How to use Hack337/flux-lora-Uni with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Hack337/flux-lora-Uni") prompt = "uni laying in a cardboard box on the floor, with a blurred background" image = pipe(prompt).images[0]
do i use "lora:uni:1" to weight it or is there some other value (e.g. 0.85) to weight the lora with
I used a weight of 1, but you can experiment with other weights.
· Sign up or log in to comment
