Krea 2 LoRA — September6969/raven

Prompt

A close-up portrait photo of vzx woman, looking directly at the camera, natural daylight, realistic photography

Prompt

A full-body photo of vzx woman standing on a city street, wearing a white T-shirt and blue jeans, natural daylight, realistic photography

Prompt

A cinematic portrait of vzx woman sitting in a modern cafe, wearing a black jacket, warm indoor 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 vzx woman to invoke the concept.

Samples

"A close-up portrait photo of vzx woman, looking directly at the camera, natural daylight, realistic photography"

"A full-body photo of vzx woman standing on a city street, wearing a white T-shirt and blue jeans, natural daylight, realistic photography"

"A cinematic portrait of vzx woman sitting in a modern cafe, wearing a black jacket, warm indoor 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("September6969/raven")
image = pipe("A close-up portrait photo of vzx woman, looking directly at the camera, natural daylight, realistic photography", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")