---
tags:
  - text-to-image
  - lora
  - diffusers
  - template:diffusion-lora
widget:
- output:
    url: images/Compare_00003_.png
  text: uhdmanscale
base_model: krea/Krea-2-Raw
instance_prompt: uhdmanscale

---
# HighRes-Krea2

<Gallery />

## Model description 

This is a high-resolution krea 2 LoKr model trained on a LR&#x2F;HR dataset of human images.

It can be used for t2i and i2i&#x2F;edit (with the Krea 2 Ostris Edit node: https:&#x2F;&#x2F;github.com&#x2F;ostris&#x2F;ComfyUI-Krea2-Ostris-Edit).

The dataset included SFW and NSFW images and generally doesn&#39;t need a bypass lora to produce NSFW imagery (it was not extensively trained for this so other loras will be needed for that type of output).

## Trigger words

You should use `uhdmanscale` to trigger the image generation.


## Download model


[Download](/n8te0/highres_krea2/tree/main) them in the Files & versions tab.