PostMalone_WanLora Open-Source Model - Free Generation of Text-to-Video Content in Post Malone Style

Postmalone WanLora

Developed by shauray

This is a LoRA fine-tuned version based on the Wan2.1-T2V-14B model, specifically designed for generating PostMalone-style text-to-video content.

Text-to-Video EnglishOpen Source License:Apache-2.0 #PostMalone-style video generation #LoRA fine-tuned diffusion model #Text-driven video synthesis

Downloads 24

Release Time : 3/21/2025

Model Overview

Through LoRA fine-tuning technology, this model achieves PostMalone-style video generation capabilities on the Wan2.1-T2V-14B base model, enabling the creation of dynamic videos with specific styles based on text descriptions.

Model Features

LoRA fine-tuning

Efficiently fine-tunes the base model using LoRA technology to achieve specific style generation.

Trigger word control

Controls the style of generated videos through the specific trigger word 'malone'.

Multi-version training

Provides three model versions trained at different steps: 750, 1000, and 1250 steps.

Model Capabilities

Text-to-video generation

Stylized video generation

Dynamic content generation

Use Cases

Entertainment content creation

Music video generation

Generates PostMalone-style music performance videos based on descriptions.

Examples showcase performance videos featuring specific outfits and actions.

🚀 PostMalone Lora for WanVideo2.1

This is a LoRA model for WanVideo2.1 that can generate videos featuring Post Malone. It provides different training steps and offers a simple way to generate videos using the Diffusers library.

🚀 Quick Start

Gallery

The first 2 videos are from [750 steps trained].
The middle 2 videos are from [1000 steps trained] which is available for download.
The last 2 videos are from [1250 steps trained].

Trigger words

You should use malone to trigger the video generation.

✨ Features

Generate videos related to Post Malone using the malone trigger word.
Support different training steps for video generation.
Compatible with the Diffusers library for easy integration.

📦 Installation

pip install git+https://github.com/huggingface/diffusers.git

💻 Usage Examples

Basic Usage

import torch
from diffusers.utils import export_to_video
from diffusers import AutoencoderKLWan, WanPipeline
from diffusers.schedulers.scheduling_unipc_multistep import UniPCMultistepScheduler

# Available models: Wan-AI/Wan2.1-T2V-14B-Diffusers, Wan-AI/Wan2.1-T2V-1.3B-Diffusers
model_id = "Wan-AI/Wan2.1-T2V-14B-Diffusers"
vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
pipe = WanPipeline.from_pretrained(model_id, vae=vae, torch_dtype=torch.bfloat16)
flow_shift = 5.0  # 5.0 for 720P, 3.0 for 480P
pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config, flow_shift=flow_shift)
pipe.to("cuda")

pipe.load_lora_weights("shauray/PostMalone_WanLora")

pipe.enable_model_cpu_offload() #for low-vram environments

prompt = "malone a man walking through texas"

output = pipe(
    prompt=prompt,
    height=480,
    width=720,
    num_frames=81,
    guidance_scale=5.0,
).frames[0]
export_to_video(output, "output.mp4", fps=16)

📚 Documentation

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.

📄 License

This project is licensed under the Apache-2.0 license.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご