近来Stable diffusion分散网络大热,跟上时代,简略的文生图,图生图,其实能够满足绝大多数设计师的运用,但是有什么是赛博画手无法做到的呢? 那就是他们运用到的stable diffusion的插件开发,他们并不清楚stable diffusino的代码结构,假如遇到一些代码层面的报错问题,他们将无法简略解决。

我们想要开发出我想要的stable diffusion插件。那么我们首先要去学习一些gradio的基础知识。

Gradio接口文档

1.想要了解stable diffusion的插件的形式,插件基本都是放在extension文件夹里边。 发动器供给经过git下载对应的内容。 其实就是经过直接copy github里边的代码来实现插件的。

Stable Diffusion 插件开发

Stable Diffusion 插件开发

2.以一个简略ffmpeg嵌入倒放视频的功用为例吧

Stable Diffusion 插件开发

发动的时分需求安装一些库,需求预备install.py文件会主动运行代码

import launch
if not launch.is_installed("ffmpeg-python"):
    launch.run_pip("install ffmpeg-python", "requirements for TemporalKit extension")
if not launch.is_installed("moviepy"):
    launch.run_pip("install moviepy", "requirements for TemporalKit extension")
if not launch.is_installed("imageio_ffmpeg"):
    launch.run_pip("install imageio_ffmpeg", "requirements for TemporalKit extension")

requirement.txt最好也预备一些你需求的库

ffmpeg-python
moviepy

3.一个发动简略的发动代码,看不懂的能够看注释,这个比如简略包括按钮,滑动条,视频展现等容器。假如需求查看更多的容器,需求去看gradio api

import gradio as gr
from modules import scripts, script_callbacks
import os
import ffmpeg
# base_dir = scripts.basedir()
#ffmpeg倒放指令
def convert_video(input_file: str, output_directory: str, speed: int, reverse: bool):
  #ffmpeg -i G:\1\c6cfb2d13929eb4967417e0bd81c314c.mp4 -vf reverse -y reverse.mp4
  fileName = os.path.basename(input_file)
  outputFile = os.path.join(output_directory, fileName)
  ffm = ffmpeg.input(input_file)
  if speed != 1 :
    ffm = ffm.filter('setpts', f'PTS/{speed}')
  if reverse :
    ffm = ffm.filter("reverse")
  ffm.output(outputFile).run()
  return outputFile
def on_ui_tabs():
  with gr.Blocks(analytics_enabled=False) as ffmpeg_kit_ui:
    with gr.Row():
      with gr.Column(variant="panel"):
        with gr.Column():
          video_file = gr.Textbox(
            label="Video File",
            placeholder="Wrire your video file address",
            value="",
            interactive=True,
          )
          org_video = gr.Video(
            interactive=True, mirror_webcam=False
          )
          def fn_upload_org_video(video):
            return video
          org_video.upload(fn_upload_org_video, org_video, video_file)
          gr.HTML(value="<p>\
            If you have trouble entering the video path manually, you can also use drag and drop.For large videos, please enter the path manually. \
          </p>")
        with gr.Column():
          output_directory = gr.Textbox(
            label="Video Output Directory",
            placeholder="Directory containing your output files",
            value="",
            interactive=True,
          )
        with gr.Column():
          with gr.Row():
            speed_slider = gr.Slider(
              label="Video Speed",
              minimum=0, maximum=8,
              step=0.1,
              value=1
            )
          with gr.Row():
            reverse_checkbox = gr.Checkbox(
              label="Video need reverse",
              value=False
            )
      with gr.Column(variant="panel"):
        with gr.Row():
          convert_video_btn = gr.Button(
            "Convert Video", label="Convert Video", variant="primary"
          )
        with gr.Row():
          dst_video = gr.Video(
            interactive=True, mirror_webcam=False
          )
        #生成按钮
        convert_video_btn.click(
          convert_video,
          inputs=[
            video_file,
            output_directory,
            speed_slider,
            reverse_checkbox
          ],
          outputs=dst_video
        )
        gr.HTML(value="<p>Converts video in a folder</p>")
  #ui布局 扩展模块名 
  return (ffmpeg_kit_ui, "FFmpeg Kit", "ffmpeg_kit_ui"),
#发动的时分,script_callback加载到扩展模块傍边
script_callbacks.on_ui_tabs(on_ui_tabs)
print("FFmpeg kit init")

这儿只是一个ffmpeg的功用嵌入,并没有包括原来一些文生图,图生图的功用。

4.下一个介绍怎样嵌入功用到文生图或许图生图的脚本功用

  • def title(self):设置脚本的标题,例如设想为“prompt matrix”
  • def show(self, is_img2img):决议脚本标签是否能够显现,比如假如脚本只想展现在img2img标签中,那便需求在show办法中做判断
  • def ui(self, is_img2img):ui界面的相关代码,例如“把可变部分放在提示词文本的开头”“为每张图片运用不同随机种子”这些选项的实现。
  • def run(self, p, angle, hflip, vflip, overwrite):额外的处理流程,例如在这儿改动prompt,然后传给下一步。这儿p是图片处理器,里边的参数是能够读取ui里边的回来的[]目标
#加载到文生图或许图生图的运用过程傍边
class FFmpegKitScript(scripts.Script):
  def __init__(self) -> None:
    super().__init__()
  # 功用块名
  def title(self):
    return "FFmpeg Kit"
  #是否默认显现
  def show(self, is_img2img):
      return scripts.AlwaysVisible
  #ui显现
  def ui(self, is_img2img):
    video_file = gr.Textbox(
      label="Video File",
      placeholder="Wrire your video file address",
      value="",
      interactive=True,
    )
    output_directory = gr.Textbox(
      label="Video Output Directory",
      placeholder="Directory containing your output files",
      value="",
      interactive=True,
    )
    generateBtn = gr.Button("Generate", label="Generate", variant="primary")
    generateBtn.click(
      convert_video,
      inputs=[
        video_file,
        output_directory
      ],
      outputs=[]
    )
    return [
      video_file,
      output_directory,
      generateBtn,
    ]
  #运行的时分嵌入运行
  def run(self, video_file, output_directory, generateBtn):
    return

4.增加到设定页面里边 这儿需求调用script_callbacks.on_ui_settings办法 shared.opts.add_optioin是增加公共的设置,Shared.OptionsInfo里边是对应的布局,对应都是return目标。 真实不知道怎样写的同学能够参照infinite_zoom这个插件。

Stable Diffusion 插件开发

def on_ui_settings():
    section = ("infinite-zoom", "Infinite Zoom")
    shared.opts.add_option(
        "infzoom_outpath",
        shared.OptionInfo(
            "outputs",
            "Path where to store your infinite video. Default is Outputs",
            gr.Textbox,
            {"interactive": True},
            section=section,    
        ),
    )
    shared.opts.add_option(
        "infzoom_outSUBpath",
        shared.OptionInfo(
            "infinite-zooms",
            "Which subfolder name to be created in the outpath. Default is 'infinite-zooms'",
            gr.Textbox,
            {"interactive": True},
            section=section,
        ),
    )
script_callbacks.on_ui_settings办法
shared.opts.add_optioin是增加公共的设置,Shared.OptionsInfo里边(on_ui_settings)

需求拿出设置里边的数据,能够拿shared.opts.data.get的办法来实现

output_path = shared.opts.data.get("infzoom_outpath", "outputs")

这儿简略介绍了,stable diffusion的插件功用的办法,一些深化的定制需求会在接下来的文章中介绍一些深化运用。