Potat1
The first open-source 1024x576 text-to-video model, fine-tuned from a base model
Downloads 56
Release Time : 6/5/2023
Model Overview
Potat 1 is a text-to-video generation model capable of producing high-quality video content based on input text descriptions.
Model Features
High-resolution video generation
Supports generating high-quality videos at 1024x576 resolution
Multi-stage training model
Provides models trained from 5,000 to 50,000 steps across multiple stages
Open-source dataset
Training dataset is publicly available, containing 2,197 video clips and 68,388 annotated frames
Model Capabilities
Text-to-video conversion
High-resolution video generation
Dynamic content generation based on text descriptions
Use Cases
Creative content generation
Short video creation
Automatically generates creative short videos based on text descriptions
Can produce video clips at 1024x576 resolution
Educational content
Educational video generation
Automatically generates supporting video content based on curriculum
Featured Recommended AI Models