2-4 Create images with simple words(Stable Diffusion Practical Guide Table of Contents)

List

Chapter 1 Let's learn about image generation AI

• 1-1 Let's create images with AI
• 1-2 The birth and evolution of image generation AI
• 1-3 Let's think about the 'definition of AI' at the present time
• 1-4 Let's learn about artificial neural networks
• 1-5 Let's learn about the principle of image generation by the diffusion model

Chapter 2 Let's start building the environment

• 2-1 Let's prepare the environment to use Stable Diffusion
• 2-2 Let's build the environment using Google Colab
• 2-3 Let's build the Stability Matrix in the local environment
• 2-4 Let's create images with simple words
• 2-5 Download the model
• 2-6 Download the VAE

Chapter 3 Let's create images with prompts

• 3-1 Create images as you think using prompts
• 3-2 Build negative prompts
• 3-3 Let's create images 'as you think'
• 3-4 Let's increase the resolution of the image
• 3-5 Let's adjust various parameters
• 3-6 Let's test various prompts

Chapter 4 Let's create images using images

• 4-1 You can do it with img2img Let's figure out what's there
• 4-2 Let's create an image using Sketch
• 4-3 Let's edit an image using Inpaint
• 4-4 Apply Inpaint to modify an image
• 4-5 Extend an image using Outpainting
• 4-6 Increase the resolution of an image using img2img
• 4-7 Let's upscale with the extension function

Chapter 5 Let's use ControlNet

• 5-1 Let's learn about ControlNet
• 5-2 Download and prepare ControlNet
• 5-3 Create an image using ControlNet
• 5-4 Understand the role of the preprocessor

Chapter 6 Let's create and use LoRA

• 6-1 Let's learn what we can do with additional learning
• 6-2 Let's create an image using LoRA
• 6-3 Create your own dedicated painting style LoRA
• 6-4 Let's create various types of LoRA
• 6-5 Let's evaluate the learning content

Chapter 7 Let's use the image generation AI more

>>> Check the screen of AUTOMATIC1111

First, let's run AUTOMATIC1111 WebUI and check the basic configuration and role of the AUTOMATIC1111 screen

.

1.Prompt

Enter a prompt that describes the image you want to generate.

2.Negative prompt

Enter a prompt that describes the image you do not want to generate.

3.Sampling method

Select the algorithm that the AI ​​infers.

4.Sampling steps

Set the number of times the AI ​​infers.

5.Width, Height

Set the width and height of the image to generate. The unit is pixels.

6.Batch count

Set the number of times the image will be generated. The maximum number is 100.

7.Batch size

Set the number of images to generate at once. The default is 1 unless you are using a large VRAM, such as when using a cloud GPU.

8.CFG Scale

Adjusts the strength of the influence that the prompt and negative prompt will have.

9.Seed

Sets the initial value for the AI ​​to infer. '-1' means a random value.

10.Generate

Click to start generating images. Right-click to select the options menu.

11.Generation Viewer

You can check the intermediate status during the generation process. When the image generation is complete, you can see the image that was generated just before. It also displays the settings, prompts, and errors that were used.

12.Open Images output directory

Opens the folder where the generated images are saved. It is not available in the colab environment.

13.Save the image to a dedicated directory (log/images)

Save the generated image.

14.Save zip archive with images to a dedicated directory (log/images)

Save all the generated images as a ZIP file.

15.Send image and generation parameters to img2img tab

Move the generated image to the img2img tab.

16.Send image and generation parameters to img2img inpaint tab

Move the generated image to the img2img inpaint tab.

17.Send image and generation parameters to extras tab

Move the generated image to the Extra tab.

18.Create an upscaled version of the Current image using hires fix setting

Move the generated image to the HiRes fix tab.

19.Stable Diffusion checkpoint

Reload and select the model to use.

20.SD VAE

Optionally, it can be displayed on the UI. Reload and select the VAE to use.

>>> Let's create an image

First, let's test whether the installed program actually creates an image. First, select sd_xl_base_1.0.sagetensors from the checkpoint.

Enter 1girl for the prompt. Enter worst quality for the negative prompt, and then click Generate without changing any other settings to create the image.