wan25-fp16-i2v-loras

# Enable memory-efficient attention
pipe.enable_xformers_memory_efficient_attention()

# Use CPU offloading for limited VRAM
pipe.enable_sequential_cpu_offload()

# Reduce precision for inference (if needed)
pipe.vae.to(dtype=torch.float16)
pipe.unet.to(dtype=torch.float16)

# Process multiple prompts efficiently
prompts = [
    "Scene 1 with camera pan",
    "Scene 2 with dramatic lighting",
    "Scene 3 with enhanced details"
]

videos = pipe(
    prompt=prompts,
    num_frames=48,
    height=512,
    width=768,
    num_inference_steps=30,
    guidance_scale=7.5
).frames

for i, video in enumerate(videos):
    export_to_video(video, f"batch_output_{i}.mp4", fps=24)