Wan2.1 T2V 1.3B Crush Smol V0

🚀 LoRA Fine-tuned Text-to-Video Model

This project is a LoRA fine-tune of the Wan-AI/Wan2.1-T2V-1.3B-Diffusers model on the finetrainers/crush-smol dataset, aiming to enhance the text-to-video generation capabilities.

✨ Features

• Text-to-Video Generation: Generate videos based on text descriptions.
• Diffusers Integration: Utilize the diffusers library for model training and inference.
• LoRA Fine-tuning: Fine-tune the base model using LoRA to improve performance.

📦 Installation

The installation process mainly involves setting up the diffusers library and related dependencies. You can follow the official documentation of diffusers for installation steps.

💻 Usage Examples

Basic Usage

import torch
from diffusers import WanPipeline
from diffusers.utils import export_to_video

pipe = WanPipeline.from_pretrained(
    "Wan-AI/Wan2.1-T2V-1.3B-Diffusers", torch_dtype=torch.bfloat16
).to("cuda")
pipe.load_lora_weights("finetrainers/Wan2.1-T2V-1.3B-crush-smol-v0", adapter_name="wan-lora")
pipe.set_adapters(["wan-lora"], [0.75])

video = pipe("<my-awesome-prompt>").frames[0]
export_to_video(video, "output.mp4", fps=24)

Advanced Usage

You can adjust the parameters in the code according to your specific needs, such as changing the prompt, adjusting the LoRA weight, etc.

📚 Documentation

• Code Repository: https://github.com/a-r-r-o-w/finetrainers
• Training Logs: Available on WandB here

📄 License

This project is under the other license.

⚠️ Important Note

This is an experimental checkpoint and its poor generalization is well-known.