Global radar

Bring portraits to life! https://github.com/KwaiVGI/LivePortrait

MuseTalk is a cutting-edge video-to-video (V2V) lip-sync solution engineered to deliver highly accurate and natural mouth movements synchronized to audio input. Precision LipSync: Realistic and seamless synchronization of speech audio to facial movements. Efficiently designed to run on 8–12 GB VRAM,

AI Song Generation with Full Style Control - Generate complete songs with lyrics, vocals, and instrumental tracks using Tencent AI Lab's SongGeneration (LeVo) model. [NVIDIA ONLY]

(WINDOWS)NVIDIA, Hallo2: Long-Duration and High-Resolution Audio-driven Portrait Image Animation

Self-hosted AI workspace for local-first chat, agents, tools, memory, research, documents, email, and model endpoint management.

Free LLM API server with dashboard

Qwen3-TTS is an open-source series of TTS models developed by the Qwen team

A privacy-respecting metasearch engine that runs locally.

[NVIDIA ONLY] Make virtual avatars talk whatever you want with an image and an audio clip https://github.com/antgroup/echomimic_v2

Multi-voice text-to-speech for stories and audiobooks, with local and cloud TTS engines plus optional LLM text processing.

User-friendly WebUI for LLMs, supported LLM runners include Ollama and OpenAI-compatible APIs https://github.com/open-webui/open-webui

MAGNeT is a text-to-music and text-to-sound model capable of generating high-quality audio samples conditioned on text descriptions https://github.com/facebookresearch/audiocraft/blob/main/docs/MAGNET.md

[AMD ONLY] All-in-one local AI video, image & music studio built on the WanGP pipeline (Wan 2.1/2.2, LTX-2.3, Qwen, Hunyuan Video, Flux). ROCm-powered. Supported on Windows and Linux for RDNA 2-4 dGPUs (RX 6000/7000/8000/9000) and gfx1150-53 APUs (Strix Point/Halo, Krackan Point/Halo). 6 GB+ VRAM recommended. For NVIDIA GPUs use the upstream Maestro app. Credits: the app itself is Maestro by Blizaine (github.com/Blizaine/Maestro) — this is just an AMD installer wrapper around it. The clone-at-install-time approach used to port it to AMD was pioneered by 6Morpheus6's wan2gp-amd (github.com/6Morpheus6/wan2gp-amd).

Irodori-TTS is a Flow Matching-based Text-to-Speech Model with Emoji-driven Style Control

1-click MiniMax H3 video in ComfyUI plus H3 Studio: local T2V/I2V, references, continuation, Gallery, Director/Cinema and TR/EN. NVIDIA GPU.

A local creation studio, forked from Maestro, for directing persistent worlds across video, images, sound, comics and 3D. Includes recoverable Director pipelines and optimized MiniMax H3 generation. Requires an NVIDIA GPU (6GB+ VRAM).

Install AnimateDiff Automatic1111 Extension and the models with one click

[AMD ONLY] All-in-one local AI video, image & music studio built on the WanGP pipeline (Wan 2.1/2.2, LTX-2.3, Qwen, Hunyuan Video, Flux). ROCm-powered. Supported on Windows and Linux for RDNA 2-4 dGPUs (RX 6000/7000/8000/9000) and gfx1150-53 APUs (Strix Point/Halo, Krackan Point/Halo). 6 GB+ VRAM recommended. For NVIDIA GPUs use the upstream Maestro app. Credits: the app itself is Maestro by Blizaine (github.com/Blizaine/Maestro) — this is just an AMD installer wrapper around it. The clone-at-install-time approach used to port it to AMD was pioneered by 6Morpheus6's wan2gp-amd (github.com/6Morpheus6/wan2gp-amd).

[Runs fast on NVIDIA GPUs. Works on M1/M2/M3 Macs but slow] VideoCrafter is an open-source video generation and editing toolbox for crafting video content. It currently includes the Text2Video and Image2Video models https://github.com/AILab-CVC/VideoCrafter

Local MiniMax Music3 studio fork for Windows + NVIDIA GPUs.