Krea 2 LoRA — guillekenzo/aros-e9b8b4fb-Lily

Prompt

A photo of jtv woman on a wooden table indoors.

Prompt

A photo of jtv woman outdoors on a patch of grass.

Prompt

A close-up photo of jtv woman against a plain background.

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 jtv woman to invoke the concept.

Samples

"A photo of jtv woman on a wooden table indoors."

"A photo of jtv woman outdoors on a patch of grass."

"A close-up photo of jtv woman against a plain background."

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("guillekenzo/aros-e9b8b4fb-Lily")
image = pipe("A photo of jtv woman on a wooden table indoors.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")