Media & Creative · CUDA · For developers

Train a custom VideoHighlighter action or object model from a few videos the user provides — cut into samples, sort with CLIP, review contact sheets, build, train, install only if better.

Aseiel/VideoHighlighter

Integrate a new text-to-speech model into vLLM-Omni from HuggingFace reference implementation through production-ready serving with streaming and CUDA graph acceleration.

vllm-project/vllm-omni

Set up and run HeartMuLa, the open-source music generation model family (Suno-like).

RedWoodOG/Hermes-Desktop

HeartMuLa: Suno-like song generation from lyrics + tags. An agent skill from Luciole-Studio/Misaka-Agent.

Luciole-Studio/Misaka-Agent

A skill your agent uses when authoring or validating PAIDF augmentation YAML configs, or running remote Cosmos Transfer (including Cosmos3 WSM controls), Cosmos Predict, image-edit, or…

NVIDIA/skills

Use this repo skill for DiscoArt image generation, configuration/prompt scheduling, CLI, Jina serving, Docker runtime planning, and troubleshooting.

VectorSpaceLab/AREX-Skill

Use this operating skill for Tencent-Hunyuan/HunyuanVideo text-to-video setup, checkpoint layout, inference commands, Gradio launch, and CUDA/FP8/xDiT troubleshooting.

VectorSpaceLab/AREX-Skill