import torch
from diffusers import DiffusionPipeline
from diffusers.utils import export_to_video
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Wan-AI/Wan2.2-T2V-A14B", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("obsxrver/Wan2.2_GTA-Style")
prompt = "A man with short gray hair plays a red electric guitar."
output = pipe(prompt=prompt).frames[0]
export_to_video(output, "output.mp4")Wan 2.2 GTA Style
Just a little side project I whipped together for fun. Generates GTA-Style driving videos. I just made it and haven't really experimented all that much yet. But it captures the GTA Aesthetic pretty well. Include gta style in your prompt to activate it.
gta style, a black supercar is driving down the road, speeding past other cars, cyberpunk chinese city, raining, nighttime
gta style, a red sports car is driving quickly on a highway overpass, through a megacity filled with futuristic skyscrapers, overcast, thunderstorming, lightning streaks in distance
My Generation Settings:
LightX2V V1.1 4-step Lora: Strength 0.7
10 Steps
High Noise: 5 steps, Res_Multistep, Simple, Add Noise On, Return Leftover noise On
High Noise: 5 steps, Res_Multistep, Simple, Add noise off, return leftover noise off
- Downloads last month
- 41
Model tree for obsxrver/Wan2.2_GTA-Style
Base model
Wan-AI/Wan2.2-T2V-A14B