Open source проекты по теме «video-generation»

A Claude Code skill that produces motion design videos from HTML, Playwright and ffmpeg, with no After Effects or Remotion license needed.

A Claude Code skill that turns a short theme into a beat-synced motion graphics video rendered to MP4 with HyperFrames.

An agent skill for Claude Code and Codex that turns your app's real UI into launch films and other short videos, cut to music and rendered locally.

A set of four Agent Skills that teach AI coding agents to build motion graphics videos with Remotion.

A motion design toolkit that lets coding agents like Claude Code build videos with Remotion and render web-based simulations to 60 fps MP4.

A set of installable Claude Code and AI agent skills covering motion design principles, After Effects, Remotion, logo animation, and motion backgrounds.

Open-source Stable Diffusion-based tool for generating character-consistent comic images and long-range image-to-video sequences.

Turns a pasted URL or text prompt into a 20-40 second launch video, with Claude Opus 5.5 writing HTML and a headless Chromium and ffmpeg pipeline rendering the MP4.

A Claude Code plugin that turns a music track and a creative prompt into a motion graphics music video using AI image and video generation via Fal.ai.

Claude Code skills that have Claude Opus 5.5 build complete videos in code, one skill per visual style: hand-painted animation and kinetic-typography reels.

An agent skill that lets Claude Code, Codex and similar coding agents produce commercial-style product launch videos from code, with a browser editor for point-and-comment edits.

Open-source large-scale video generative models for text-to-video, image-to-video, speech-to-video and character animation.

A Gradio-based web UI for running Stable Diffusion and newer image/video models, continuing the Forge fork with added model support and optimizations.

A node-graph GUI, API and backend for running diffusion models locally to generate images, video, audio and 3D content.

Open-source interactive game video generation model that turns a reference image and keyboard or mouse inputs into controllable gameplay-style video.

Open-source interactive world model that renders playable game scenes from low-poly frames using streaming neural rendering.

A unified training engine for multimodal models, supporting VLM, diffusion and LLM training with FSDP2, Muon and Liger kernels.

Open-source research framework for real-time, audio-driven avatar video generation with streaming, infinite-length output built on a 14B diffusion model.

An agentic framework that generates educational videos by writing executable Manim code instead of producing pixels directly.

A Codex Skill that turns a Chinese spoken line or abstract idea into pen-line and colored-pencil explainer animation assets using Gemini video generation.