stabilityai/stable-diffusion-2-1 生成黑图问题

stabilityai/stable-diffusion-2-1 · Only generates black images?

Loading saved model downloaded from stabilityai/stable-diffusion-2-1

stable_2_1 = StableDiffusionPipeline.from_pretrained(
  "/var/app/models/ldm/sd-2-1/",
  torch_dtype=float16
  ).to("cuda")
stable_2_1.enable_attention_slicing()

All I am getting is black images, running code that worked with 1.5. I'm using an A10 gpu. It is not flagging them as NSFW, and it takes a normal amount of time to do the generation.