wan21-fp16-480p

from diffusers import DiffusionPipeline
import torch

# Load model with memory optimizations
pipe = DiffusionPipeline.from_single_file(
    "E:/huggingface/wan21-fp16-480p/diffusion_models/wan/wan21-i2v-480p-14b-fp16.safetensors",
    torch_dtype=torch.float16,
    use_safetensors=True
)

# Enable memory-efficient attention
pipe.enable_attention_slicing()
pipe.enable_vae_slicing()

# For even lower VRAM usage
pipe.enable_model_cpu_offload()

pipe.to("cuda")

# Generate video with optimizations
video = pipe(
    image=input_image,
    prompt="your prompt here",
    num_frames=16,  # Reduce frames for lower memory
    num_inference_steps=30,  # Fewer steps for faster generation
    guidance_scale=7.5
).frames[0]

# Enable all memory optimizations
pipe.enable_attention_slicing()
pipe.enable_vae_slicing()
pipe.enable_model_cpu_offload()

# Reduce generation parameters
num_frames=16  # Instead of 24
num_inference_steps=30  # Instead of 50