Instructions to use gabai/gab-krea2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use gabai/gab-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", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("gabai/gab-krea2") prompt = "A futuristic cyberpunk cityscape at midnight with neon rain, featuring a Gabkrea floating in a holographic display." image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Krea 2 LoRA โ gabai/gab-krea2

- Prompt
- A futuristic cyberpunk cityscape at midnight with neon rain, featuring a Gabkrea floating in a holographic display.

- Prompt
- A serene, sun-drenched Tuscan vineyard in autumn, where a rustic Gabkrea sits atop a weathered stone table.

- Prompt
- An ethereal underwater kingdom with glowing coral reefs and bioluminescent fish surrounding a shimmering Gabkrea.
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 Gabkrea to invoke the concept.
Samples
"A futuristic cyberpunk cityscape at midnight with neon rain, featuring a Gabkrea floating in a holographic display."
"A serene, sun-drenched Tuscan vineyard in autumn, where a rustic Gabkrea sits atop a weathered stone table."
"An ethereal underwater kingdom with glowing coral reefs and bioluminescent fish surrounding a shimmering Gabkrea."
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("gabai/gab-krea2")
image = pipe("A futuristic cyberpunk cityscape at midnight with neon rain, featuring a Gabkrea floating in a holographic display.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
- Downloads last month
- 15
Model tree for gabai/gab-krea2
Base model
krea/Krea-2-Raw

