---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- output:
    url: >-
      images/0856002-a pretty 30 something year old woman
      in-Krea2-INT8-ConvrotpornmasterKrea2_v2Tur.png
  text: '{'
base_model: krea/Krea-2-Raw
instance_prompt: B4gged but just use natural language
license: other
license_name: dowhateverthefkuwant
license_link: LICENSE
---
# B4gged

<Gallery />

## Model description 

Version 3 of my consensual breath-play Lora
Just use natural language,
the new Lora training is 500 times better than my last method there seems to be no more bleed where the Lora damages the quality of the default model,
i think this may be the final version as it does exactly as i expected, it was captioned with a large amount of relevant words to associate them,
i have yet to spend the time to work out what is the best epoch so i just uploaded them all try from 15 onwards but the final epoch seems awesome even at 1.0 strength,
for any wondering the new training method is now using the RAW model and using https://github.com/shootthesound/Fizgig.

* after testing will do a v4 removing watermarks

## Trigger words

You should use `B4gged but just use natural language` to trigger the image generation.


## Download model


[Download](/HuggingVince/B4gged_Krea2_V3/tree/main) them in the Files & versions tab.