#video-generation Repositories
288 repositories total
ใ่ๅ ใ - Agent-based end-to-end AI creation platform for short dramas, motion comics, and videos โ built with Java & AgentScope 2.0.
Official implementations for paper: DreamTalk: When Expressive Talking Head Generation Meets Diffusion Probabilistic Models
Topic โ 4K narrated video for coding agents. v5.3.0: local TTS (Edge free + Azure, no external engine), manifest-based Asset Engine, Remotion composition, cost-gated AI generation, Bilibili/YouTube/Xiaohongshu/Douyin/WeChat Channels
Open-source Higgsfield on ComfyUI: 120 image, video, VFX, and audio apps; every model has open weights. Runs on Modal or your own GPU.
Natural language-driven infinite canvas workflow Agent, making AI video creation truly editable for the first time. AICON is for creators, providing a full suite of capabilities from script breakdown, storyboard generation, asset generation, video synthesis to content distribution. Not just giving you an input box, but letting you drive creation with natural language and infinite canvas together, organizing text, image, video nodes into a complete chain, truly putting 'from inspiration to finished piece' into one system.
Official MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
Official implementation of "MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling"
We propose Prism, a dynamic sparse attention framework for natively training joint video-audio generation models at 2K.
[SIGGRAPH Asia 2026] 4DAnyone: Create Anyone in 4D from a Casual Monocular Video
A viral Douyin Vibe knowledge showcase video skill: deeply analyzes viral videos, recreates their visual style, generates directorโs storyboards, automatically adds sound effects, and produces a finished video with one click.
(CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models
Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the future state of the world in the form of video.
Explainer videos and product demos made by your AI agent. Free and open source: a local voice (Kokoro), word timing (Whisper), and a canvas renderer turn a script into a narrated MP4.
Clip chaining for MiniMax H3 in ComfyUI - motion and audio genuinely continue across joins
341 code animation style prompts, 196 reference stills, and an offline selector, packaged as a Claude Code / Codex Skill, with one-click importing and HTML video rendering.
Bernini is a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer.
A 3B-active-parameter native unified multimodal model for image and video understanding, generation, and editing.
Implementation of Video Diffusion Models, Jonathan Ho's new paper extending DDPMs to Video Generation - in Pytorch
[AAAI 2024] Follow-Your-Pose: This repo is the official implementation of "Follow-Your-Pose : Pose-Guided Text-to-Video Generation using Pose-Free Videos"
[TPAMI 2025๐ฅ] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators
MiniSora: A community aims to explore the implementation path and future development direction of Sora.
Code for Motion Representations for Articulated Animation paper
[NeurIPS2026] We present StableAvatar, the first end-to-end video diffusion transformer, which synthesizes infinite-length high-quality audio-driven avatar videos without any post-processing, conditioned on a reference image and audio.
[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.
[ICCV'23] Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis
The open-source AI engine for AMD Strix Halo. Text, embeddings, speech, image and video models in one binary, with OpenAI-compatible APIs, caching for coding agents and model extensions. Linux and Windows.
https://wavespeed.ai/ [WIP] The all in one inference optimization solution for ComfyUI, universal, flexible, and fast.
HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation
Creates short videos for TikTok, Instagram Reels, and YouTube Shorts using the Model Context Protocol (MCP) and a REST API.
Free open-source project designed for turning youtube-videos into viral short videos. Highlight detection, subtitles, translation, voiceover, all in one for your content.
Code for SCIS-2025 Paper "UniAnimate: Taming Unified Video Di๏ฌusion Models for Consistent Human Image Animation".
Wunjo Make: Face Swap, Lip Sync, Control, Remove Objects & Text & Background, Restyling, Audio Separator, Clone Voice, Video Generation. Open Source, Local & Free.
Claude Opus 5.5 Video Generation with Code: Examples from Across the Web and Copy-Ready Prompts | Copy-Ready Prompts & 54 Examples of Opus 5.5 Code-Rendered Videos
[ICLR24] Official implementation of the paper โMagicDrive: Street View Generation with Diverse 3D Geometry Controlโ
Local-first AI video recasting with draft review, explicit HD approval, and source-audio restoration.
[AAAI 2026] EchoMimicV3: 1.3B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation