How to use lucasnguyen69/asian with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("krea/Krea-2-Turbo", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("lucasnguyen69/asian") prompt = "The image portrays a young woman with dark hair styled in an elegant updo, adorned with a delicate, ornate gold hairpin shaped like a butterfly or wing motif, accented with subtle red and black detailing. She wears a deep blue, satin-like yukata or robe, featuring a low-cut neckline and white-trimmed edges, decorated with small, stylized white daisies with blue centers. Her skin glows softly under warm, directional lighting that highlights her collarbone and décolletage, creating a sensual yet serene atmosphere. Her gaze is direct and intimate, with large, expressive eyes and a gentle, parted-lip expression. Behind her, blurred floral arrangements in soft pinks and whites add a romantic, dreamy backdrop, while the background suggests a traditional Japanese interior with muted tones and paper screens. The composition is intimate, focusing on her upper body and face, with her hands resting gently near her chest, fingers slightly curled. The overall aesthetic blends traditional Japanese aesthetics with modern, soft-focus photography, evoking a tranquil, alluring mood. The image contains no recognizable text. " image = pipe(prompt).images[0]
The community tab is the place to discuss and collaborate with the HF community!
