Verified: a year ago
SafeTensor
Type | |
Stats | 921 |
Reviews | (120) |
Published | Aug 12, 2023 |
Base Model | |
Trigger Words | pikachu |
Hash | AutoV2 3FC9541726 |
It works well with wide aspect ratio
Prompts to start with :
closeup on pikachu on a pirate ship, cinematic, screencap, by william eggleston, high quality, light rays, sunrays, pov, ships, 1800s
closeup on fluffy pikachu wearing a hoodie in a street in london, cinematic, by william eggleston, screencap, high quality
You get better quality if you combine it with photography styles like :
https://civitai.com/models/119667/sdxl-william-eggleston-style
https://civitai.com/models/121163/sdxl-josef-koudelka-style
Trained using https://github.com/TheLastBen/fast-stable-diffusion SDXL trainer.
ComfyUI seems to give better results than A1111, but that's just me.