How to use joyfox/Kontext-Mythical-LoRA with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-Kontext-dev", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("joyfox/Kontext-Mythical-LoRA") prompt = "turn the woman in the picture into a beautiful young woman, wearing a fairy-like long dress with white and light green interwoven, with lightly flowing sleeves, long hair like ink, adorned with delicate hair accessories, and holding a jade staff in an elegant posture. She stands in a fairyland with misty clouds, the atmosphere is beautiful and ethereal, and her eyes are clear and resolute, like a fairy in the fairyland. The overall picture is beautiful and delicate, surrounded by fairy spirit. Keep the facial features unchanged" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0]
What is a pickle import?
