view reply This is really ecouraging for local tts potential. Do you have any idea if the latency would be suitable for realtime chat?
MagicVideo-V2: Multi-Stage High-Aesthetic Video Generation Paper โข 2401.04468 โข Published Jan 9 โข 48
AutoStory: Generating Diverse Storytelling Images with Minimal Human Effort Paper โข 2311.11243 โข Published Nov 19, 2023 โข 14