Instructions to use Gimbor/cuth123 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Gimbor/cuth123 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", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Gimbor/cuth123") prompt = "A futuristic neon-drenched cyberpunk cityscape where a majestic golden lion with holographic wings stalks through the rain, Cuth123, cinematic lighting." image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
metadata
base_model: krea/Krea-2-Raw
tags:
- text-to-image
- diffusers
- lora
- krea2
- template:sd-lora
license: apache-2.0
instance_prompt: Cuth123
widget:
- text: >-
A futuristic neon-drenched cyberpunk cityscape where a majestic golden
lion with holographic wings stalks through the rain, Cuth123, cinematic
lighting.
output:
url: sample_0.png
- text: >-
A serene, sun-dappled ancient library with floating books and swirling
stardust, featuring a majestic golden lion resting on a velvet rug,
Cuth123, ethereal atmosphere.
output:
url: sample_1.png
- text: >-
A vivid underwater coral kingdom with glowing jellyfish and iridescent
fish surrounding a majestic golden lion swimming gracefully through the
deep blue, Cuth123, hyper-realistic.
output:
url: sample_2.png
Krea 2 LoRA — Gimbor/cuth123

- Prompt
- A futuristic neon-drenched cyberpunk cityscape where a majestic golden lion with holographic wings stalks through the rain, Cuth123, cinematic lighting.

- Prompt
- A serene, sun-dappled ancient library with floating books and swirling stardust, featuring a majestic golden lion resting on a velvet rug, Cuth123, ethereal atmosphere.

- Prompt
- A vivid underwater coral kingdom with glowing jellyfish and iridescent fish surrounding a majestic golden lion swimming gracefully through the deep blue, Cuth123, hyper-realistic.
A DreamBooth-LoRA for Krea 2, trained on Krea 2 RAW and shown on Krea 2 Turbo. The samples below were generated with this LoRA on Turbo (8 steps).
Trigger
Use the token Cuth123 to invoke the concept.
Samples
"A futuristic neon-drenched cyberpunk cityscape where a majestic golden lion with holographic wings stalks through the rain, Cuth123, cinematic lighting."
"A serene, sun-dappled ancient library with floating books and swirling stardust, featuring a majestic golden lion resting on a velvet rug, Cuth123, ethereal atmosphere."
"A vivid underwater coral kingdom with glowing jellyfish and iridescent fish surrounding a majestic golden lion swimming gracefully through the deep blue, Cuth123, hyper-realistic."
Use it with diffusers
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("Gimbor/cuth123")
image = pipe("A futuristic neon-drenched cyberpunk cityscape where a majestic golden lion with holographic wings stalks through the rain, Cuth123, cinematic lighting.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")


