Saving Image Locally

[hi-sushanta]

I've expanded the Stable Diffusion pipeline's capabilities by introducing a new parameter that empowers you to preserve generated output locally, precisely where you wish.

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you read the contributor guideline?
• Did you read our philosophy doc (important for complex PRs)?
• Was this discussed/approved via a GitHub issue or the forum? Please add a link to it if that's the case.
• Did you make sure to update the documentation with your changes? Here are the
  documentation guidelines, and
  here are tips on formatting docstrings.
• Did you write any new necessary tests?

[sayakpaul]

We don't need this parameter as saving an image is just a one-liner.

[hi-sushanta]

But it's usefull to save generated output locally.
Example:

import torch
from diffusers import StableDiffusionPipeline

pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "a photo of an astronaut riding a horse on mars"
image = pipe(prompt,save_img_path="marse-with-horse.png")

[hi-sushanta]

And also it's small line of code.

[sayakpaul]

That is exactly the point.

prompt = "a photo of an astronaut riding a horse on mars"
image = pipe(prompt).images[0]
image.save("name.jpeg")

Does the job.

Then when num_images_per_prompt > 1, you have multiple output images. So, the behavior of save_img_path becomes undefined.

Plus there are other output formats we support too, such as "np", "pt", etc. So, its on the users how they wanna save it.

[patrickvonplaten]

Strongly agree with @sayakpaul here. Let's try to not bloat the pipelines too much