oxide-lab/Wan2.1-T2V-1.3B

Wan in Rust (Candle)

This repository provides a high-performance, native Rust implementation of Wan2.1 using the Candle ML framework.

Features

• 🦀 Native Rust: No Python dependency required for inference.
• 🚀 Performance: Optimized for NVIDIA GPUs with Flash Attention v2 and cuDNN.
• 💾 Memory Efficient: Supports GGUF quantization for UMT5-XXL text encoder and VAE tiling/slicing for generating videos on consumer GPUs.
• 🛠 Flexible: Easy to use CLI for video generation and library for custom integration.

Quick Start

Installation

Ensure you have Rust and the CUDA Toolkit installed, then:

git clone https://github.com/FerrisMind/candle-video
cd candle-video
cargo build --release --features flash-attn,cudnn

Video Generation

cargo run --example wan --release -- \
    --local-weights ./models/wan-video \
    --prompt "A serene mountain lake at sunset, photorealistic, 4k" 

Credits

• Original Model: Wan-AI/Wan2.1-T2V-1.3B
• Framework: HuggingFace Candle
• UMT5 XXL GGUF: city96/umt5-xxl-encoder-gguf (for GGUF support patterns, T5 XXl GGUF and Safetensors)

---

For more details, visit the main GitHub Repository.