Pixel Diffusion XL

For business inquires, commercial licensing, custom models/commissions, large scale image captioning for datasets and consultation contact me under [email protected]

Follow me on Twitter: @YamerOfficial Discord: yamer_ai

Checkpoint Type: SDXL 1.0 pixelated artstyle

If you have enjoyed this checkpoint:
Pixel Diffusion is a dedicated checkpoint designed for creating pixel art style images. It has the capability to generate a wide variety of images in the pixel art style, allowing users to produce beautiful and creative artworks. While it may not focus on generating perfectly shaped pixels, it excels in delivering images with the distinctive pixel art style, offering advantages such as vibrant color saturation and the convenience of shorter prompts.

The VAE has been already baked in.

How To Use:

This checkpoint can be hard to use when generating images without knowing how to get the best images with it, here is a simple list of things to follow to generate beautiful art:

1. Keep the prompt simple, don’t use extremely long prompts, focus on what you need

2. Use “Pixel Art” at the start or in the beginning part of the prompt, this way you can be sure to achive a pixel art type of image

3. Use words such as 16 bit, 32 and 64 bit to help the checkpoint understand the style if you are having a hard time getting pixel art

4. When upscaling remember to use very low Denoise Strength values, don’t go above 0.25 or else the image will start to distort

5. It’s preferrable if you don’t use words that imply a style that is very different from pixel art, especially in the beginning part of the prompt, prompts such as: realistic, Photography and hyper detailed may damage the pixel art aesthetic, use those only in the last parts of a prompt (if you want to use them at all)

6. Keep in mind this is not a perfect pixel art image creator, you may need to generate multiple times the same prompt to get what you exactly want to achive

7. Use CFG values between 4 and 12 this way the model is more stable and can generate images better

8. Pay attention to the LoRAs you are using, some may completely remove the pixel art style from the image

What can I do with this checkpoint?

You have the freedom to create what you prefer, here are some fields where this checkpoint is best used:

• Game design, generate images to use as inspiration for sprites in video games, tools, potions, armors and everything else you need for a pixelated game adventure

• Profile pictures, use it to generate your very own and unique profile picture for all social media platforms

• Commercial use, interested in using this for your next game/AI related projects? Contact me on my mail ([email protected])

• Learning tool, learn how to make pixel art by generating images with this checkpoint and trying to remake it using external drawing software

• Experimentation, have fun and make something really unique with it, share with friends and enjoy what you create

Creator note:

Hi, I’m an Italian creator on a mission to spread the joy of using AI to generate images and the progress it has made in the past few years. I craft checkpoints and prompts that anyone can use to generate their own art and share it. My ultimate aim is to be a good creator, sharing the models I create as a hobby with others.

The primary goal of this checkpoint is to be multi use, good with most styles and that can give you the creator, a good starting point to create your AI generated images and start your own career in the AI world.
All the various versions follow the general idea of an unstable model, but they individually showcase distinct styles. V2 for instance, isn't a direct improvement of V1 and the same applies to all the other versions. Every version introduces its own unique style, and with each iteration I try my best to enhance the aesthetics and visuals, ensuring each model stands out with its own distinct identity! 😸

P͓̽e͓̽r͓̽s͓̽o͓̽n͓̽a͓̽l͓̽ ͓̽R͓̽a͓̽t͓̽i͓̽n͓̽g͓̽:͓̽

• Quality: 7.5/10 (for version 1 to 9 – 11)

• Stability (Variety): 6/10, the lower = the more variety with one prompt

• Flexibility: 7/10

• CFG resistance: 12/30

• Style strength: 9/10

• Style Variety: 5/10

Recommended Settings:

Image Quality: 1024×1024 (Standard for SDXL), 768×1024 (Used in the showcase) 16:9, 4:3, 6:13

Steps: 30-50

• Hires Upscaler: 4x_foolhardy_Remacri or 4xUltraSharp

• Hires upscale: The only limit is your GPU (I upscale 1,5 times the base image, 576×1024)

• VAE: XL_VAE_C

To achieve a specific nsfw result I recommend to use a SDXL LoRA, this is not a nsfw focused model but it can generate some NSFW content. (SD 1.5 LoRAs doesn’t work with SDXL models)

1) Perfect for pixel creatures, gotta generate'em all
2) Imagination is the first ingredient of AI
3) Think outside the hypercube!

    -Yamer Grimlock