README.md

---
base_model: krea/Krea-2-Raw
tags:
- text-to-image
- diffusers
- lora
- krea2
- template:sd-lora
license: apache-2.0
instance_prompt: "Beth3"
widget:
- text: "A cinematic, wide shot of Beth3 as a futuristic cybernetic explorer standing on the neon-lit crystalline plains of a distant purple planet."
  output:
    url: sample_0.png
- text: "A cozy, sun-drenched oil painting of Beth3 reading an ancient leather book in a dusty Victorian library filled with floating candles."
  output:
    url: sample_1.png
- text: "A high-fashion editorial photo of Beth3 wearing an avant-garde gown made of liquid gold, posing amidst a surreal desert of white sand."
  output:
    url: sample_2.png
---

# Krea 2 LoRA — Lonuhbow/beth3

<Gallery />

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 `Beth3` to invoke the concept.

## Samples

![sample](./sample_0.png)

> *"A cinematic, wide shot of Beth3 as a futuristic cybernetic explorer standing on the neon-lit crystalline plains of a distant purple planet."*

![sample](./sample_1.png)

> *"A cozy, sun-drenched oil painting of Beth3 reading an ancient leather book in a dusty Victorian library filled with floating candles."*

![sample](./sample_2.png)

> *"A high-fashion editorial photo of Beth3 wearing an avant-garde gown made of liquid gold, posing amidst a surreal desert of white sand."*

## Training snapshots

Directly usable LoRA weights saved during training:

- [Step 200](./snapshots/step-200.safetensors)
- [Step 400](./snapshots/step-400.safetensors)
- [Step 600](./snapshots/step-600.safetensors)
- [Step 800](./snapshots/step-800.safetensors)
- [Step 1000](./snapshots/step-1000.safetensors)
- [Step 1200](./snapshots/step-1200.safetensors)
- [Step 1400](./snapshots/step-1400.safetensors)
- [Step 1600](./snapshots/step-1600.safetensors)
- [Step 1800](./snapshots/step-1800.safetensors)
- [Step 2000](./snapshots/step-2000.safetensors)

## Use it with diffusers

```py
import torch
from diffusers import Krea2Pipeline

pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("Lonuhbow/beth3")
image = pipe("A cinematic, wide shot of Beth3 as a futuristic cybernetic explorer standing on the neon-lit crystalline plains of a distant purple planet.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
```