Instructions to use n8te0/highres_krea2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use n8te0/highres_krea2 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("krea/Krea-2-Raw", torch_dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("n8te0/highres_krea2") prompt = "uhdmanscale" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
HighRes-Krea2

- Prompt
- uhdmanscale
Model description
This is a high-resolution krea 2 LoKr model trained on a LR/HR dataset of human images.
It can be used for t2i and i2i/edit (with the Krea 2 Ostris Edit node: https://github.com/ostris/ComfyUI-Krea2-Ostris-Edit).
The dataset included SFW and NSFW images and generally doesn'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 them in the Files & versions tab.
- Downloads last month
- -
Model tree for n8te0/highres_krea2
Base model
krea/Krea-2-Raw