Krea 2 LoRA — mobbrain/hdoub4

Prompt

hdoub standing on a wooden dock, fully nude, smiling at the camera, bright daylight, calm water background

Prompt

hdoub lying on a white bed, nude from the waist up, soft smile, long dark hair spread out, soft indoor lighting

Prompt

hdoub wearing a white blouse, close-up portrait, warm golden hour sunlight, wooden wall 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 hdoub to invoke the concept.

Samples

"hdoub standing on a wooden dock, fully nude, smiling at the camera, bright daylight, calm water background"

"hdoub lying on a white bed, nude from the waist up, soft smile, long dark hair spread out, soft indoor lighting"

"hdoub wearing a white blouse, close-up portrait, warm golden hour sunlight, wooden wall 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("mobbrain/hdoub4")
image = pipe("hdoub standing on a wooden dock, fully nude, smiling at the camera, bright daylight, calm water background", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")