ByteDance’s next-gen AI model can generate clips based on text, images, audio, and video

Source: The Verge

Overview

ByteDance, the China‑based company behind TikTok, announced its next‑gen video generator, Seedance 2.0, in a recent blog post. The model is designed to follow prompts more accurately and to produce higher‑quality video clips.

Features of Seedance 2.0

• Multimodal prompting – accepts a combination of text, images, video, and audio.
• Rich input limits – users can supply up to 9 images, 3 video clips, and 3 audio clips per prompt.
• Clip length – can generate video clips up to 15 seconds long, complete with synchronized audio.
• Improved generation quality – better at rendering complex scenes with multiple subjects and following detailed instructions.

Source

Read the full story at The Verge.