README.md

---
license: mit
base_model:
- Wan-AI/Wan2.2-I2V-A14B-Diffusers
- lightx2v/Wan2.2-Lightning
pipeline_tag: image-to-video
---
This model is a merger of [Wan-AI/Wan2.2-I2V-A14B-Diffusers](https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B-Diffusers) and [Wan2.2-Lightning v1 model](https://huggingface.co/lightx2v/Wan2.2-Lightning/tree/main/Wan2.2-I2V-A14B-4steps-lora-rank64-Seko-V1), it can be run with diffusers pipeline.

Running with [FastDM](https://github.com/KE-AI-ENG/FastDM):

```
python gen.py --model-path FastDM/Wan2.2-I2V-A14B-Merge-Lightning-V1.0-Diffusers --architecture wan-i2v --guidance-scale 1.0 --height 480 --width 832 --steps 4 --use-fp8 --output-path ./output.mp4 --num-frames 81 --fps 16 --task i2v --prompts [PROMPTS] --image-path [PATH/TO/IMAGE]
```

Running with diffusers:
```python
import torch
import numpy as np
from diffusers import WanImageToVideoPipeline
from diffusers.utils import export_to_video, load_image

model_id = "FastDM/Wan2.2-I2V-A14B-Merge-Lightning-V1.0-Diffusers"
dtype = torch.bfloat16
device = "cuda"

pipe = WanImageToVideoPipeline.from_pretrained(model_id, torch_dtype=dtype)
pipe.to(device)


image = load_image(
    "https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/wan_i2v_input.JPG"
)
max_area = 480 * 832
aspect_ratio = image.height / image.width
mod_value = pipe.vae_scale_factor_spatial * pipe.transformer.config.patch_size[1]
height = round(np.sqrt(max_area * aspect_ratio)) // mod_value * mod_value
width = round(np.sqrt(max_area / aspect_ratio)) // mod_value * mod_value
image = image.resize((width, height))
prompt = "Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard. The fluffy-furred feline gazes directly at the camera with a relaxed expression. Blurred beach scenery forms the background featuring crystal-clear waters, distant green hills, and a blue sky dotted with white clouds. The cat assumes a naturally relaxed posture, as if savoring the sea breeze and warm sunlight. A close-up shot highlights the feline's intricate details and the refreshing atmosphere of the seaside."

negative_prompt = "色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走"
generator = torch.Generator(device=device).manual_seed(0)
output = pipe(
    image=image,
    prompt=prompt,
    negative_prompt=negative_prompt,
    height=height,
    width=width,
    num_frames=81,
    guidance_scale=1.0,
    num_inference_steps=4,
    generator=generator,
).frames[0]
export_to_video(output, "i2v_output.mp4", fps=16)

```