AI Agent Skills

[CVPR 2025] MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis

A unified inference and post-training framework for accelerated video generation.

Toonflow 是开源一站式 AI 短剧创作工具，将小说、剧本快速转化为动画短剧。集成 AI 编剧、智能分镜、角色与视频生成，跨平台桌面端轻量部署，助力创作者低成本批量产出视觉内容。Toonflow is an open-source AI tool that turns stories and scripts into animat…

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

FLUX, Stable Diffusion, SDXL, SD3, LoRA, Fine Tuning, DreamBooth, Training, Automatic1111, Forge WebUI, SwarmUI, DeepFake, TTS, Animation, Text To Video, Tutorials, Guid…

[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.