How to use ByteDance/SDXL-Lightning with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ByteDance/SDXL-Lightning", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0]
Hello, I have noticed some artifacts in the images that are generated from the 8-step model + 8-step LoRA. Any ideas on how to fix this/settings I should be using?
Never mind, I found the issue! It was the LoRA causing the artifacts
· Sign up or log in to comment