Krea 2 LoRA — SHotoor/elisegpt

Prompt

EliseGPT, photorealistic medium close-up portrait, standing beside a large window in a modern apartment during golden hour, relaxed three-quarter angle with her head turned toward the camera, soft confident expression, natural makeup, wearing a fitted black turtleneck and small gold earrings, warm sunlight tracing her platinum-blonde bob, realistic skin texture, shallow depth of field, 85mm lens, cinematic natural lighting, highly detailed photography.

Prompt

EliseGPT, full-body fashion photograph walking through a rainy city street at night, caught mid-step and looking over her shoulder toward the camera with a playful smile, wearing a fitted burgundy leather jacket, dark jeans, and ankle boots, wet pavement reflecting neon storefront lights, platinum-blonde bob moving naturally with her motion, realistic proportions, candid body language, cinematic street photography, 50mm lens, shallow depth of field, highly detailed photorealism.

Prompt

EliseGPT, seated sideways on a simple wooden chair in a bright minimalist studio, torso rotated toward the camera while her face is shown in a strong three-quarter view, one leg crossed casually over the other, thoughtful neutral expression, wearing a cream sleeveless top and tailored charcoal trousers, soft diffused daylight, plain warm-gray backdrop, natural skin texture, realistic anatomy, editorial fashion photography, 70mm lens, crisp focus and subtle depth of field.

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 EliseGPT to invoke the concept.

Samples

"EliseGPT, photorealistic medium close-up portrait, standing beside a large window in a modern apartment during golden hour, relaxed three-quarter angle with her head turned toward the camera, soft confident expression, natural makeup, wearing a fitted black turtleneck and small gold earrings, warm sunlight tracing her platinum-blonde bob, realistic skin texture, shallow depth of field, 85mm lens, cinematic natural lighting, highly detailed photography."

"EliseGPT, full-body fashion photograph walking through a rainy city street at night, caught mid-step and looking over her shoulder toward the camera with a playful smile, wearing a fitted burgundy leather jacket, dark jeans, and ankle boots, wet pavement reflecting neon storefront lights, platinum-blonde bob moving naturally with her motion, realistic proportions, candid body language, cinematic street photography, 50mm lens, shallow depth of field, highly detailed photorealism."

"EliseGPT, seated sideways on a simple wooden chair in a bright minimalist studio, torso rotated toward the camera while her face is shown in a strong three-quarter view, one leg crossed casually over the other, thoughtful neutral expression, wearing a cream sleeveless top and tailored charcoal trousers, soft diffused daylight, plain warm-gray backdrop, natural skin texture, realistic anatomy, editorial fashion photography, 70mm lens, crisp focus and subtle depth of field."

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("SHotoor/elisegpt")
image = pipe("EliseGPT, photorealistic medium close-up portrait, standing beside a large window in a modern apartment during golden hour, relaxed three-quarter angle with her head turned toward the camera, soft confident expression, natural makeup, wearing a fitted black turtleneck and small gold earrings, warm sunlight tracing her platinum-blonde bob, realistic skin texture, shallow depth of field, 85mm lens, cinematic natural lighting, highly detailed photography.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")