Guide to Image Generation. Part 3

Part 1 Here

Part 2 Here

My Links: twitter, discord, IG

Subscribe for FBB images @ https://patreon.com/fitCorderAI

We'll focus on how to create something artistic. In this example we take an image from google and create original art with it.

This article assumes you know how to install an embedding, VAE & HiRes. It also assumes you know how to install a checkpoint. If you need further help please reach out using the links above.

The vae is mse-840k unless specified. Find it here.

Google/Yandex

Look on your favorite search engine for an interesting base image.

I thought this one might be interesting.

Text2Img with Controlnet x 2

So now we need to go-to Automatic1111 with controlnet. More controlnet info here

Anime Model: fCAnimeMix

Positive Prompt: woman, brazillian, amanda nunes, ufc, armor, champion, golden, lioness, lion, safari, sky background, fcHeatPortrait, black hair

Negative Prompt: BadDream

Steps: 20, Sampler: DPM++ 2M SDE, CFG scale: 7, Seed: 1106876908, Size: 768x512, Model: fC_fcAnimeMix-V2, Denoising strength: 0.5

Controlnet 0: Depth

Controlnet 1: Canny

AI Output

After some basic Photoshop:

Hopefully part 3 helps inspire you to make great looking art on Stable Diffusion.

My Links: twitter, discord, IG

Support my efforts at @ ko-fi.com/fitcorderai

Subscribe for FBB images @ https://patreon.com/fitCorderAI