Qwen VLo: Unified multimodal understanding and generation model from Alibaba

Alibaba releases Qwen VLo, a unified multimodal model that both understands and generates images. It supports open-ended editing, multilingual instructions, dynamic resolution, and progressive generation from top to bottom and left to right. Available as a preview on Qwen Chat.

Alibaba/Qwen

Qwen-TTS now speaks dialects: new Alibaba speech synthesizer

Alibaba Cloud has updated Qwen-TTS, a text-to-speech model that supports 3 Chinese dialects (Pekingese, Shanghainese, Sichuanese) and 7 bilingual Chinese-English voices. The model achieves human-level naturalness and expressiveness, available via Qwen API.

Alibaba/Qwen