from huggingface_hub import notebook_login

notebook_login()

import os
import torch

import PIL
from PIL import Image

from diffusers import StableDiffusionPipeline
from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer


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

pretrained_model_name_or_path = "stable-diffusion-v1-5/stable-diffusion-v1-5"
repo_id_embeds = "sd-concepts-library/cat-toy"

pipeline = StableDiffusionPipeline.from_pretrained(pretrained_model_name_or_path, torch_dtype=torch.float16).to("cuda")

pipeline.load_textual_inversion(repo_id_embeds)

prompt = "a grafitti in a favela wall with a <cat-toy> on it"

num_samples = 2
num_rows = 2

all_images = []
for _ in range(num_rows):
    images = pipe(prompt, num_images_per_prompt=num_samples, num_inference_steps=50, guidance_scale=7.5).images
    all_images.extend(images)

grid = image_grid(all_images, num_samples, num_rows)
grid