---
license: creativeml-openrail-m
language:
- en
library_name: diffusers
tags:
- stable-diffusion
- realistic
- stable-diffusion-diffusers
---
Hugging Face is way more fun with friends and colleagues! 🤗 Join an organization

ConsistentFactor
/
Consistent-Factor 
like
0
Text-to-Image
Diffusers
stable-diffusion
stable-diffusion-diffusers

License:
creativeml-openrail-m
Model card
Files and versions
Community
Settings
Consistent-Factor/
README.md
Metadata UI
license

Consistent Factor is a merged model trying to get as close to realistic as I can. Currently there are 9 models in the merge, with version 5.1 being the most recent official release. Versions 5.2 and 5.3 are just updated versions that are currently in testing, they work just don't offer much improvement over v5.1 that I can notice.

One thing I'm happy to celebrate about my model as that it is a lot more racially friendly and will more often than not, produce people who are not Caucasian, in fact around 60%-70% of the time it will produce people of colour in my testing at least. If you find it's not producing Caucasian people, just add either white or Caucasian to the prompt.
It's also very good at aging people so adding an age can make a big difference.

The only thing it doesn't do well most of the time are eyes, if you don't get decent eyes try adding prefect eyes or round eyes to the prompt and increase the weight till you are happy.

Negative prompt I use: (unrealistic, render, 3d,cgi,cg,2.5d), (bad-hands-5:1.05), easynegative, [( NG_DeepNegative_V1_64T :0.9) :0.1], ng_deepnegative_v1_75t, worst quality, low quality, normal quality, child, (painting, drawing, sketch, cartoon, anime, render, 3d), blurry, deformed, disfigured, morbid, mutated, bad anatomy, bad art, (bad teeth, weird teeth, broken teeth), (weird nipples, twisted nipples, deformed nipples, flat nipples), (worst quality, low quality, logo, text, watermark, username), incomplete, bad_prompt_version2

Recommend: DPM++ 2M SDE Karras, Steps: 20+, Hires fix 0.15 - 0.2, CFG 6 - 8.