Type | |
Stats | 645 |
Reviews | (82) |
Published | Jan 12, 2024 |
Base Model | |
Hash | AutoV2 E688C8CB8F |
Introduction
This model is generally pretty easy to prompt. It will primarily produce photorealistic images but can be pushed to produce 3d style animated content. It is very biased towards generating females, and produces NSFW content very easily.
Disclaimer
All prompts in the example images use InvokeAI Syntax NOT Automatic1111 syntax. The key thing you need to know is that 'term+' is equivalent to '(term)' ++ is the same as (()) and so on. All example images were generated in InvokeAI with xformers enabled. InvokeAI also converts all safetensors or ckpt files into diffusers models before generating images. For these reasons you will likely not be able to reproduce my example images 1:1.
Prompting & Generation
Sampler: DPM++ SDE, Euler, or Restart
Steps: 35-45
CFG: 5 - 10
CLIP Skip: doesn't matter
Prompting is pretty easy with this one. Just try whatever you want and you'll probably get a pretty decent result. It can struggle with eyes when the character is further away from view, and for that reason you'll get the best eyes from portrait style images.
For NSFW Prompting use prompts similar to those that are used on Pyros, they seem to work the best and simpler is better.