Instructions to use xilanhua12138/Wan2.1-T2V-1.3B-Reward with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use xilanhua12138/Wan2.1-T2V-1.3B-Reward with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("xilanhua12138/Wan2.1-T2V-1.3B-Reward", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
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
| Original | After Reward |
|---|---|
480x832 Resolution
| Original | After Reward |
|---|---|
- Downloads last month
- 24
Model tree for xilanhua12138/Wan2.1-T2V-1.3B-Reward
Base model
Wan-AI/Wan2.1-T2V-1.3B