How to use MomlessTomato/kasumi-nakasu with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Laxhar/noobai-XL-Vpred-1.0", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("MomlessTomato/kasumi-nakasu") prompt = "ninakkas, love live! school idol festival all stars, masterpiece, best quality, cel shading, cinematic lighting, 1girl, standing, idol dress, frilled skirt, sleeveless dress, thighhighs, hair ribbon, pastel colors looking at viewer, smile, cheerful, stage, spotlight, hearts, small breasts, thick thighs" image = pipe(prompt).images[0]
The community tab is the place to discuss and collaborate with the HF community!
