Added PhotoDoodle Pipeline

[AMEERAZAM08]

What does this PR do?

Fixes # (issue)

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?

Who can review?

@sayakpaul ,@yiyixuxu and @asomoza

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

[AMEERAZAM08]

Hi @sayakpaul ,
Please take a look at this PR, thank you for your help :)

[AMEERAZAM08]

@DN6 @a-r-r-o-w please review this PR ,
Thanks

[AMEERAZAM08]

@sayakpaul Any other can review this

[a-r-r-o-w]

Hi, there is an excessive amount of unrelated changes that make this PR hard to review. Could you please rebase with main such that only the changes related to PhotoDoodle persist? You can follow some of the past PRs for an example on the expected changes: #10660, #11428, #10136

Additionally, I think if we tried shipping this in the community projects folder, we could review it faster

[AMEERAZAM08]

I wanted to merge in diffuser
it can easily
import diffusers from PhotoDoodlePipeline
@a-r-r-o-w Now Updated .

[AMEERAZAM08]

Hi @DN6 , @a-r-r-o-w change has been done

[AMEERAZAM08]

@a-r-r-o-w can you review this we need it in diffusers pipeline
cc: @sayakpaul

[a-r-r-o-w]

@yiyixuxu Could you take a look here/test if you have the bandwidth?

[github-actions]

This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.

Please note that issues that do not follow the contributing guidelines are likely to be ignored.

[yiyixuxu]

cc @dg845 can you take a look here?

[dg845]

As far as I can tell, this pipeline is essentially identical to FluxKontextPipeline, as both accept a conditioning image argument which is encoded by the VAE to image_latents, packed, and concatenated with the packed latents in the patch sequence dimension (dim 1). The example from pipeline_photodoodle.py works quite well with FluxKontextPipeline:

import torch
from diffusers import FluxKontextPipeline
from diffusers.utils import load_image

pipe = FluxKontextPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
pipe = pipe.to("cuda")

pipe.load_lora_weights(
    "nicolaus-huang/PhotoDoodle", adapter_name="pretrain", weight_name="pretrain.safetensors"
)
pipe.load_lora_weights(
    "nicolaus-huang/PhotoDoodle", adapter_name="magiceffects", weight_name="sksmagiceffects.safetensors"
)
pipe.set_adapters(["pretrain", "magiceffects"], [1.0, 1.0])

image = load_image(
    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg"
)
prompt = "add a halo and wings for the astronaut by sksmagiceffects"

output_image = pipe(
    image=image,
    prompt=prompt,
    height=image.height,
    width=image.width,
    num_inference_steps=28,
    guidance_scale=3.5,
    generator=torch.Generator().manual_seed(42),
).images[0]

output_image.save("photodoodle_results.png")

So I don't think there is a need to merge this PR.

[AMEERAZAM08]

I agree that this is present now, but it was not there earlier.

@dg845
Alternatively, we can move the code sample to the community code section.
Please let me know if you would like me to create a pull request for this.

[AMEERAZAM08]

@dg845 let me know

[AMEERAZAM08]

added in community
@dg845
thanks