AI Gallery 资产详情

您的余额不足，模型已暂停发布查看详情

!pip install diffusers transformers accelerate MoviePy

显示 output

Looking in indexes: http://repo.myhuaweicloud.com/repository/pypi/simple
Collecting diffusers
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/2e/ed/58a13f88dfcdd1bcfeabf44d4c9861979551339348e579fd6559c64b12e0/diffusers-0.21.4-py3-none-any.whl (1.5 MB)
     |████████████████████████████████| 1.5 MB 30.3 MB/s eta 0:00:01
Collecting transformers
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/5b/0b/e45d26ccd28568013523e04f325432ea88a442b4e3020b757cf4361f0120/transformers-4.30.2-py3-none-any.whl (7.2 MB)
     |████████████████████████████████| 7.2 MB 64.8 MB/s eta 0:00:01
Collecting accelerate
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/10/d3/5382aa337d3e67214003a17b06bfc07cf0334356b4e8aaf3b12b0d38c83f/accelerate-0.20.3-py3-none-any.whl (227 kB)
     |████████████████████████████████| 227 kB 28.8 MB/s eta 0:00:01
Requirement already satisfied: MoviePy in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (1.0.3)
Requirement already satisfied: psutil in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (from accelerate) (5.8.0)
Requirement already satisfied: numpy>=1.17 in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (from accelerate) (1.19.5)
Requirement already satisfied: torch>=1.6.0 in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (from accelerate) (1.13.1)
Requirement already satisfied: packaging>=20.0 in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (from accelerate) (21.3)
Requirement already satisfied: pyyaml in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (from accelerate) (6.0.1)
Requirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (from packaging>=20.0->accelerate) (3.0.9)
Requirement already satisfied: nvidia-cublas-cu11==11.10.3.66 in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (from torch>=1.6.0->accelerate) (11.10.3.66)
Requirement already satisfied: typing-extensions in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (from torch>=1.6.0->accelerate) (4.4.0)
Requirement already satisfied: nvidia-cuda-runtime-cu11==11.7.99 in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (from torch>=1.6.0->accelerate) (11.7.99)
Requirement already satisfied: nvidia-cudnn-cu11==8.5.0.96 in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (from torch>=1.6.0->accelerate) (8.5.0.96)
Requirement already satisfied: nvidia-cuda-nvrtc-cu11==11.7.99 in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (from torch>=1.6.0->accelerate) (11.7.99)
Requirement already satisfied: setuptools in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (from nvidia-cublas-cu11==11.10.3.66->torch>=1.6.0->accelerate) (65.5.0)
Requirement already satisfied: wheel in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (from nvidia-cublas-cu11==11.10.3.66->torch>=1.6.0->accelerate) (0.37.1)
Requirement already satisfied: safetensors>=0.3.1 in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (from diffusers) (0.4.2)
Requirement already satisfied: importlib-metadata in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (from diffusers) (5.0.0)
Requirement already satisfied: regex!=2019.12.17 in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (from diffusers) (2023.12.25)
Requirement already satisfied: huggingface-hub>=0.13.2 in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (from diffusers) (0.16.4)
Requirement already satisfied: filelock in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (from diffusers) (3.12.2)
Requirement already satisfied: requests in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (from diffusers) (2.27.1)
Requirement already satisfied: Pillow in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (from diffusers) (9.3.0)
Requirement already satisfied: tqdm>=4.42.1 in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (from huggingface-hub>=0.13.2->diffusers) (4.64.1)
Requirement already satisfied: fsspec in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (from huggingface-hub>=0.13.2->diffusers) (2023.1.0)
Requirement already satisfied: imageio<3.0,>=2.5 in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (from MoviePy) (2.31.2)
Requirement already satisfied: proglog<=1.0.0 in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (from MoviePy) (0.1.10)
Requirement already satisfied: imageio-ffmpeg>=0.2.0 in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (from MoviePy) (0.4.9)
Requirement already satisfied: decorator<5.0,>=4.0.2 in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (from MoviePy) (4.4.2)
Requirement already satisfied: urllib3<1.27,>=1.21.1 in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (from requests->diffusers) (1.26.12)
Requirement already satisfied: idna<4,>=2.5 in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (from requests->diffusers) (3.4)
Requirement already satisfied: charset-normalizer~=2.0.0 in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (from requests->diffusers) (2.0.12)
Requirement already satisfied: certifi>=2017.4.17 in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (from requests->diffusers) (2022.9.24)
Collecting tokenizers!=0.11.3,<0.14,>=0.11.1
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/4d/40/ab3c3c705e0a8cbbe760c49302b407190201d96fe7dfeea37ccafa004da3/tokenizers-0.13.3-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (7.8 MB)
     |████████████████████████████████| 7.8 MB 19.9 MB/s eta 0:00:01
Requirement already satisfied: zipp>=0.5 in /home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages (from importlib-metadata->diffusers) (3.10.0)
Installing collected packages: tokenizers, transformers, diffusers, accelerate
Successfully installed accelerate-0.20.3 diffusers-0.21.4 tokenizers-0.13.3 transformers-4.30.2
WARNING: You are using pip version 21.0.1; however, version 24.0 is available.
You should consider upgrading via the '/home/ma-user/anaconda3/envs/PyTorch-1.8/bin/python3.7 -m pip install --upgrade pip' command.

import moxing as mox
mox.file.copy_parallel('obs://modelarts-labs-bj4-v2/case_zoo/zeroscope/model', 'model')

import os
import torch
from diffusers import DiffusionPipeline, DPMSolverMultistepScheduler
from diffusers.utils import export_to_video

pipe = DiffusionPipeline.from_pretrained("model", torch_dtype=torch.float16)
pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
pipe.enable_model_cpu_offload()

video_path = os.path.join(os.getcwd(),'result.mp4')

prompt = "Darth Vader is surfing on waves"
video_frames = pipe(prompt, num_inference_steps=40, height=320, width=576, num_frames=24).frames
export_to_video(video_frames, output_video_path=video_path)
print('video_path:',video_path)

显示 output

/home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages/tqdm/auto.py:22: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html
  from .autonotebook import tqdm as notebook_tqdm
/home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages/requests/__init__.py:104: RequestsDependencyWarning: urllib3 (1.26.12) or chardet (5.2.0)/charset_normalizer (2.0.12) doesn't match a supported version!
  RequestsDependencyWarning)
Loading pipeline components...: 100%|██████████| 5/5 [00:03<00:00,  1.28it/s]
100%|██████████| 40/40 [03:55<00:00,  5.88s/it]

video_path: /home/ma-user/work/zeroscope/result.mp4

#将视频文件转成动图显示
from moviepy.editor import *
 
# 指定输入视频路径
video_path = "result.mp4"
 
# 加载视频
clip = VideoFileClip(video_path)
 
# 设置保存GIF的参数（如分辨率、持续时间等）
output_file = "result_animation.gif"
fps = 10 # GIF每秒显示的帧数
 
# 生成并保存GIF
clip.write_gif(output_file, fps=fps)

MoviePy - Building file result_animation.gif with imageio.

from IPython.display import Image
Image(open('result_animation.gif','rb').read())