How to use editmilliionss/realisticloraqwen 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("editmilliionss/realisticloraqwen") prompt = "A iPhone photo of a IGMODEL woman with rlskn (detailed skin texture:1.3) in a dramatic and sultry pose, her head slightly tilted to the side, showcasing her intense gaze directly at the camera. She is wearing a black satin top that accentuates her cleavage, adding an element of allure. Her hair is styled in loose waves, cascading down her shoulders, framing her face beautifully. The background is minimalistic, featuring a plain white wall which helps to keep the focus entirely on her. The lighting is soft yet directional, highlighting her facial features and the intricate details of her makeup, including defined eyebrows, long eyelashes, and a bold lip color. The overall tone of the image is moody and sophisticated. She is accessorized with a unique snake-themed choker necklace that drapes elegantly around her neck, adding a touch of edginess to her look. The camera angle is slightly elevated, capturing her from a high position, which enhances the sense of dominance and confidence she exudes. The framing is tight, focusing primarily on her upper body and face, ensuring all attention remains on her striking presence. This image has a cinematic quality, reminiscent of high-end fashion photography, with a strong emphasis on texture, detail, and mood." image = pipe(prompt).images[0]
The community tab is the place to discuss and collaborate with the HF community!
