Krea 2 LoRA — LelouchR18/k2char-v1

Prompt

k2char woman, natural portrait photo, casual clothing, looking at the camera, realistic photography, soft natural light

Prompt

k2char woman, full body photo, standing outdoors on a street, casual clothing, natural pose, realistic photography

Prompt

k2char woman, seated indoors at a cafe, different outfit, candid expression, natural lighting, realistic photography

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 k2char woman to invoke the concept.

Samples

"k2char woman, natural portrait photo, casual clothing, looking at the camera, realistic photography, soft natural light"

"k2char woman, full body photo, standing outdoors on a street, casual clothing, natural pose, realistic photography"

"k2char woman, seated indoors at a cafe, different outfit, candid expression, natural lighting, realistic photography"

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("LelouchR18/k2char-v1")
image = pipe("k2char woman, natural portrait photo, casual clothing, looking at the camera, realistic photography, soft natural light", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")