Pixel Survivors Character
Consider supporting further research on Patreon or Twitter
Checkout my other models at RetroDiffusion
Trained with 64x64 samples, all generations will need to be downscaled 8 times.
512x512 => 64x64 with Nearest Neighbors. You can use an extension or Aseprite.
No extra pixelizations methods required.
Best used in conjunction with: Astropulse PixelDetector
Tips:
Used best with DreamShaper
Use it at 0.9-0.8 of strength
Better results at 512x512, 512x768 and 768x512
Use simple prompts and no trigger word, see examples for prompt examples
Changelog
v1: Release of v1 checkpoint
Description
Initial release
FAQ
Comments (4)
I have no idea what happens when you make it render in 1024x1024, but I like it :D
Interesting. I generated 50 images of "person", and 50 out of 50 were women. I did another test without the lora, and it seems to be a limitation of the checkpoint you trained this on.
Yup, it's a overfitted. You can try decreasing the strength or use a neg prompt.
I'm planning to release a v2 with a more curated dataset
Any chance of a sdxl version or update?