X-VC Voice Conversion
Zero-shot streaming voice conversion in codec space
Animate bounding boxes into video, one prompt per box
Generate and outpaint seamless 360° panoramas with Krea 2
Omni-modal image, audio and video understanding
Generate 8-panel cinematic storyboards from text prompts
Steer a 3D camera path through any still image
Generate custom music tracks from text captions and lyrics
Qwen3-VL 33B prompt conditioning as a service
Find when a described sound happens in a recording
Dense fine-grained image captioning with Qwen3-VL-4B
Proactive real-time commentary on audio-video streams