🐎 Alibaba introduces Happy Horse 1.1 model for image-to-video generation
The new Happy Horse 1.1 model specializes in the Image-to-Video (I2V) task. It allows animating images in 720p/1080p resolution for up to 15 seconds, using up to 9 reference frames to maintain consistency. A key feature is the support for synchronized audio and multilingual lip-sync.
🌍 The emergence of high-quality I2V models from Alibaba brings AI tools closer to professional production levels.
👤 Users can now create videos where characters speak realistically in different languages.
Source 1: https://fal.ai/models/alibaba/happy-horse/v1.1/image-to-video Source 2: https://x.com/HappyHorseATH/status/2068941160584974753