Wan 14b Cyberpunk Realistic

🚀 Wan 14B 赛博朋克写实风格（图像转视频）

本项目是一个图像转视频的模型，基于LoRA技术对Wan2.1 14b视频生成模型进行优化，可用于生成具有赛博朋克写实风格的视频。

🚀 快速开始

关于此LoRA

这是适用于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转视频和图像转视频的Wan2.1模型中。该模型在 Replicate 上使用AI工具包进行训练：https://replicate.com/ostris/wan-lora-trainer/train 。

触发词

你应该使用 CYB77 或 “In the style of CYB77” 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": "CYB77",
    "image": "https://replicate.delivery/xezq/4BGR8w4ELvJfcqIG4KIF0Kr82JxtfQCM2xVAIUieSeifmTZjC/output_frame.jpg",
    "lora_url": "https://huggingface.co/fofr/wan-14b-cyberpunk-realistic/resolve/main/wan-14b-i2v-cyberpunk-realistic-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-cyberpunk-realistic")

pipe.enable_model_cpu_offload() #for low-vram environments

prompt = "CYB77"
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

训练详情

🤝 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创作成果的视频。

📄 许可证

本项目采用Apache-2.0许可证。