Text-to-Video
Diffusers
wan
video
text-to-image
image-to-video
video-to-video
diffusion-pipe
lora
template:sd-lora
standard
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-TI2V-5B", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("AlekseyCalvin/UkraineWar_wan2.2_5B_ti2vLoRA")
prompt = "UKR footage clip..."
output = pipe(prompt=prompt).frames[0]
export_to_video(output, "output.mp4")Impacts of War: Ukraine
A Low(ish) Rank Adapter (LoRA)
For Wan2.2 5B Text to Image to Video Model
||| By SilverAgePoets.com |||
Still This Nightmare History Remains...
A Rank64 LoRA for the Wan2.2 5B TI2V model, also accessible via HF Diffusers at this repo.
Fine-tuned using Ostris' ai-toolkit trainer...
...on a custom dataset consisting of 100s of open-domain/public record visual documents of certain catastrophic events, impacts, and consequences...
- Prompt
- UKR footage clip...
TRIGGERING:
[UKR] style war footage movie clip, in Ukraine, wartime scene, etc...
OTHER VARIANTS of this LoRA:
HERE is a Wan2.2 A14B-MoE-T2V version of this adapter.
HERE is a Wan2.1 1.3B-T2V version of this adapter.
HERE is a Wan2.1 14B-T2V version of this adapter.
- Downloads last month
- 20
Model tree for AlekseyCalvin/UkraineWar_wan2.2_5B_ti2vLoRA
Base model
Wan-AI/Wan2.2-TI2V-5B