CompVis

/

stable-diffusion-v1-4

like 6.56k

Follow

CompVis 1,121

Hi,

Today, I just randomly started to get a new error message in certain instances when using the diffusers library to run SD. I'm not sure what the message is referring to, and I've never seen it before now. The model works and I do get a valid output.

Here is the code I am testing with:

import torch
from torch import autocast
from diffusers import StableDiffusionPipeline

model_id = "CompVis/stable-diffusion-v1-4"
device = "cuda"


pipe = StableDiffusionPipeline.from_pretrained(model_id, use_auth_token=True)
pipe = pipe.to(device)

prompt = "a photo of an astronaut riding a horse on mars"
with autocast("cuda"):
    image = pipe(prompt, guidance_scale=7.5)["sample"][0]  
    
image.save("astronaut_rides_horse.png")

Here is the message I get. Is anyone else seeing this?

{'trained_betas'} was not found in config. Values will be initialized to default values.