combined_pipe.py

#!/usr/bin/env python3
from diffusers import AutoPipelineForText2Image, AutoPipelineForImage2Image,  AutoPipelineForInpainting
from diffusers.utils import load_image
from pathlib import Path
import torch
import numpy as np
import requests
from io import BytesIO
from PIL import Image
from huggingface_hub import HfApi
import os

api = HfApi()

url = "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"
response = requests.get(url)
original_image = Image.open(BytesIO(response.content)).convert("RGB")
original_image = original_image.resize((768, 512))

original_image = load_image(
    "https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main" "/kandinsky/cat.png"
)

mask = np.ones((768, 768), dtype=np.float32)
# Let's mask out an area above the cat's head
mask[:250, 250:-250] = 0

# pipe = AutoPipelineForText2Image.from_pretrained("kandinsky-community/kandinsky-2-1", torch_dtype=torch.float16)
# pipe = AutoPipelineForImage2Image.from_pretrained("kandinsky-community/kandinsky-2-1", torch_dtype=torch.float16)
pipe = AutoPipelineForInpainting.from_pretrained("kandinsky-community/kandinsky-2-1", torch_dtype=torch.float16)

# pipe = AutoPipelineForText2Image.from_pretrained("kandinsky-community/kandinsky-2-2-decoder", torch_dtype=torch.float16)
# pipe = AutoPipelineForImage2Image.from_pretrained("kandinsky-community/kandinsky-2-2-decoder", torch_dtype=torch.float16)
# pipe = AutoPipelineForInpainting.from_pretrained("kandinsky-community/kandinsky-2-2-decoder-inpaint", torch_dtype=torch.float16)
pipe.enable_model_cpu_offload()

prompt = "A lion in galaxies, spirals, nebulae, stars, smoke, iridescent, intricate detail, octane render, 8k"
negative_prompt = ""

prompt = "A fantasy landscape, Cinematic lighting"
prompt = "a hat"
negative_prompt = "low quality, bad quality"

# rompts = ["a cat playing with a ball++ in the forest", "a cat playing with a ball++ in the forest", "a cat playing with a ball-- in the forest"]

# prompt_embeds = torch.cat([compel.build_conditioning_tensor(prompt) for prompt in prompts])

# generator = [torch.Generator(device="cuda").manual_seed(0) for _ in range(prompt_embeds.shape[0])]
#
# url = "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"
 
# response = requests.get(url)
# image = Image.open(BytesIO(response.content)).convert("RGB")
# image.thumbnail((768, 768))


generator = torch.Generator(device="cpu").manual_seed(0)
# images = pipe(prompt=prompt, generator=generator, num_images_per_prompt=1, num_inference_steps=25).images
# images = pipe(prompt=prompt, image=original_image, generator=generator, num_images_per_prompt=1, num_inference_steps=25).images
images = pipe(prompt=prompt, image=original_image, mask_image=mask, generator=generator, num_images_per_prompt=1, num_inference_steps=25).images

for i, image in enumerate(images):
    file_name = f"bb_1_{i}"
    path = os.path.join(Path.home(), "images", f"{file_name}.png")
    image.save(path)

    api.upload_file(
        path_or_fileobj=path,
        path_in_repo=path.split("/")[-1],
        repo_id="patrickvonplaten/images",
        repo_type="dataset",
    )
    print(f"https://huggingface.co/datasets/patrickvonplaten/images/blob/main/{file_name}.png")