metadata
language:
- en
base_model:
- Wan-AI/Wan2.1-T2V-1.3B
pipeline_tag: text-to-video
library_name: diffusers
license: apache-2.0
Quik Start
import torch
from diffusers import AutoencoderKLWan, WanPipeline
from diffusers.utils import export_to_video
model_id = "xilanhua12138/Wan2.1-T2V-1.3B-Reward"
vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
pipe = WanPipeline.from_pretrained(model_id, vae=vae, torch_dtype=torch.bfloat16)
pipe.to("cuda")
prompt = "A cat walks on the grass, realistic"
negative_prompt = "Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards"
output = pipe(
prompt=prompt,
negative_prompt=negative_prompt,
height=480,
width=832,
num_frames=81,
guidance_scale=5.0
).frames[0]
export_to_video(output, "output.mp4", fps=15)
384x672 Resolution
480x832 Resolution
