Diffusers How to use chapa1337/vikralora with Diffusers:
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Qwen/Qwen-Image", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("chapa1337/vikralora")
prompt = "a photo of a woman named vikra, amateur smartphone selfie, candid indoor shot against a white paneled door and neutral wall, soft warm ambient lighting, she is a young adult with fair smooth skin (no freckles), dark wavy shoulder-length hair with soft curtain bangs, and warm hazel eyes looking directly at the camera with a calm, neutral expression—lips closed, slight head tilt, she wears a black lace-trimmed top and a silver chain necklace with a small black cross pendant, makeup includes precise black winged eyeliner, natural-looking lashes, and deep burgundy matte lipstick, no facial markings or decorations, natural skin texture with visible pores and subtle shine on nose and lips, realistic fabric details, shallow depth of field with softly blurred background, subtle sensor noise in shadow areas, authentic imperfections: stray hairs, minor asymmetry in brow sa photo of a woman named vikra, amateur smartphone selfie, casual shot taken indoors in a modern room during evening, she is a young adult with fair skin, natural skin texture with subtle freckles on cheeks, dark wavy shoulder-length hair with soft bangs, and hazel eyes, she wears a black spaghetti strap top with delicate lace trim along the neckline and a silver necklace featuring a circular pendant, she looks directly at the camera with a neutral expression, the background shows white shelving units adorned with decorative items like a small statue, patterned wall art, and assorted bottles slightly blurred, soft indoor lighting creates gentle shadows on her face and neck, natural skin texture with slight shine on the forehead and collarbone, visible sensor noise in darker areas of the background, natural skin texture, realistic details, genuine expression, captured moment, authentic imperfections"
image = pipe(prompt).images[0] 
