---
license: apache-2.0
language:
- en
base_model:
- Wan-AI/Wan2.1-T2V-14B
tags:
- text-to-video
- lora
- diffusers
- template:diffusion-lora
widget:
- text: >-
    [malone] a man with a beard and mustache, wearing a dark green baseball cap, singing and dancing, with a few blurred lights visible..
  output:
    url: videos/1742519489362__000000750_0.webp
- text: >-
    [malone] a man singing while holding a cigarette in his hand and dancing.
  output:
    url: videos/1742520256525__000000750_1.webp
    
- text: >-
    [malone] a man with a beard and mustache, wearing a dark green baseball cap, singing and dancing, with a few blurred lights visible..
  output:
    url: videos/1742522116718__000001000_0.mp4
- text: >-
    [malone] a man singing while holding a cigarette in his hand and dancing.
  output:
    url: videos/1742522882787__000001000_1.mp4
    
- text: >-
    [malone] a man with a beard and mustache, wearing a dark green baseball cap, singing and dancing, with a few blurred lights visible..
  output:
    url: videos/1742524740417__000001250_0.webp
- text: >-
    [malone] a man singing while holding a cigarette in his hand and dancing.
  output:
    url: videos/1742525503397__000001250_1.webp

---
# PostMalone Lora for WanVideo2.1
<Gallery />

- First 2 videos are from [750 steps trained]
- Middle 2 videos are from [1000 steps trained] which is available for download
- Last 2 videos are from [1250 steps trained]

## Trigger words

You should use `malone` to trigger the video generation.

## Using with Diffusers
```py
pip install git+https://github.com/huggingface/diffusers.git
```

```py
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)
```

## Download model

Weights for this model are available in Safetensors format.

[Download](/shauray/PostMalone_WanLora/tree/main) them in the Files & versions tab.