Inkpunk Diffusion

Originally posted to HuggingFace by Envvi

Finetuned Stable Diffusion model trained on dreambooth. Vaguely inspired by Gorillaz, FLCL, and Yoji Shinkawa.

Inkpunk Diffusion v2

Improvements:

  • Excorsized the woman that seemed to be haunting the model and appearing in basically every prompt (she still pops in here and there, I honestly don't know where she comes from)
  • Faces are better overall, and characters are more responsive to descriptive language in prompts, try playing around with emotions/nationality/age/poses to get the best results
  • Hair anarchy has been toned down slightly, added more diverse hairstyles to the dataset to avoid everyone having tumbleweed hair, again descriptive language in prompts helps
  • Full body poses are also more diverse, though keep in mind that wide angle shots tend to lead to distorted faces that may need to be touched up with img2img/inpainting