How to use bdsqlsz/LCM_FIX_RANK1 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("latent-consistency/lcm-lora-sdxl", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("bdsqlsz/LCM_FIX_RANK1") prompt = "(masterpiece), (best quality), (super delicate), (illustration), (extremely delicate and beautiful), (dynamic angle), white and black highlights, (legendary Dragon Queen:1.3)ï¼1 girl), Hanfu, (complex details) (beautiful and delicate eyes), golden eyes, green pupils, delicate face, upper body, messy floating hair, messy hair, focus, perfect hands, (fantasy wind), <lora:sdxl_LCM_lora_rank1:1>, <lora:neg4all_bdsqlsz_xl_V7:1>" image = pipe(prompt).images[0]
The community tab is the place to discuss and collaborate with the HF community!