Downloads · 30 days
735
33% of all-time downloads
bonticario/Krea-2-Realism-LoRA
Krea-2-Realism-LoRA is a text-to-image model from bonticario. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as other.
A realism LoRA for Krea 2. It pushes Krea 2 toward natural, candid, true-to-life photography — everyday people, places, and light — without needing any "photorealistic / 8k / DSLR" style keywords. Just write a normal,…
Downloads · 30 days
735
33% of all-time downloads
All-time downloads
2.3K
Public
Repo size
490 MB
Likes
0
Public
Click a slice to open those files.
.safetensors469 MB · 96%
From the Hugging Face model README
A realism LoRA for Krea 2. It pushes Krea 2 toward natural, candid, true-to-life photography — everyday people, places, and light — without needing any "photorealistic / 8k / DSLR" style keywords. Just write a normal, descriptive sentence and let the LoRA do the rest.
Trained with the FAL Krea LoRA Trainer on krea/Krea-2-Raw and meant to be used directly on krea/Krea-2-Turbo (per Krea's recommended workflow of training on Raw and running on Turbo).
No trigger word is required. Simply describe the scene in plain natural language. Longer, descriptive single-sentence prompts work best, e.g.:
A young woman taking a selfie in front of a steamy bathroom mirror with her phone partly covering her face, soft morning light coming through a frosted window, water droplets on the glass and a white towel wrapped around her hair
Install diffusers from source (for Krea2Pipeline):
pip install git+https://github.com/huggingface/diffusers.git
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained(
"krea/Krea-2-Turbo", torch_dtype=torch.bfloat16
).to("cuda")
pipe.load_lora_weights("gokaygokay/Krea-2-Realism-LoRA")
prompt = (
"A woman with curly hair laughing while holding an open paperback in a cluttered "
"secondhand bookshop, tall crowded shelves towering around her in soft warm lamplight"
)
image = pipe(prompt, num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("krea2_realism.png")
The LoRA can be used directly on the hosted Krea 2 Turbo endpoint by pointing to the weights:
import fal_client
result = fal_client.subscribe(
"fal-ai/krea-2/turbo/lora",
arguments={
"prompt": "A barista with tattooed forearms leaning on the worn wooden counter of a tiny corner cafe holding a cup with delicate latte art, late afternoon sun streaking across shelves of mismatched mugs behind her",
"loras": [{
"path": "https://huggingface.co/gokaygokay/Krea-2-Realism-LoRA/resolve/main/krea2_realism_lora.safetensors",
"scale": 1.0
}],
"image_size": {"width": 1280, "height": 1600},
"num_images": 1
},
)
print(result["images"][0]["url"])
All images below were generated on Krea 2 Turbo with this LoRA at scale 1.0, using only plain descriptive prompts (no style keywords).
<table> <tr> <td width="50%"> <img src="images/example_01.png" width="100%"/><br/> <sub>A young woman taking a selfie in front of a steamy bathroom mirror with her phone partly covering her face, soft morning light coming through a frosted window, water droplets on the glass and a white towel wrapped around her hair</sub> </td> <td width="50%"> <img src="images/example_04.png" width="100%"/><br/> <sub>A barista with tattooed forearms leaning on the worn wooden counter of a tiny corner cafe holding a cup with delicate latte art, late afternoon sun streaking across shelves of mismatched mugs behind her</sub> </td> </tr> <tr> <td width="50%"> <img src="images/example_11.png" width="100%"/><br/> <sub>A construction worker in a yellow hard hat and high-visibility vest drinking from a water bottle during a break on a high rooftop, the hazy city skyline stretching out behind him in the midday heat</sub> </td> <td width="50%"> <img src="images/example_12.png" width="100%"/><br/> <sub>An elderly woman in a floral apron tending to potted geraniums on a narrow apartment balcony in the early morning, a metal watering can in her hand and laundry drying on a line beside her</sub> </td> </tr> <tr> <td width="50%"> <img src="images/example_14.png" width="100%"/><br/> <sub>A young father carrying his sleeping toddler against his shoulder through an empty airport terminal late at night, wheeling a small suitcase behind him under cold overhead lights</sub> </td> <td width="50%"> <img src="images/example_15.png" width="100%"/><br/> <sub>A woman with curly hair laughing while holding an open paperback in a cluttered secondhand bookshop, tall crowded shelves towering around her in soft warm lamplight</sub> </td> </tr> <tr> <td width="50%"> <img src="images/example_16.png" width="100%"/><br/> <sub>A skateboarder sitting on a curb tying his shoe in an empty parking lot at dusk, the deep orange sky reflecting off the windows of nearby shops</sub> </td> <td width="50%"> <img src="images/example_19.png" width="100%"/><br/> <sub>A mechanic in grease-stained overalls leaning under the open hood of a car in a cluttered garage, a work lamp casting hard light across the engine and his focused face</sub> </td> </tr> </table>Weights are available in Files & versions (krea2_realism_lora.safetensors).