Showing 142 open source projects for "video frames"

View related business solutions
  • Build Agents and Models on One Platform Icon
    Build Agents and Models on One Platform

    Everything you need to build production-ready agents and models. Access 200+ Google and third-party AI models and tools.

    Gemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
    Start Free
  • $300 Free Credits to Build on Google Cloud Icon
    $300 Free Credits to Build on Google Cloud

    New customers can spin up VMs, build with AI, and query data at no cost.

    Put your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
    Start Free
  • 1
    CCapture.js

    CCapture.js

    A library to capture canvas-based animations at a fixed framerate

    CCapture.js is a JavaScript library designed to capture high-quality recordings of HTML5 canvas animations at a fixed and consistent frame rate. Unlike traditional screen recording tools, it decouples rendering speed from capture speed, allowing developers to generate smooth video outputs even when frames take longer to compute. It works by overriding time-related browser functions such as requestAnimationFrame and Date.now to simulate a stable time progression, ensuring every frame is captured accurately. This approach enables the creation of high-resolution videos, slow-motion sequences, or complex visualizations without dropped frames. ...
    Downloads: 3 This Week
    Last Update:
    See Project
  • 2
    h265web.js

    h265web.js

    A HEVC/H.265 Web Player

    ...The project includes components for parsing H.265 bitstreams into NAL units and decoding them into raw YUV frames that can then be rendered onto a canvas or processed further. Its architecture separates parsing, decoding, and rendering, giving developers fine-grained control over how video data is handled and displayed. The system is designed to work with streaming data, allowing incremental feeding of video chunks and real-time decoding, which is useful for surveillance, streaming platforms, and custom media pipelines.
    Downloads: 10 This Week
    Last Update:
    See Project
  • 3
    Sa2VA

    Sa2VA

    Official Repo For "Sa2VA: Marrying SAM2 with LLaVA

    Sa2VA is a cutting-edge open-source multi-modal large language model (MLLM) developed by ByteDance that unifies dense segmentation, visual understanding, and language-based reasoning across both images and videos. It merges the segmentation power of a state-of-the-art video segmentation model (based on SAM‑2) with the vision-language reasoning capabilities of a strong LLM backbone (derived from models like InternVL2.5 / Qwen-VL series), yielding a system that can answer questions about visual content, perform referring segmentation, and maintain temporal consistency across frames in video. With minimal instruction tuning (often one-shot), Sa2VA can handle tasks such as “segment the main subject,” “what are the objects in this scene?”...
    Downloads: 0 This Week
    Last Update:
    See Project
  • 4
    h3-metal

    h3-metal

    MiniMax H3 inference engine for Mac computers

    h3-metal is a native MiniMax-H3 inference engine for Apple Silicon focused on generating video and audio locally with Metal. It supports prompt-to-video and prompt-to-audio workflows as well as first-frame, last-frame, image, video, and audio references. An interactive terminal session keeps prompt conditioning, the diffusion transformer, and the video decoder in memory for faster repeated generations. Users can trade speed, quality, and memory through denoising steps, layer counts, reuse modes, token reduction, internal render size, and SSD streaming. ...
    Downloads: 1 This Week
    Last Update:
    See Project
  • Custom VMs From 1 to 96 vCPUs With 99.95% Uptime Icon
    Custom VMs From 1 to 96 vCPUs With 99.95% Uptime

    General-purpose, compute-optimized, or GPU/TPU-accelerated. Built to your exact specs.

    Live migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
    Start Free
  • 5
    Computer Vision Annotation Tool (CVAT)

    Computer Vision Annotation Tool (CVAT)

    Interactive video and image annotation tool for computer vision

    Computer Vision Annotation Tool (CVAT) is a free and open source, interactive online tool for annotating videos and images for Computer Vision algorithms. It offers many powerful features, including automatic annotation using deep learning models, interpolation of bounding boxes between key frames, LDAP and more. It is being used by its own professional data annotation team to annotate millions of objects with different properties. The UX and UI were also specially developed by the team for...
    Downloads: 24 This Week
    Last Update:
    See Project
  • 6
    HunyuanCustom

    HunyuanCustom

    Multimodal-Driven Architecture for Customized Video Generation

    HunyuanCustom is a multimodal video customization framework by Tencent Hunyuan, aimed at generating customized videos featuring particular subjects (people, characters) under flexible conditions, while maintaining subject/identity consistency. It supports conditioning via image, audio, video, and text, and can perform subject replacement in videos, generate avatars speaking given audio, or combine multiple subject images. The architecture builds on HunyuanVideo, with added modules for...
    Downloads: 0 This Week
    Last Update:
    See Project
  • 7
    Open Vision Agents by Stream

    Open Vision Agents by Stream

    Build Vision Agents quickly with any model or video provider

    Open Vision Agents by Stream is an open source framework from Stream for building real time, multimodal AI agents that watch, listen, and respond to live video streams. It focuses on combining video understanding models, such as YOLO and Roboflow based detectors, with real time large language models like OpenAI Realtime and Gemini Live to create interactive experiences. The framework uses Stream’s ultra low latency edge network so agents can join sessions quickly and maintain very low audio and video latency while processing frames and generating responses. ...
    Downloads: 9 This Week
    Last Update:
    See Project
  • 8
    VOID

    VOID

    Video Object and Interaction Deletion

    ...Built on top of transformer-based architectures and fine-tuned for video inpainting tasks, the system uses interaction-aware mask conditioning to ensure temporal consistency across frames. One of its most notable capabilities is its ability to simulate realistic scene behavior after object removal, such as causing an object to fall naturally if its support is removed, which significantly enhances realism.
    Downloads: 1 This Week
    Last Update:
    See Project
  • 9
    HunyuanWorld-Voyager

    HunyuanWorld-Voyager

    RGBD video generation model conditioned on camera input

    HunyuanWorld-Voyager is a next-generation video diffusion framework developed by Tencent-Hunyuan for generating world-consistent 3D scene videos from a single input image. By leveraging user-defined camera paths, it enables immersive scene exploration and supports controllable video synthesis with high realism. The system jointly produces aligned RGB and depth video sequences, making it directly applicable to 3D reconstruction tasks. At its core, Voyager integrates a world-consistent video...
    Downloads: 1 This Week
    Last Update:
    See Project
  • Cut Data Warehouse Costs by 54% Icon
    Cut Data Warehouse Costs by 54%

    Easily migrate from Snowflake, Redshift, or Databricks with free tools.

    BigQuery delivers 54% lower TCO with exabyte scale and flexible pricing. Free migration tools handle the SQL translation automatically.
    Start Free
  • 10
    Scrcpy GUI

    Scrcpy GUI

    A simple & beautiful GUI application for scrcpy

    ...Scrcpy works by running a server on your Android device, and the desktop application communicates using USB (or using ADB tunneling wireless). The server streams the H.264 video of the device screen. The client decodes the video frames and displays them. The client captures input (keyboard and mouse) events, sends them to the server, and the server injects them into the device. If you want to see your Android screen interact with the app or content on your desktop, record your phone screen or perform other basic tasks, then Scrcpy is a good choice. ...
    Downloads: 210 This Week
    Last Update:
    See Project
  • 11
    SwiftFFmpeg

    SwiftFFmpeg

    A Swift wrapper for the FFmpeg API

    SwiftFFmpeg is a Swift wrapper for FFmpeg that provides direct access to multimedia processing capabilities within Apple development environments. It exposes FFmpeg’s libraries through Swift-friendly APIs, enabling developers to perform encoding, decoding, and stream manipulation tasks. The project is designed to maintain performance while improving usability through modern language features. It supports working with media containers, codecs, and frames at a low level, offering fine control...
    Downloads: 3 This Week
    Last Update:
    See Project
  • 12
    Oasis

    Oasis

    Inference script for Oasis 500M

    Open-Oasis provides inference code and released weights for Oasis 500M, an interactive world model that generates gameplay frames conditioned on user keyboard input. Instead of rendering a pre-built game world, the system produces the next visual state via a diffusion-transformer approach, effectively “imagining” the world response to your actions in real time. The project focuses on enabling action-conditional frame generation so developers can experiment with interactive, model-generated environments rather than static video generation alone. ...
    Downloads: 1 This Week
    Last Update:
    See Project
  • 13
    scroll-world

    scroll-world

    A skill that turn any brand into a scrollable 3D world

    ...The workflow interviews the user about the brand, message, visual direction, and ordered sequence of scenes. It then uses Higgsfield to generate still images, scene-entry videos, and connector clips built from matching boundary frames. A portable JavaScript engine maps scrolling to video time, adds lazy loading, and blends seams between clips. Templates and batch scripts cover prompting, frame extraction, encoding, page setup, and optional background removal. The output is framework-agnostic and can be embedded in plain HTML, Next.js, Vue, or Python-served sites.
    Downloads: 3 This Week
    Last Update:
    See Project
  • 14
    Repair Video Master

    Repair Video Master

    Video repair software designed to fix corrupted or damaged video files

    Repair Video Master is a video repair software designed to fix corrupted or damaged video files in various formats, such as AVI, WMV, RM, and MPEG-4. It allows users to repair videos that cannot be played or have other issues, like broken frames or unsynced audio. The software offers a simple interface, making it easy for users to add files and start the repair process quickly, and it saves the repaired videos as new files without overwriting the originals. ...
    Downloads: 11 This Week
    Last Update:
    See Project
  • 15
    Apprentice Video

    Apprentice Video

    it's a video player, also works for music and pictures

    This player stands on the giant shoulders of FFmpeg. Audio rendering is accomplished via portaudio v19. Video rendering is via OpenGL, using fragment programs when possible. User interface is implemented with Qt 4/5/6. ASS/SSA subtitle rendering is implemented with libass. This player provides several performance options to enable adequate video playback on slow hardware: * skip loop filter * skip non-reference frames * skip color converter * reduce playback speed to accommodate slow video decoding This player supports playback of HDR video on non-HDR displays: * colorspace transform to BT.709 colorspace via an auto-generated 3D LUT * tone mapping from HDR to SDR (BT. 709) This player supports playback of MPEG-TS files containing multiple programs, timeline anomalies, and codec changes. ...
    Leader badge
    Downloads: 18 This Week
    Last Update:
    See Project
  • 16
    Rsmpeg

    Rsmpeg

    A Rust crate that exposes FFmpeg's power as much as possible

    Rsmpeg is a Rust-based binding for FFmpeg that provides low-level access to multimedia processing capabilities through safe and efficient abstractions. It allows developers to interact directly with FFmpeg libraries for tasks such as encoding, decoding, and stream manipulation. The library is designed to balance performance with safety by leveraging Rust’s ownership model and memory management features. It supports handling of containers, codecs, and frames, enabling fine-grained control...
    Downloads: 0 This Week
    Last Update:
    See Project
  • 17
    trackers

    trackers

    Multi-object tracking algorithms

    trackers is a plug-and-play multi-object tracking library designed to work with virtually any object detection model, enabling developers to follow objects across video frames with minimal setup. The library provides clean, modular implementations of leading tracking algorithms and can be used either from the command line or embedded directly into Python pipelines. It supports inputs such as videos, webcams, RTSP streams, or image directories and produces annotated tracking outputs that include labels and trajectories. ...
    Downloads: 0 This Week
    Last Update:
    See Project
  • 18
    Zoo Design Studio

    Zoo Design Studio

    The Zoo Design Studio app

    ...Users can interact with the system through a familiar point-and-click interface, but every action is translated into code in the underlying modeling language, ensuring consistency between visual and programmatic representations. The application is powered by a GPU-first geometry engine that streams rendered output as video frames, enabling high-performance modeling even when heavy computation is offloaded to remote infrastructure. It uses WebSockets for real-time communication between the client and the modeling engine, allowing immediate feedback and interactive design updates.
    Downloads: 14 This Week
    Last Update:
    See Project
  • 19
    Vidiot

    Vidiot

    Non-linear video editor targeted for home video editing.

    Vidiot is a non-linear video editor targeted for home video editing. It supports compositing (scaling/rotating/positioning), cropping, changing speed, adding transitions and titles, trimming, key frames, etc.
    Leader badge
    Downloads: 399 This Week
    Last Update:
    See Project
  • 20
    BoxMOT

    BoxMOT

    Pluggable SOTA multi-object tracking modules for segmentation

    BoxMOT is an open-source framework designed to provide modular implementations of state-of-the-art multi-object tracking algorithms for computer vision applications. The project focuses on the tracking-by-detection paradigm, where objects detected by vision models are continuously tracked across frames in a video sequence. It provides a pluggable architecture that allows developers to combine different object detectors with multiple tracking algorithms without modifying the core codebase. The framework supports integration with detection, segmentation, and pose estimation models that produce bounding box outputs. It also includes evaluation tools and benchmarking pipelines that allow researchers to test tracking performance on standard datasets such as MOT17 and MOT20. ...
    Downloads: 3 This Week
    Last Update:
    See Project
  • 21
    Lyra 2

    Lyra 2

    Project Lyra: Open Generative 3D World Models

    The Lyra 2 project is a research-driven framework developed by NVIDIA that focuses on building open generative 3D world models using advanced diffusion-based techniques. It enables the creation of fully explorable 3D environments from minimal inputs such as a single image or video, leveraging self-distillation methods to generate consistent spatial representations. The system evolves across versions, with newer iterations introducing long-horizon generation and improved 3D consistency across frames. It combines elements of computer vision, generative modeling, and spatial intelligence to produce dynamic and navigable virtual worlds. ...
    Downloads: 1 This Week
    Last Update:
    See Project
  • 22
    gganimate

    gganimate

    A Grammar of Animated Graphics

    gganimate extends the grammar of graphics as implemented by ggplot2 to include the description of animation. It does this by providing a range of new grammar classes that can be added to the plot object in order to customize how it should change with time. Here we take a simple boxplot of fuel consumption as a function of cylinders and let it transition between the number of gears available in the cars. As this is a discrete split (gear being best described as an ordered factor) we use...
    Downloads: 0 This Week
    Last Update:
    See Project
  • 23
    Video Object Remover – Frame-Accurate

    Video Object Remover – Frame-Accurate

    🎥 A free & open-source Python tool to remove unwanted objects from videos frame-by-frame using brush masking and AI inpainting (OpenCV + FFmpeg). EXE included.

    Video Object Remover – Frame Accurate Edition is a free and open-source desktop application that helps you remove unwanted objects, logos, or watermarks from videos using brush-based masking and AI inpainting. The tool extracts video frames using FFmpeg, lets you mask objects frame-by-frame, and removes them using OpenCV. Built with Python and Tkinter, it features a modern dark-themed GUI, adjustable brush tool, zoom control, and real-time logging.
    Downloads: 72 This Week
    Last Update:
    See Project
  • 24
    Smooth My Video

    Smooth My Video

    Offline AI frame interpolation, upscaling and HDR for NVIDIA GPUs

    ...The same render can AI-upscale to 16K (RTX Video Super Resolution + Real-ESRGAN restore), sharpen, and convert SDR to real HDR10 with proper mastering metadata, plus optional Dolby Vision 8.1 and HDR10+ export. Original frames pass through untouched; output is 10-bit visually lossless HEVC, AV1 or H.266 with every audio track, subtitle, chapter and font preserved. Pause anytime or close the app - renders resume where they left off.
    Downloads: 8 This Week
    Last Update:
    See Project
  • 25

    Virtualdub Batch Video DeShake v26.0204

    Batch to compress [and deshake] all videos [or images] in folder

    Installation: Execute "DeShakInst.BAT" VirtualDub2 44282; AviSynth+ 3.7.5 updated to C:\DVD DESHAK.BAT updated to C:\UT and added to PATH Usage: DESHAK task[s] [parameters] Tasks: tp1: deshake pass1 LOG generation for 2nd pass tp2: deshake pass2 and compress video and audio to MP3 tcomp: compress (no deshake) twav: extract WAV and/or uses external WAV audio Parameters (more in help): vEXT: video extension (ie: vmov), default: vAVI qN: h264...
    Downloads: 5 This Week
    Last Update:
    See Project