W

Wan2.1 T2V 1.3B

Developed by Isi99999
Wan 2.1 is a comprehensive open-source video foundation model designed to push the boundaries of video generation, supporting tasks like text-to-video and image-to-video in both Chinese and English.
Downloads 40
Release Time : 2/27/2025

Model Overview

Wan 2.1 is an advanced video generation model capable of text-to-video, image-to-video, video editing, text-to-image, and video-to-audio tasks, featuring top-tier performance and high computational efficiency.

Model Features

Top-tier Performance
Outperforms existing open-source models and commercial solutions across multiple benchmarks.
Consumer-GPU Support
The T2V-1.3B model requires only 8.19GB VRAM, compatible with almost all consumer-grade GPUs.
Multi-task Support
Covers text-to-video, image-to-video, video editing, text-to-image, and video-to-audio tasks.
Visual Text Generation
The first video model supporting bilingual (Chinese-English) text generation with powerful text-to-video capabilities.
Efficient Video VAE
Wan-VAE preserves temporal information when encoding/decoding arbitrary-length 1080P videos, providing an ideal foundation for video and image generation.

Model Capabilities

Text-to-video
Image-to-video
Video editing
Text-to-image
Video-to-audio

Use Cases

Creative Video Production
Anthropomorphic Animal Videos
Generate videos of anthropomorphic animal behaviors, such as cats boxing.
Generating a 5-second 480P video takes approximately 4 minutes (RTX 4090).
Educational Content
Educational Video Generation
Generate instructional videos based on text descriptions.
Featured Recommended AI Models
ยฉ 2025AIbase