HuMo is a unified, human-centered video generation framework that can generate high-quality, fine-grained, and controllable human videos based on multimodal inputs such as text, images, and audio. It supports powerful text prompt following, consistent subject retention, and synchronized audio-driven motion.

MultimodalGguf

HuMo is a human-centered video generation framework that can generate high-quality, fine-grained, and controllable human videos using multimodal inputs such as text, images, and audio. It supports text prompt following, subject retention, and audio-driven motion synchronization.

MultimodalGguf

Wan2.2-S2V-14B is a Mixture of Experts (MoE) model designed for audio-driven cinema-level video generation. It can generate high-quality video content based on input audio, reference images, and text prompts, supports 480P and 720P resolutions, and features complex motion generation and cinema-level aesthetic effects.

MultimodalDiffusersSpanish

JoyVASA is an audio-driven facial animation generation method based on diffusion models, capable of generating facial dynamics and head movements with support for multilingual input.

JoyHallo is a Mandarin-focused audio-driven facial animation generation model capable of producing realistic facial animations from Mandarin speech.