Store

[SIGGRAPH 2026] Official code of the paper "Relit-LiVE: Relight Video by Jointly Learning Environment Video".

TokenSpeed is a speed-of-light LLM inference engine.

Accessible large language models via k-bit quantization for PyTorch.

Flask video browser with previews and streaming.

Your mission control center for a swarm of Ai agents.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Contribute to kohya-ss/sd-scripts development by creating an account on GitHub.

generate a video from an image with a text prompt

Upload one or more photos and type a short edit instruction (e.g., “add a cat” or “change the sky to sunset”). The app can first rewrite your prompt to make it clear, then uses a fast AI model to a...

Professional browser-based video editor. Open source CapCut alternative. 100% browser-based, no cloud uploads, no watermarks.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Local dashboard for Dynatrace problems and metrics with Azure OpenAI incident analysis.

DeepSeek 4 Flash local inference engine for Metal

a state-of-the-art open-source model for fast feedforward 3D reconstruction from a single image, developed in collaboration between Tripo AI and Stability AI. https://huggingface.co/spaces/stabilityai/TripoSR

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

SILMA Arabic TTS v1 Official Repo — a Lightweight Open Bilingual (Arabic & English) Text to Speech Model

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

首家工业级全流程 AI 影视生产平台。Industry-first professional AI Agent platform for controllable film & video production. From shorts to live-action with Hollywood-standard workflows.