Instructions to use NO8D/HighResolution with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use NO8D/HighResolution with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("NO8D/HighResolution", torch_dtype=torch.bfloat16, device_map="cuda") prompt = "High Resolution" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Notebooks
- Google Colab
- Kaggle
tags:
- diffusers
- template:diffusion-lora
- image-to-image
- LoRA
widget:
- output:
url: images/01.png
text: High Resolution
- output:
url: images/02.png
text: High Resolution
- output:
url: images/ComfyUI_temp_dapnm_00024_.png
text: High Resolution
- output:
url: images/ComfyUI_temp_dapnm_00025_.png
text: High Resolution
- output:
url: images/ComfyUI_temp_dapnm_00026_.png
text: High Resolution
- output:
url: images/ComfyUI_temp_dapnm_00054_.png
text: High Resolution
base_model:
- black-forest-labs/FLUX.2-klein-4B
- black-forest-labs/FLUX.2-klein-9B
instance_prompt: High Resolution
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://bfl.ai/legal/non-commercial-license-terms
HighResolution4B

- Prompt
- High Resolution

- Prompt
- High Resolution

- Prompt
- High Resolution

- Prompt
- High Resolution

- Prompt
- High Resolution

- Prompt
- High Resolution
Model description
Do you... Want to turn a small image into a large one? Want to make a low-resolution image clear? Or the images generated by ZIT are always blurry, and using the upscale model or controlnet model for enlargement always changes the content of the image, requiring repeated modifications to parameters and prompts, consuming a great deal of time and energy, yet the results may not necessarily be good.
This LORA is designed to address these issues. It only does one thing: making the image clearer without changing its content at all.
Below is a comparison with Klein.
Comparison with input
Advanced version of High-resolution for Klein4B ( ✔️ )
Advanced version of High-resolution for Klein9B ( ✔️ )
Advanced version of High-resolution for Krea2 ( ✔️ )
Krea2 does not have native image editing capabilities, so you will need additional nodes.
https://github.com/ostris/ComfyUI-Krea2-Ostris-Edit and https://github.com/no8d/ComfyUI-NO8D-controls
Trigger words
Klei:High Resolutio krea2:High quality
I'm an independent model and workflow developer. If you like my work and want to support independent development, please consider buying me a cup of coffee to keep this motivation going! Thank you very much.
support 🫡 May the AI-power be with you, see you soon !🫡



