemy works or is used. See the SQLAlchemy documentation to learn how to work with the ORM in depth. The documentation here will only cover setting up the extension, not how to use SQLAlchemy. -
12
D2L.ai
Interactive deep learning book with multi-framework code
...The entire book is drafted in Jupyter notebooks, seamlessly integrating exposition figures, math, and interactive examples with self-contained code. Offers sufficient technical depth to provide a starting point on the path to actually becoming an applied machine learning scientist. -
13
xTuring
Easily build, customize and control your own LLMs
xTuring is an open-source AI personalization software. xTuring makes it easy to build and control LLMs by providing a simple interface to personalize LLMs to your own data and application. xTuring provides fast, efficient and simple fine-tuning of LLMs, such as LLaMA, GPT-J, Galactica, and more. By providing an easy-to-use interface for fine-tuning LLMs to your own data and application, xTuring makes it simple to build, customize and control LLMs. The entire process can be done inside your... -
14
MetaTransformer
Meta-Transformer for Unified Multimodal Learning
We're thrilled to present OneLLM, an ensembling Meta-Transformer framework with Multimodal Large Language Models, which performs multimodal joint training, supports more modalities including fMRI, Depth, and Normal Maps, and demonstrates very impressive performances on 25 benchmarks. -
15
PIFuHD
High-Resolution 3D Human Digitization from A Single Image
...It also uses a two-stage architecture: a coarse global model followed by local refinement patches to capture fine detail, balancing global consistency and local detail. The repo includes training pipelines, dataset loaders (for Multi-POP, etc.), and inference scripts for mesh output including depth maps for postprocessing. To help practical use, there are utilities for normal estimation, texture back-projection, mesh cleanup, and integration with rendering pipelines. -
16
The Art of Programming
A collection of practical tips can be found at the bottom of this page
The Art of Programming (Second Edition) is a curated collection of programming problems and solutions originally derived from the Microsoft 100 Interview Questions blog series, later refined into a long-running tutorial and ultimately a published book. Created by July, the series began in 2010 and has since evolved into an in-depth exploration of algorithmic thinking, data structures, and coding interview preparation. The repository brings together 42 classic programming problems from the original series, enhanced with detailed explanations, formula derivations, and optimized solutions. In July 2023, work on the second edition was announced, which expands the project with updated content, new problems inspired by recent big-tech interviews, and introductions to modern machine learning techniques such as XGBoost, CNNs, RNNs, and LSTMs. ... -
17
BitcoinExchangeFH
Cryptocurrency exchange market data feed handler
BitcoinExchangeFH is a slim application to record the price depth and trades in various exchanges. You can set it up quickly and record all the exchange data in a few minutes! If the exchange is not supported with the WebSocket API feed, it will automatically fall into using its REST API feed. The subscription section specifies the exchange and instruments to subscribe. After receiving the order book or trade update, each handler is updated. -
18
Crunch PNG
Insane(ly slow but wicked good) PNG image optimization
Crunch is a tool for lossy PNG image file optimization. It combines selective bit depth, color type, and color palette reduction with zopfli DEFLATE compression algorithm encoding using the pngquant and zopflipng PNG optimization tools. This approach leads to a significant file size gain relative to lossless approaches at the expense of a relatively modest decrease in image quality. Continuous benchmark testing is available in our GitHub Actions CI. -
19
Crunch
Insane(ly slow but wicked good) PNG image optimization
Crunch is an image compression tool for lossy PNG image file optimization. Using a combination of selective bit depth, color palette reduction and color type, as well as zopfli DEFLATE compression algorithm encoding that employs the pngquant and zopflipng PNG optimization tools, Crunch is effectively able to optimize and compress images with minimal decrease in image quality. While it may produce file size gains larger than those produced by lossless approaches, the impact on image quality is often imperceptible, and optimized file sizes are still significantly lower than the original. -
20
INVESTOCK - Analyze Indian shares
Back test, analyze, rate of return of Indian shares for 20+ years.
Analyze, winning percentage, back test and estimate the maximum rate of return from the historical prices of an equity stock listed in NSE, India between any two selected dates for more than 20 years. INVESTOCK program is used to get the historical prices of an Indian share listed in National Stock Exchange( NSE), India between any two selected dates. All the shares listed in National Stock Exchange (NSE), India can be analyzed. Interactive graphs will be displayed for the... -
21
YOLOv4-large
Scaled-YOLOv4: Scaling Cross Stage Partial Network
...The project provides a PyTorch implementation of the Scaled-YOLOv4 framework, which extends the original YOLOv4 architecture using Cross Stage Partial (CSP) networks and new scaling techniques. Unlike earlier object detection systems that only scale depth or width, this architecture scales multiple aspects of the neural network including structure, resolution, and channel configuration. This scaling strategy enables the model to adapt to different hardware environments while maintaining a strong balance between speed and detection accuracy. The repository includes multiple model variants such as YOLOv4-tiny, YOLOv4-CSP, and large-scale configurations designed for high-performance detection tasks. -
22
Kubestriker
A Blazing fast Security Auditing tool for Kubernetes
Kubestriker is a platform-agnostic tool designed to tackle Kubernetes cluster security issues due to misconfigurations and will help strengthen the overall IT infrastructure of any organization. It performs numerous in-depth checks on a range of services and open ports well across more than one platform such as self-hosted kubernetes, Amazon EKS, Azure AKS, Google GKE etc., to identify any misconfigurations which make organizations an easy target for attackers. In addition, it helps safeguard against potential attacks on Kubernetes clusters by continuously scanning for anomalies. ... -
23
Pydub
Manipulate audio with a simple and easy high level interface
...For opening and saving non-wav files, like mp3, you'll need ffmpeg or libav. Any operations that combine multiple AudioSegment objects in any way will first ensure that they have the same number of channels, frame rate, sample rate, bit depth, etc. -
24
pycassonne
Carcassonne clone written in python using pygame
...You may play against one or more computer/human players using this game with different selectable computer players' skills. Computer player examines own her step only, so the analysation depth is only 1, trying to gain the maximum available extra points. Turning trace mode on it is possible to play against computer with ultra skill level, where the analysation depth is increased to 2. With this setting the AI is stronger but the gameplay is unbearable slow. It is just for test purpose. -
25
Consistent Depth
We estimate dense, flicker-free, geometrically consistent depth
Consistent Depth is a research project developed by Facebook Research that presents an algorithm for reconstructing dense and geometrically consistent depth information for all pixels in a monocular video. The system builds upon traditional structure-from-motion (SfM) techniques to provide geometric constraints while integrating a convolutional neural network trained for single-image depth estimation.
