This is 8bitdiffuser! A model trained on 1000 pixel art images!

Update! for versions v2 and above they are trained on 5000 images!

Another update, for versions v3 and above, the dataset has 3020 images!

This page is for the 64x model!

PLEASE when using this model, use one of the AnyLoRA forks, CuteYukiMix, Angelbreed or Animekawa. it works best with these models, while it can work on many other models, it might not produce the "pixel perfect" results

When generating images scaling them down 8x will produce pixel perfect results! you can downscale them via billinear, but i have had the BEST results when using astropulse's Pixelize plugin for A1111, it is completely free and can run even on lower end devices.

make sure to use an 8X downscale factor

• the 64x model, while a bit worse at generating even pixels, still operates greatly when downsampling images to native size, it also works much better at full body character portraits. with all v3 versions and above, high resolutions (768x and 1024x) are highly reccomended

best settings for this LoRA is:

• Steps: 20-40 (On lower step counts, pixels will look very noisy, however if you downsample this to native pixel size this issue is resolved, increase step count if you want a great generation without downsampling)

• CFG scale: 7-14

• LoRA scale: 0.85-1.5 (the lower you will set the scale, the more it will look like traditional art and the pixels will become uneven, but the higher the scale is it will appear much noisy)

• Sampling method: DPM++ 2M SDE karras

• Recommended prompt: "pixelart" (Add these to the start every generation, this isn't "required" but I found it gets the best results)

• Resolution: 512-1024 (on lower resolutions, the pixels will be less even, on higher ones the artifacts will be less noticeable but will take much more time)