W

Wan2.1 Fun V1.1 1.3B InP

Developed by alibaba-pai
A 1.3B parameter text-to-video model supporting multi-resolution training with first/last frame prediction capability
Downloads 93
Release Time : 4/24/2025

Model Overview

This is a text-to-video model based on Diffusion-Transformer architecture that can generate high-quality video content from text descriptions, supporting multiple output resolutions.

Model Features

Multi-resolution support
Supports video generation at various resolutions including 512/768/1024
First/last frame prediction
Capable of predicting video's first and last frames to improve continuity
Multi-language support
Supports text input in both Chinese and English for video generation

Model Capabilities

Text-to-video generation
Multi-resolution video generation
First/last frame prediction
Multi-language support

Use Cases

Creative content generation
Short video creation
Automatically generate creative short videos from text descriptions
Can generate 81-frame videos at 16fps
Advertisement production
Quickly generate product showcase videos
Supports various product display effects
Education & entertainment
Animation production
Convert story text into animated videos
Can generate coherent animation effects
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase