Search Results for "video frames"
Sort By:
Showing 37 open source projects for "video frames"
View related business solutions-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
1
LongCat-Video
Foundational video generation model with 13.6B parameters
LongCat-Video is a 13.6-billion-parameter foundation model for generating and extending video. A unified architecture handles text-to-video, image-to-video, and video-continuation tasks without separate models. It is pretrained for continuation, allowing it to create minutes-long sequences while limiting color drift and quality loss. A coarse-to-fine strategy operates across time and space to produce 720p video at 30 frames per second efficiently. ... -
2
claude-video
Give Claude the ability to watch any video
Claude Video is an agent skill that gives Claude and compatible coding assistants the ability to analyze video content. It accepts public video URLs or local video files, then extracts the information needed to answer user questions about what happened on screen and in the audio. The workflow checks captions first, downloads only what is necessary, extracts timestamped frames, and produces a transcript through native captions or Whisper fallback. ... -
3
Step-Video-T2V
State-of-the-art (SoTA) text-to-video pre-trained model
Step-Video-T2V is a state-of-the-art text-to-video foundation model developed to generate videos from natural-language prompts; its 30B-parameter architecture is designed to produce coherent, temporally extended video sequences — up to around 204 frames — based on input text. Under the hood it uses a compressed latent representation (a Video-VAE) to reduce spatial and temporal redundancy, and a denoising diffusion (or similar) process over that latent space to generate smooth, plausible motion and visuals. ... -
4
Video-subtitle-extractor
A GUI tool for extracting hard-coded subtitle (hardsub) from videos
Video hard subtitle extraction, generate srt file. There is no need to apply for a third-party API, and text recognition can be implemented locally. A deep learning-based video subtitle extraction framework, including subtitle region detection and subtitle content extraction. A GUI tool for extracting hard-coded subtitles (hardsub) from videos and generating srt files. Use local OCR recognition, no need to set up and call any API, and do not need to access online OCR services such as Baidu... -
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.
-
5
claude-real-video
Let Claude (or any LLM) actually watch a video
claude-real-video is a local video processing tool that prepares videos for analysis by Claude or other LLMs. It accepts public video URLs or local files and extracts the visual and audio evidence an AI model needs. Instead of sampling at a fixed interval, it detects scene changes and removes near-duplicate frames to reduce unnecessary token usage. -
6
FramePack
Lets make video diffusion practical
FramePack explores compact representations for sequences of image frames, targeting tasks where many near-duplicate frames carry redundant information. The idea is to “pack” frames by detecting shared structure and storing differences efficiently, which can accelerate training or inference on video-like data. By reducing I/O and memory bandwidth, datasets become lighter to load while models still see the essential temporal variation. -
7
Video-subtitle-remover (VSR)
AI tool that removes hardcoded subtitles and text from videos locally
Video Subtitle Remover is an AI-based application designed to remove hardcoded subtitles from videos and generate new files without the embedded text. Video Subtitle Remover analyzes video frames and detects subtitle regions, then replaces the removed areas using an AI algorithm that fills the space with reconstructed visual content. This process aims to maintain the original resolution and visual continuity of the video after subtitle removal. ... -
8
LatentSync
Taming Stable Diffusion for Lip Sync
LatentSync is an open-source framework from ByteDance that produces high-quality lip-synchronization for video by using an audio-conditioned latent diffusion model, bypassing traditional intermediate motion representations. In effect, given a source video (with masked or reference frames) and an audio track, LatentSync directly generates frames whose lip motions and expressions align with the audio, producing convincing talking-head or animated lip-sync output. ... -
9
SlowFast
Video understanding codebase from FAIR for reproducing video models
SlowFast is a video understanding framework that captures both spatial semantics and temporal dynamics efficiently by processing video frames at two different temporal resolutions. The slow pathway encodes semantic context by sampling frames sparsely, while the fast pathway captures motion and fine temporal cues by operating on densely sampled frames with fewer channels. -
Train ML Models With SQL You Already KnowBuild and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
-
10
Deep-Live-Cam
Real time face swap and one-click video deepfake
Real time face swap and one-click video deepfake with only a single image. Choose a face (image with the desired face) and the target image/video (image/video in which you want to replace the face) and click on Start. Open File Explorer and navigate to the directory you select your output to be in. You will find a directory named <video_title> where you can see the frames being swapped in real time. -
11
Memvid
Video-based AI memory library. Store millions of text chunks in MP4
Memvid encodes text chunks as QR codes within MP4 frames to build a portable “video memory” for AI systems. This innovative approach uses standard video containers and offers millisecond-level semantic search across large corpora with dramatically less storage than vector DBs. It's self-contained—no DB needed—and supports features like PDF indexing, chat integration, and cloud dashboards. -
12
MiniMax H3
MiniMax H3 is a general-purpose, omni-modal generative system
MiniMax H3 is an omni-modal generative system for creating synchronized video and native stereo audio from complex multimodal instructions. It can understand combinations of text, images, video, and audio as generation context. Outputs range from four to fifteen seconds at 24 frames per second, with multiple aspect ratios and resolutions up to 2K. H3-Base supports text-to-video, first-frame, last-frame, and first-and-last-frame generation. -
13
LTX-2.3
Official Python inference and LoRA trainer package
LTX-2.3 is an open-source multimodal artificial intelligence foundation model developed by Lightricks for generating synchronized video and audio from prompts or other inputs. Unlike most earlier video generation systems that only produced silent clips, LTX-2 combines video and audio generation in a unified architecture capable of producing coherent audiovisual scenes. The model uses a diffusion-transformer-based architecture designed to generate high-fidelity visual frames while simultaneously producing corresponding audio elements such as speech, music, ambient sound, or effects. ... -
14
VGGSfM
VGGSfM: Visual Geometry Grounded Deep Structure From Motion
...The system combines learned feature matching and geometric optimization to generate high-quality camera calibrations, sparse/dense point clouds, and depth maps in standard COLMAP format. Version 2.0 adds support for dynamic scene handling, dense point cloud export, video-based reconstruction (1000+ frames), and integration with Gaussian Splatting pipelines. It leverages tools like PyCOLMAP, poselib, LightGlue, and PyTorch3D for feature matching, pose estimation, and visualization. With minimal configuration, users can process single scenes or full video sequences, apply motion masks to exclude moving objects, and train neural radiance or splatting models directly from reconstructed outputs. -
15
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?”... -
16
SeedVR
Repo for SeedVR2 & SeedVR
SeedVR (from the ByteDance-Seed organization) is an open-source research and implementation repository focused on cutting-edge video restoration using diffusion transformer architectures. The project includes both the original SeedVR and its successor SeedVR2 models, which are designed to restore degraded or low-quality video content by learning to reconstruct high-fidelity frames with temporal coherence. These models leverage advanced techniques such as adaptive attention mechanisms and adversarial training to produce visually appealing results in a single inference step, pushing the boundaries of video restoration research. ... -
17
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... -
18
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. ... -
19
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. -
20
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... -
21
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. ... -
22
UCO3D
Uncommon Objects in 3D dataset
uCO3D is a large-scale 3D vision dataset and toolkit centered on turn-table videos of everyday objects drawn from the LVIS taxonomy. It provides about 170,000 full videos per object instance rather than still frames, along with per-video annotations including object masks, calibrated camera poses, and multiple flavors of point clouds. Each sequence also ships with a precomputed 3D Gaussian Splat reconstruction, enabling fast, differentiable rendering workflows and modern implicit/point-based modeling experiments. The repository includes automated downloaders with checksum verification, fine-grained controls to fetch only selected modalities or super-categories, and a lightweight Python API for loading frames, geometry, and splats on demand. ... -
23
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. ... -
24
Fast3R
Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass
...It represents a next-generation feedforward 3D reconstruction model capable of producing dense point clouds and camera poses for hundreds to thousands of images or video frames in a single inference pass—eliminating the need for slow, iterative structure-from-motion pipelines. Built on PyTorch Lightning and extending concepts from DUSt3R and Spann3r, Fast3R unifies multi-view geometry, depth estimation, and camera registration within a single transformer-based architecture. It outputs high-quality 3D scene representations from unordered or sequential views, scaling to large datasets and varied camera intrinsics. ... -
25
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. ...
