error in using stable cascede

[saeedkhanehgir]

Hello,
Thanks for sharing this project.

I want to run stable cascade inference code but I get the below warning and my final "cascade.png" image is all black.

inference code :

import torch
from diffusers import StableCascadeDecoderPipeline, StableCascadePriorPipeline

prompt = "a man"
negative_prompt = ""

prior = StableCascadePriorPipeline.from_pretrained(
    "stabilityai/stable-cascade-prior", torch_dtype=torch.float16
)
decoder = StableCascadeDecoderPipeline.from_pretrained(
    "stabilityai/stable-cascade", torch_dtype=torch.float16
)

prior.enable_model_cpu_offload()
prior_output = prior(
    prompt=prompt,
    height=1024,
    width=1024,
    negative_prompt=negative_prompt,
    guidance_scale=4.0,
    num_images_per_prompt=1,
    num_inference_steps=20,
)

decoder.enable_model_cpu_offload()
decoder_output = decoder(
    image_embeddings=prior_output.image_embeddings.to(torch.float16),
    prompt=prompt,
    negative_prompt=negative_prompt,
    guidance_scale=0.0,
    output_type="pil",
    num_inference_steps=10,
).images[0]
decoder_output.save("cascade.png")

my warning :

my env:

diffusers==0.27.2
torch==2.0.1
torchvision==0.15.2
cuda11.8

I can run other stable diffusion models such as SDXL correctly with this env and my device.

Thanks