Improve latent diff example

[satpalsr]

Use GPU and improve code
Original Code:

# !pip install diffusers transformers
from diffusers import DiffusionPipeline

model_id = "CompVis/ldm-text2im-large-256"

# load model and scheduler
ldm = DiffusionPipeline.from_pretrained(model_id)

# run pipeline in inference (sample random noise and denoise)
prompt = "A painting of a squirrel eating a burger"
images = ldm([prompt], num_inference_steps=50, eta=0.3, guidance_scale=6).images

# save images
for idx, image in enumerate(images):
    image.save(f"squirrel-{idx}.png")

Generates an error (This PR fixes it):
AttributeError: 'dict' object has no attribute 'images'

[HuggingFaceDocBuilderDev]

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

[patrickvonplaten]

Hey @satpalsr,

The .images attribute will be added today! So the code should work then. Hope it's ok to close for now 😅

[patrickvonplaten]

@satpalsr - actually there were a couple of nice improvements. Could change the image API back to before and leave the rest? Happy to merge then :-)

[satpalsr]

Thanks for the info. Accepted the suggestions.

[patrickvonplaten]

Thanks!