Wan 14b Cyberpunk Realistic

🚀 Wan 14B 賽博朋克寫實風格（圖像轉視頻）

本項目是一個圖像轉視頻的模型，基於LoRA技術對Wan2.1 14b視頻生成模型進行優化，可用於生成具有賽博朋克寫實風格的視頻。

🚀 快速開始

關於此LoRA

這是適用於Wan2.1 14b視頻生成模型的 LoRA。它可以與Diffusers或ComfyUI配合使用，並且可以加載到文本轉視頻和圖像轉視頻的Wan2.1模型中。該模型在 Replicate 上使用AI工具包進行訓練：https://replicate.com/ostris/wan-lora-trainer/train 。

觸發詞

你應該使用 CYB77 或 “In the style of CYB77” 來觸發視頻生成。

使用此LoRA

Replicate 有一系列針對速度和成本進行優化的Wan2.1模型，它們也可以與此LoRA一起使用：

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

使用Replicate的API運行此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())

與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)

🔧 技術細節

訓練詳情

🤝 貢獻你自己的示例

你可以使用 社區板塊 來添加展示你使用此LoRA創作成果的視頻。

📄 許可證

本項目採用Apache-2.0許可證。