Search Results for "clip"
Sort By:
48 projects for "clip" with 1 filter applied:
-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
Veeam Data Platform v13.1 - Get Your Free TrialTry Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
1
CLIP
CLIP, Predict the most relevant text snippet given an image
...The repository provides code for model architecture, preprocessing transforms, evaluation pipelines, and example inference scripts. Because it generalizes to arbitrary labels via text prompts, CLIP is a powerful tool for tasks that involve interpreting images in terms of descriptive language. -
2
clip-js
online video editor built with nextjs, remotion and ffmpeg
clip-js is a browser-based video editor built with modern web technologies such as Next.js and Remotion, designed to provide real-time editing and rendering directly in the browser. It enables users to create and edit video compositions using a timeline interface, combining video, audio, images, and text layers into a single project. The system uses a WebAssembly port of FFmpeg to perform high-quality rendering, allowing export of videos without relying on server-side processing. ... -
3
clip-retrieval
Easily compute clip embeddings and build a clip retrieval system
clip-retrieval is an open-source toolkit designed to build large-scale semantic search systems for images and text by leveraging CLIP embeddings to enable multimodal retrieval. It allows developers to compute embeddings for both images and text efficiently and then index them for fast similarity search across massive datasets. The system is optimized for performance and scalability, capable of processing tens or even hundreds of millions of embeddings using GPU acceleration. ... -
4
MetaCLIP
ICLR2024 Spotlight: curation/training code, metadata, distribution
MetaCLIP is a research codebase that extends the CLIP framework into a meta-learning / continual learning regime, aiming to adapt CLIP-style models to new tasks or domains efficiently. The goal is to preserve CLIP’s strong zero-shot transfer capability while enabling fast adaptation to domain shifts or novel class sets with minimal data and without catastrophic forgetting. The repository provides training logic, adaptation strategies (e.g. prompt tuning, adapter modules), and evaluation across base and target domains to measure how well the model retains its general knowledge while specializing as needed. ... -
Save Up to 91% on Cloud Compute With Spot VMsRun batch jobs at 60-91% off with Spot VMs. Long-running workloads get automatic discounts with sustained use.
-
5
OpenShorts
Free & open source AI video platform
OpenShorts is an open-source, self-hosted AI video automation platform designed to generate, edit, and distribute short-form vertical content across social media platforms. It combines multiple tools into a single pipeline, including clip generation, AI-driven video creation, and YouTube optimization features. The system can transform long videos or uploaded files into short clips by detecting engaging moments, reframing content, and adding subtitles and visual effects. It also supports generating marketing videos using AI actors, voiceovers, and scripted narratives without requiring cameras or production resources. ... -
6
Multimodal
TorchMultimodal is a PyTorch library
...The library provides modular building blocks such as encoders, fusion modules, loss functions, and transformations that support combining modalities (vision, text, audio, etc.) in unified architectures. It includes a collection of ready model classes—like ALBEF, CLIP, BLIP-2, COCA, FLAVA, MDETR, and Omnivore—that serve as reference implementations you can adopt or adapt. The design emphasizes composability: you can mix and match encoder, fusion, and decoder components rather than starting from monolithic models. The repository also includes example scripts and datasets for common multimodal tasks (e.g. retrieval, visual question answering, grounding) so you can test and compare models end to end. ... -
7
Bili23 Downloader
Cross platform GUI tool for downloading videos from Bilibili sites
Bili23-Downloader is an open source desktop application designed for downloading video content from the Bilibili platform. It provides a graphical interface that allows users to download various types of media including user-uploaded videos, series episodes, movies, and other hosted content. It focuses on ease of use with a zero-configuration setup, making it accessible to both beginners and experienced users. It supports high performance downloads through multi-threading and includes resume... -
8
OmniVoice
High-Quality Voice Cloning TTS for 600+ Languages
...Built on a diffusion language model-style architecture, it combines scalability with strong performance, enabling both natural-sounding voice synthesis and efficient inference speeds. One of its most notable capabilities is zero-shot voice cloning, allowing users to replicate a speaker’s voice using only a short reference audio clip. In addition, it supports voice design through configurable attributes such as gender, accent, pitch, and speaking style, giving users fine-grained control over generated speech. The system also includes advanced features like non-verbal expression tags and pronunciation overrides, enabling expressive and precise output. With support for both API-based and command-line usage, it is designed for research, production, and experimentation alike. -
9
ComfyUI-LTXVideo
LTX-Video Support for ComfyUI
...This integration empowers non-programmers and rapid-iteration teams to harness the performance of LTX-Video while maintaining the clarity and flexibility of a dataflow graph model. It supports nodes for common video operations like trimming, layering, color grading, and generative augmentations, making it suitable for everything from simple clip edits to complex sequences with conditional behavior. -
Paessler - Monitor Your Whole Network in MinutesWaiting weeks for a monitoring rollout isn't an option when infrastructure doesn't stop running. PRTG's auto-discovery scans your network and suggests from over 200 pre-configured sensor types, so you're watching servers, applications and devices within minutes, not after a multi-week deployment. Enterprise-strength monitoring, without the enterprise complexity. Start your free trial today.
-
10
VoxCPM
TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning
...Trained on a large 1.8-million-hour bilingual corpus, VoxCPM can infer appropriate speaking style from context, dynamically adjusting intonation, rhythm, and emotional tone. It supports zero-shot voice cloning from a short reference audio clip, capturing timbre, accent, and pacing to closely mimic a target speaker without per-speaker fine-tuning. -
11
comfyui-mixlab-nodes
Workflow and speech recognition app
...On the AI side, it integrates multiple LLM providers (cloud and local), supports OpenAI-compatible endpoints, Siliconflow models, and includes prompt-focused utilities for random prompt generation, Chinese prompts, clip interrogation. -
12
OuteTTS
Interface for OuteTTS models
...It also includes a notion of speaker profiles: you can create a speaker from a short audio sample, save it as JSON, and reuse it for consistent voice identity across generations and sessions. For best quality, the model is designed to work with a reference speaker clip and will inherit emotion, style, and accent from that reference. -
13
hCaptcha Challenger
Gracefully face hCaptcha challenge with multimodal llms
hCaptcha Challenger is an open-source automation framework designed to solve hCaptcha verification challenges using computer vision models and multimodal reasoning techniques. The project integrates machine learning models capable of analyzing visual captcha tasks and identifying the correct responses required to pass the verification process. Instead of relying on third-party captcha-solving services or browser scripts, the system operates independently by using pretrained neural networks... -
14
Vidi2
Large Multimodal Models for Video Understanding and Editing
Vidi is a family of large multimodal models developed for deep video understanding and editing tasks, integrating vision, audio, and language to allow sophisticated querying and manipulation of video content. It’s designed to process long-form, real-world videos and answer complex queries such as “when in this clip does X happen?” or “where in the frame is object Y during that moment?” — offering temporal retrieval, spatio-temporal grounding (i.e. locating objects over time + space), and even video question answering. Vidi targets applications like intelligent video editing, automated video search, content analysis, and editing assistance, enabling users to efficiently locate relevant segments and objects in hours-long footage. ... -
15
xjadeo
The X Jack Video Monitor
X JAck viDEo mOnitor: xjadeo is a program that displays a video clip in sync with an external time source, most notably jack-transport, LTC and MTC. Applications include: soundtrack composition/editing, video monitoring and -installations. -
16
MARS5
MARS5 speech model (TTS) from CAMB.AI
...The model is built to handle prosodically challenging content such as sports commentary, anime dialogue, and other high-energy or highly varied speech patterns with realistic rhythm and intonation. To control speaker identity, MARS5 uses a short reference audio clip, typically between 2 and 12 seconds, from which it learns the voice characteristics. It supports two main inference modes: shallow clone, which is faster and only needs the reference audio, and deep clone, which additionally uses the transcript of the reference audio to increase similarity and naturalness at the cost of more computation. -
17
Quick Subtitles
HTML5 Based Subtitle Creation Tool
Quick Subtitles in an HTML5 based solution for rapid creation and syncing of subtitles while playing your video. It is designed around the concept that you should minimize the need to take your hands off the keyboard while performing data entry. -
18
Stable Diffusion
A latent text-to-image diffusion model
Stable Diffusion is a widely used open-source latent text-to-image diffusion model developed by the CompVis group for generating high-quality images from natural language prompts. The model operates by conditioning a diffusion process on text embeddings produced by a CLIP text encoder, enabling detailed and controllable image synthesis. It was trained on large-scale image datasets and later fine-tuned to produce 512×512 images with strong visual fidelity. Because the system runs efficiently on consumer hardware compared to earlier generative models, it helped popularize local AI image generation workflows. ... -
19
Motionity
The web-based motion graphics editor for everyone
Motionity is an open-source, browser-based motion-graphics editor designed to bring animation and video editing power to the web, blending the intuitiveness of drag-and-drop tools with advanced capabilities akin to desktop motion editors. It allows users to assemble video or image assets, layer them, and apply animation via keyframes — with customizable easing — giving fine-grained control over motion timing. In addition to keyframing, motionity supports layer masking, filters (color... -
20
Atom Vim-Mode-Plus
vim-mode improved
atom‑vim‑mode‑plus is a feature-rich Vim emulation layer for Atom, bringing modal editing (like Vim’s normal, insert, and visual modes) with enhanced capabilities beyond basic keybindings. Incremental search by incrementalSearch setting (disabled by default). Cursor visible in all visual modes (characterwise, blockwise, linewise). Maintain the same cursor position after operations (e.g y, gU) by stayOnYank and stayOnOperate settings. Set cursor position to start of change on undo or redo by... -
21
LiVES
LiVES is a Video Editing System. It is designed to be simple to use, y
...It is a very flexible tool which is used by both professional VJ's and video editors - mix and switch clips from the keyboard, use dozens of realtime effects, trim and edit your clips in the clip editor, and bring them together using the multitrack timeline. You can even record your performance in real time, and then edit it further or render it straight away. For the more technically minded, the application is frame and sample accurate, and it can be controlled remotely or scripted for use as a video server. And it supports all of the latest free standards. -
22
magicCss
CSS3 whimsy, single label implements various graphics
...The project serves primarily as an educational and inspirational collection for developers who want to push the boundaries of what can be achieved with native CSS capabilities. It explores advanced techniques such as gradients, blend modes, clip-path usage, and animation timing to construct visually rich UI elements without relying on images or JavaScript-heavy solutions. The repository is organized as a gallery of experiments, each illustrating a specific visual trick or pattern that can be studied and reused. By emphasizing minimal markup and clever styling, it encourages performance-conscious and elegant front-end design practices. ... -
23
svg-map-animation
generate animated video-clips from svg-image
Draw some track-segments as bezier-curves on top of a map-image. Run svgAnim.rb-script to generate a vido-clip witch shows the track animated from 0% to 100% visibility -
24
Asterisk CDR import
Simple web interface for mapping CDR from VoIP provider to Asterisk
This is a simple tool to map information for the cost of phone calls given by your VoIP provider, to the call log inside your Asterisk. As a result, you will know how much each of your employees has spent for phone calls. Additionally, this tool shows information about the assigned DID and CLIP numbers in Asterisk. This is helpful to identify obsolete, duplicate and multiple assignments. -
25
Veejay is a visual instrument and real-time video sampler. It allows you to "play" the video like you would play a piano. While playing, you can record the resulting video directly to disk (video sampling).
