Video Seedance 2.0 officially launched! Kill the game!
Remember from the day when we could only "tell a story" using text and the first/last frames, we've always wanted to create a video model that truly understands your expression. Today, it's finally here!
Seedance 2.0 now supports four modalities of input: images, videos, audio, and text, offering richer expression and more controllable generation.
You can set the style of the scene with a single image, specify the character's actions and camera changes with a video, and then set the rhythm and atmosphere with a few seconds of audio... With the help of prompts, the creative process becomes more natural, more efficient, and more like a real "director."
The biggest highlight of this upgrade is the "reference ability":
- Reference images can accurately reproduce the composition and character details of the scene
- Reference videos support the replication of camera language, complex action rhythms, and creative special effects
- Videos support smooth extension and connection, allowing the generation of continuous shots based on user prompts, not just generating but also "continuing to shoot"
- Editing capabilities are also enhanced, supporting role replacement, deletion, and addition to existing videos
Video Seedance 2.0 officially launched! Kill the game!
Remember from the day when we could only "tell a story" using text and the first/last frames, we've always wanted to create a video model that truly understands your expression. Today, it's finally here!
Seedance 2.0 now supports four modalities of input: images, videos, audio, and text, offering richer expression and more controllable generation.
You can set the style of the scene with a single image, specify the character's actions and camera changes with a video, and then set the rhythm and atmosphere with a few seconds of audio... With the help of prompts, the creative process becomes more natural, more efficient, and more like a real "director."
The biggest highlight of this upgrade is the "reference ability":
- Reference images can accurately reproduce the composition and character details of the scene
- Reference videos support the replication of camera language, complex action rhythms, and creative special effects
- Videos support smooth extension and connection, allowing the generation of continuous shots based on user prompts, not just generating but also "continuing to shoot"
- Editing capabilities are also enhanced, supporting role replacement, deletion, and addition to existing videos