Guidelines for Multimodal Video Creation

Produce high-quality video content by utilizing detailed text instructions from a reference image to bypass character constraints in standard inputs.

プロンプト

Generate a video based on the text description in the reference image.

詳細
モデルSeedance 2.0 Fast
解像度720p
アスペクト比9:16
ソース

さらに見る

すべて見る →