Bailian Multimodal Skills

Generate images, audio, video, and transcribe speech using Aliyun Bailian (Qwen/Wan/PixVerse/Kling/CosyVoice) models.

Features

Image Generation: z-image-turbo, wan2.6-t2i, wan2.7-image-pro
Image Editing: wan2.7-image-pro
Video Editing: wan2.7-videoedit
ASR (Speech-to-Text): qwen3-asr-flash
TTS (Text-to-Speech): qwen3-tts-flash
Text-to-Video: wan2.7-t2v, wan2.6-t2v, pixverse/pixverse-v5.6-t2v, kling/kling-v3-video-generation
Image-to-Video: wan2.7-i2v, wan2.6-i2v-flash, wan2.6-i2v, pixverse/pixverse-v5.6-it2v, kling/kling-v3-video-generation
Reference-to-Video: wan2.6-r2v-flash, wan2.6-r2v, pixverse/pixverse-v5.6-r2v