Wan 14b Laezel

🚀 Wan 14B Laezel

本项目是用于视频生成的LoRA模型，基于Wan2.1 14b视频生成模型，可用于文本到视频、图像到视频的生成任务，能与diffusers或ComfyUI结合使用。

🚀 快速开始

关于此LoRA

这是一个适用于Wan2.1 14b视频生成模型的LoRA。它可以与diffusers或ComfyUI配合使用，并且可以加载到文本到视频和图像到视频的Wan2.1模型中。它是在Replicate上使用AI工具包进行训练的：https://replicate.com/ostris/wan-lora-trainer/train 。

触发词

你应该使用 LAEZEL 来触发视频生成。

使用此LoRA

Replicate有一系列针对速度和成本进行了优化的Wan2.1模型，它们也可以与此LoRA一起使用：

• https://replicate.com/collections/wan-video
• https://replicate.com/fofr/wan2.1-with-lora

使用Replicate的API运行此LoRA

import replicate

input = {
    "prompt": "LAEZEL",
    "lora_url": "https://huggingface.co/fofr/wan-14b-laezel/resolve/main/wan2.1-14b-laezel-lora.safetensors"
}

output = replicate.run(
    "fofr/wan2.1-with-lora:f83b84064136a38415a3aff66c326f94c66859b8ad7a2cb432e2822774f07b08",
    model="14b",
    input=input
)
for index, item in enumerate(output):
    with open(f"output_{index}.mp4", "wb") as file:
        file.write(item.read())

与Diffusers一起使用

pip install git+https://github.com/huggingface/diffusers.git

import torch
from diffusers.utils import export_to_video
from diffusers import AutoencoderKLWan, WanPipeline
from diffusers.schedulers.scheduling_unipc_multistep import UniPCMultistepScheduler

model_id = "Wan-AI/Wan2.1-T2V-14B-Diffusers"
vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
pipe = WanPipeline.from_pretrained(model_id, vae=vae, torch_dtype=torch.bfloat16)
flow_shift = 3.0  # 5.0 for 720P, 3.0 for 480P
pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config, flow_shift=flow_shift)
pipe.to("cuda")

pipe.load_lora_weights("fofr/wan-14b-laezel")

pipe.enable_model_cpu_offload() #for low-vram environments

prompt = "LAEZEL"
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=16)

🔧 技术细节

🤝 贡献你自己的示例

你可以使用社区板块来添加展示你使用此LoRA所制作的视频。

📄 许可证

本项目采用Apache-2.0许可证。