This is a fine-tuned Stable Diffusion model (based on v1.5) trained on action figure pictures: Use the token actionauf in your prompts to use the style.
You can make the prompt stronger using words as "realistic" or "action figure" or whatever you think being fit. Do not exceed with steps, try to check the restore faces and enjoy with cfg scale. At the moment this is an experimental model. Hope you like it.Please feel free to merge with some useful model and let me know ^_^
This model was trained with Dreambooth training by TheLastBen, using 77 images at 11550 steps.