wan22-fp16-encoders

from diffusers import DiffusionPipeline
import torch

# Load WAN2.2 pipeline with custom text encoders
pipe = DiffusionPipeline.from_pretrained(
    "your-wan22-model",
    text_encoder_path="E:/huggingface/wan22-fp16-encoders/text_encoders/t5-xxl-fp16.safetensors",
    torch_dtype=torch.float16,
    variant="fp16"
).to("cuda")

# Generate video from text
prompt = "A serene mountain landscape at sunset with flowing clouds"
video = pipe(prompt, num_frames=24, height=512, width=512).frames

# Save output
video[0].save("output_video.mp4")

from diffusers import DiffusionPipeline
import torch

# Load with multilingual encoder
pipe = DiffusionPipeline.from_pretrained(
    "your-wan22-model",
    text_encoder_path="E:/huggingface/wan22-fp16-encoders/text_encoders/umt5-xxl-fp16.safetensors",
    torch_dtype=torch.float16,
).to("cuda")

# Generate with multilingual prompt
prompt = "東京の夜景、ネオンライトと雨"  # Japanese: Tokyo nightscape with neon lights and rain
video = pipe(prompt, num_frames=48, height=768, width=768).frames

from diffusers import DiffusionPipeline
import torch

# Enable CPU offloading for lower VRAM systems
pipe = DiffusionPipeline.from_pretrained(
    "your-wan22-model",
    text_encoder_path="E:/huggingface/wan22-fp16-encoders/text_encoders/t5-xxl-fp16.safetensors",
    torch_dtype=torch.float16,
).to("cuda")

# Enable model CPU offload
pipe.enable_model_cpu_offload()

# Enable attention slicing for further memory reduction
pipe.enable_attention_slicing(1)

# Generate with reduced memory footprint
video = pipe(prompt, num_frames=16).frames