https://civitai.com/articles/1274 <----------------------------------------START ➲ GENERATION GUIDE

https://civitai.com/models/926443/ntr-mix-or-illustrious-xl-or-noob-xl <------------------

Model's like pony will be added in the future, NTR Mix is very beginner friendly which is why I'm using it.Beginner Prompting Guide:

The closer a prompt is to the beginning, the higher its priority will be.

you can also artificially change a prompts priority by adding parenthesis or square brackets around the prompt. EX:

each time you surround a prompt with either symbols, its priority will increase or decrease by 10%.

parenthesis: (a rainy day) ⇡ 10%

parenthesis: (((((a rainy day))))) ⇡ 50%

square brackets: [a rainy day] ⇣ 10%

square brackets: [[[[[a rainy day]]]]] ⇣ 50%

Common Tags:

• 1girl / 1boy - one female/male

  this also works with 2girl 3girls exc...

• portrait - focuses on the face and head of your subject

• dramatic lighting - increases lighting contrast

• rim lighting - emphasizes back light

• backlighting - similar to rim lighting

• looking at viewer - causes the subject to look towards the camera

• from above - places the camera above the subject or scene

• from below - places the camera below the subject or scene

• side view - places the camera to the side of the subject or scene

• dutch angle - tilts the camera

• close-up - will generally zoom into the focus of your prompt

• neon lights - generates secondary colorful light sources

• depth-of-field - add blur to foreground and background elements

• upper-body-focus / upper body - focuses on the upper half of the subject

• tired eyes - slims the eyes

• solo / solo focus - increases the focus on a single subject

• Cowboy shot - generally focuses from the knees to head of the subject

• off-shoulder - this will generally generate clothes not covering her shoulders

  These can also be altered however you'd like EX:

• from slightly below

• a girl

• close view

• mood lighting

  These are just basic prompts that you can use, but aren't limited to, to speed up your workflow.

  Different EX:

• a beautiful girl sitting on a bench outside

Before we get started...

Let's set our Sampling Method to DPM++ 2M. This one is the fastest and gives good results with this model.

And let's also change our Schedule type to Karras for the best results, Beta works as well.

Let's also set our Sampling Steps to 30, this will ensure a quick but accurate enough generation.

Since this model is an SDXL model here are my recommended aspect ratios for the best results:

(The pixel count is approximately 1,048,576, with the following recommended resolutions for common aspect ratios.)

1024 x 1024 - 1:1

1254 x 836 - 3:2

1366 × 768 - 16:9

(width and height can be swapped depending on if you want landscape or portrait.)

And you can keep the CFG Scale to 7 for now, this just determines the models "creativity". the higher the number the more it follows your prompt but it will also distort your image more.

Generating an Image ➲

masterpiece, high quality, absurdres, best quality, very aesthetic, newest, from below, backlighting, abstract, cinematic, colorful, (portrait:0.8), dutch angle,

1girl, Mai Sakurajima, blush, looking at viewer, bunny outfit, large breasts, hands on face

worst quality, ugly, low quality, bad anatomy, bad hands, ugly face

First, we start off with our idea. But how do we get there? Maybe it changes as you go along; But to start, you need a base to work off of.

I like to start with my quality tags and build off that.

✦ 1girl, Mai Sakurajima

Then I'd hit GENERATE ➲

This isn't bad but I want the character to resemble her a little better. Let's add in some of her features and what we want her to be doing.

✦ 1girl, Mai Sakurajima, blush, looking at viewer, bunny outfit, large breasts, hands on face

That's better, but I want it to be a little more interesting to look at. Let's add some scene details.

✦  from below, backlighting, abstract, cinematic, colorful, (portrait:0.75), dutch angle,

There we go, that's what we were looking for!

This is a process of adding, generating, adding, and generating over and over, fine tuning the prompt to give the desired output.

The same goes for the negative prompt as well. See something you don't like? complain about it to the negative prompt!

This looks good, but we can make it even better! I introduce to you...

Let's send our image into Inpaint and work on it some more there.

Don't know how? Refer to the video below! ☟

Once you're inside Inpaint, Here's the setting I'd recommend and why I recommend them.

Soft Inpainting = True

Mask Blur = 4

Inpaint Area = Only Masked

Denoising Strength = 0.45 - 0.6

Seed = -1

Aspect Ratio = Press: [📐]

Sampling Steps = 60

Sampling Method / Scheduling Type = DPM++ 2M | Karras

First, Soft Inpainting. This will allow the masked area to blend seamlessly with the unmasked area.

Second, Mask Blur. This is the feather of the mask's edge, higher numbers mean a larger fade.

Third, Inpaint Area. Having it set to Only Masked means that only the area in the mask is altered.

Fourth, Denoising Strength. Ranging from 0-1, this determines how much the image is altered.

Fifth, Seed. Make sure this is set to -1 so you aren't repeating the same generation.

Sixth, Aspect Ratio. This is the size/shape of the Inpainting area.

Seventh, Samling Steps, This is how many steps it takes to diffuse the image. Higher numbers will generally make higher quality generation, up to a point.

And lastly, Eighth; Sampling Method and Scheduling Type. I like to set this to a more slow and accurate sampler and scheduler, such as DPM++ 2M and Karras.

Let's mask the face and change our prompt. Remember, the more area masked, the lower the quality of the inpaint so try and save space.

masterpiece, high quality, absurdres, best quality, very aesthetic, newest, 

1girl, Mai Sakurajima, blush, looking at viewer, eyes, beautiful

worst quality, ugly, low quality, bad anatomy, bad hands, ugly face

It's always good practice to start from the bare minimum and build back up your positive and negative prompts each inpaint to ensure you get exactly what you want.

GENERATE ➲

You can repeat this process over and over as many times as you'd like anywhere in the image!

But wait, how do I get the image back onto the canvas? Simply hold click the generated image, and drag it back onto the canvas.

I would highly recommend you play around with the Denoising Strength depending on what you're changing.

It can be, but you can take it one step further! (you can also edit externally and then inpaint the image to blend it in)

Using Photopea you can enhance your images even more!

And voilà, you've done it, you have learned the basics to creating your first image!

This article will be receiving up-to-date information on how to create the best images possible, utilizing every aspect of Stable Diffusion.

I hope to see you here again! Happy Generating!