Downloads · 30 days
103
3% of all-time downloads
Miniaturus_PotentiaV1.2
dataautogpt3/Miniaturus_PotentiaV1.2
Miniaturus_PotentiaV1.2 is a text-to-image model from dataautogpt3. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as gpl-3.0.
All-time downloads
4.1K
Public
Repo size
7.6 GB
Likes
12
Public
Repo makeup
Click a slice to open those files.
.bin5.5 GB · 72%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- License
- gpl-3.0
- Access
- Public
- Created
- Jan 23, 2024
- Updated
- Feb 21, 2024
- SHA
- 7ef53951
Try a prompt
Model card
From the Hugging Face model README
<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
- Task
- Text-to-Image
- Library
- diffusers
- License
- gpl-3.0
- Created
- Jan 23, 2024
- Updated
- Feb 21, 2024