wan25-fp8-i2v

wan25-fp8-i2v/
├── diffusion_models/
│   └── wan/              # Base WAN 2.5 I2V models (empty)
└── README.md             # This file (15KB)

from diffusers import DiffusionPipeline, AutoencoderKL
from PIL import Image
import torch

# Load WAN 2.5 FP8 I2V model (when released)
pipe = DiffusionPipeline.from_single_file(
    "E:/huggingface/wan25-fp8-i2v/diffusion_models/wan/wan25-i2v-14b-fp8-high-scaled.safetensors",
    torch_dtype=torch.float8_e4m3fn,  # FP8 precision
)

# Load shared VAE from wan25-vae repository
pipe.vae = AutoencoderKL.from_single_file(
    "E:/huggingface/wan25-vae/vae/wan25-vae-fp8.safetensors",
    torch_dtype=torch.float8_e4m3fn
)

pipe.to("cuda")

# Load input image
input_image = Image.open("input.jpg")

# Generate video from static image
video = pipe(
    image=input_image,
    prompt="The scene comes to life with gentle, natural movement",
    num_frames=48,              # 2 seconds at 24fps
    num_inference_steps=40,
    guidance_scale=6.5,
    motion_intensity=0.7        # Control motion strength (0-1)
).frames

# Save video
from diffusers.utils import export_to_video
export_to_video(video, "animated_output.mp4", fps=24)

# Use low-scaled variant for faster inference (lower VRAM)
pipe_low = DiffusionPipeline.from_single_file(
    "E:/huggingface/wan25-fp8-i2v/diffusion_models/wan/wan25-i2v-14b-fp8-low-scaled.safetensors",
    torch_dtype=torch.float8_e4m3fn
)

# Use high-scaled variant for maximum quality
pipe_high = DiffusionPipeline.from_single_file(
    "E:/huggingface/wan25-fp8-i2v/diffusion_models/wan/wan25-i2v-14b-fp8-high-scaled.safetensors",
    torch_dtype=torch.float8_e4m3fn
)

# Generate with high quality model
portrait_image = Image.open("portrait.jpg")
video = pipe_high(
    image=portrait_image,
    prompt="Subtle facial expressions and natural head movement",
    num_frames=48,
    guidance_scale=7.0
).frames

@misc{wan25-i2v-fp8,
  title={WAN 2.5 I2V: Advanced Image-to-Video Generation with FP8 Optimization},
  author={WAN Team},
  year={2025},
  howpublished={\url{https://huggingface.co/wan-models/wan-2.5-fp8-i2v}},
  note={FP8-optimized image-to-video generation model with 14B parameters}
}