ByteDance recently launched a new feature for the Doubao app - Image Understanding. The Doubao app and PC version have added photo and camera buttons, allowing users to upload images for the system to recognize their content. The image understanding feature of Doubao is not limited to text recognition; it can also analyze image content and even understand and explain jokes.

ByteDance Douyin Doubao Large Model

As a large model AI assistant under ByteDance, Doubao already supports various functions such as text generation and image generation.

Previously, Doubao was in the beta testing phase for its video generation feature. The official Doubao website states that the video generation function supports converting images and text into vivid and realistic video content with one click. Users can choose different styles and ratios according to their needs and add dynamic and camera effects to achieve consistency across multiple shots, creating unique video content.