Pinned Loading

1. ACE-Step-1.5 ACE-Step-1.5 Public

   Forked from ace-step/ACE-Step-1.5

   The most powerful local music generation model that outperforms most commercial alternatives

   Python

2. CosyVoice CosyVoice Public

   Forked from FunAudioLLM/CosyVoice

   Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

   Python

3. HunyuanVideo-Foley HunyuanVideo-Foley Public

   Forked from Tencent-Hunyuan/HunyuanVideo-Foley

   HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation.

   Python

4. Ovi Ovi Public

   Forked from character-ai/Ovi

   Python