[Community Pipeline] : First proposal of a multilingual stable diffusion …

[juancopi81]

[Community Pipeline] Based on issue #871 I thought it would be nice to have a pipeline with multilingual support and @patrickvonplaten said it was a good idea! :)

Followed the format of #897.

Code example (Also added in the PR):

from PIL import Image

import torch

from diffusers import DiffusionPipeline
from transformers import (
    pipeline,
    MBart50TokenizerFast,
    MBartForConditionalGeneration,
)
device = "cuda" if torch.cuda.is_available() else "cpu"
device_dict = {"cuda": 0, "cpu": -1}

# helper function taken from: https://huggingface.co/blog/stable_diffusion
def image_grid(imgs, rows, cols):
    assert len(imgs) == rows*cols

    w, h = imgs[0].size
    grid = Image.new('RGB', size=(cols*w, rows*h))
    grid_w, grid_h = grid.size

    for i, img in enumerate(imgs):
        grid.paste(img, box=(i%cols*w, i//cols*h))
    return grid

# Add language detection pipeline
language_detection_model_ckpt = "papluca/xlm-roberta-base-language-detection"
language_detection_pipeline = pipeline("text-classification",
                                       model=language_detection_model_ckpt,
                                       device=device_dict[device])

# Add model for language translation
trans_tokenizer = MBart50TokenizerFast.from_pretrained("facebook/mbart-large-50-many-to-one-mmt")
trans_model = MBartForConditionalGeneration.from_pretrained("facebook/mbart-large-50-many-to-one-mmt").to(device)

diffuser_pipeline = DiffusionPipeline.from_pretrained(
    "CompVis/stable-diffusion-v1-4",
    custom_pipeline="multilingual_stable_diffusion",
    language_detection_pipeline=language_detection_pipeline,
    translation_model=trans_model,
    translation_tokenizer=trans_tokenizer,
    revision="fp16",
    torch_dtype=torch.float16,
)

diffuser_pipeline.enable_attention_slicing()
diffuser_pipeline = diffuser_pipeline.to(device)

prompt = ["a photograph of an astronaut riding a horse", 
          "Una casa en la playa",
          "Ein Hund, der Orange isst",
          "Un restaurant parisien"]

output = diffuser_pipeline(prompt)

images = output.images

grid = image_grid(images, rows=2, cols=2)

This example produces the following image:

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint.

[juancopi81]

Sorry I had some mistake so I am closing this pull request and go back to fix some issues.