sd-community

/

sdxl-flash-lora

like 6

Follow

Stable Diffusion Community (Unofficial, Non-profit) 91

i use a code

import torch
from diffusers import StableDiffusionXLPipeline, DPMSolverSinglestepScheduler
# Load model.
pipe = StableDiffusionXLPipeline.from_pretrained("sd-community/sdxl-flash", torch_dtype=torch.float16).to("cuda")
# Ensure sampler uses "trailing" timesteps.
pipe.scheduler = DPMSolverSinglestepScheduler.from_config(pipe.scheduler.config, timestep_spacing="trailing")
# Image generation.
pipe("a happy dog, sunny day, realism", num_inference_steps=7, guidance_scale=3).images[0].save("output.png")

However, the output.png image is completely black