fix a bug in StableDiffusionUpscalePipeline when prompt is None

[yiyixuxu]

fix a bug described here
#4249 (comment)

this example currently fails but will work with this fix

import requests
from PIL import Image
from io import BytesIO
from diffusers import StableDiffusionUpscalePipeline
import torch

# load model and scheduler
model_id = "stabilityai/stable-diffusion-x4-upscaler"
pipeline = StableDiffusionUpscalePipeline.from_pretrained(
    model_id, revision="fp16", torch_dtype=torch.float16
     )
pipeline = pipeline.to("cuda")

# let's download an  image
url = "https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/sd2-upscale/low_res_cat.png"
response = requests.get(url)
low_res_img = Image.open(BytesIO(response.content)).convert("RGB")
low_res_img = low_res_img.resize((128, 128))
prompt = "a white cat"

prompt_embeds = pipeline._encode_prompt(prompt, "cuda", 1, True)
prompt_embeds, _ = prompt_embeds.chunk(2)

upscaled_image = pipeline(image=[low_res_img] * 1, prompt_embeds = prompt_embeds).images[0]

[HuggingFaceDocBuilderDev]

The documentation is not available anymore as the PR was closed or merged.

[patrickvonplaten]

Can we add a test here as well? :-)

[patrickvonplaten]

Thanks for adding the test :-)