Cat Text To Video 2.3b
C
Cat Text To Video 2.3b
Developed by motexture
A text-to-video model based on conditional enhancement, extending generated segments and achieving smooth transitions through temporal condition transformers, supporting prompt interpolation functionality
Downloads 25
Release Time : 1/22/2025
Model Overview
This model adopts the pre-trained weights of the ModelScope text-to-video model and enhances them with temporal condition transformers to extend generated segments and achieve smooth transitions between segments. It also supports prompt interpolation, enabling scene switching during segment extension.
Model Features
Temporal Condition Transformer
Enhanced with temporal condition transformers, enabling the extension of generated segments and smooth transitions between segments.
Prompt Interpolation
Supports scene switching during segment extension, achieving natural transitions between different scenes.
High-Resolution Generation
Supports video generation at 320x320 resolution.
Model Capabilities
Text-to-Video Generation
Video Segment Extension
Scene Transition
Use Cases
Creative Content Generation
Action Scene Transition
Smoothly transition from a cycling scene to a motorcycle riding scene
Man riding a bicycle -> Man riding a motorcycle
Character Action Change
Show a natural transition of a person from eating a hamburger to eating ice cream
Will Smith eating a hamburger -> Will Smith eating ice cream
Animation Generation
Anime Character Expression Change
Generate an animation of an anime girl transitioning from a static pose to laughing
Beautiful anime girl with pink hair -> Anime girl laughing
Featured Recommended AI Models