dataautogpt3/Miniaturus_PotentiaV1.2

<Gallery />

Miniaturus Potentia is my sd 1.5 family of models using my main acheivements discovered and first implemented within SDXL/Proteus.

trained on 220k GPTV captioned images and than dpo tuned on 3k hand picked stylistic images. the same methodoligy used for Proteus.

Settings for Miniaturus_Potentia v1.2

Use these settings for the best results with Miniaturus_Potentia v1.2:

CFG Scale: Use a CFG scale of 8.5

Steps: 35 to 70 steps for more detail, 35 steps for faster results.

Sampler: DPM++ 3M SDE

Scheduler: Karras

Use it with 🧨 diffusers

from diffusers import AutoPipelineForText2Image
import torch
        
pipeline = AutoPipelineForText2Image.from_pretrained('dataautogpt3/Miniaturus_PotentiaV1.2', torch_dtype=torch.float16).to('cuda')        
image = pipeline('The image features an older man, a long white beard and mustache,  He has a stern expression, giving the impression of a wise and experienced individual. The mans beard and mustache are prominent, adding to his distinguished appearance. The close-up shot of the mans face emphasizes his facial features and the intensity of his gaze.').images[0]

please support the work I do through donating to me on: https://www.buymeacoffee.com/DataVoid or following me on https://twitter.com/DataPlusEngine