How to use ManyWayne/ELISIA 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-Raw", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("ManyWayne/ELISIA") prompt = "omnielisia, A cozy, close-up mirror selfie of an woman with standing inches away from a vanity mirror in a sunlit bedroom. She wears an oversized cream cable-knit sweater with the collar slightly bunched up. She leans her forehead almost against the glass, holding the phone at chin level. Soft morning sunlight creates a hazy, ethereal glow, blurring the background into a soft bokeh. The focus is sharp on the reflection of her eyes and the fine knit fibers of her sweater. Photorealistic, highly detailed. Sharp focus on the face, contrasting with the smooth gradients of the background. retain natural pores and texture. Fair skin that displays a natural, high-resolution texture with visible pores, high-resolution eyelashes of premium quality." image = pipe(prompt).images[0]
The community tab is the place to discuss and collaborate with the HF community!
