from datasets import load_dataset

# prompts = load_dataset("nateraw/parti-prompts", split="train")
# prompts = prompts.shuffle()
# sample_prompts = [prompts[i]["Prompt"] for i in range(5)]

# Fixing these sample prompts in the interest of reproducibility.
sample_prompts = [
    "a corgi",
    "a hot air balloon with a yin-yang symbol, with the moon visible in the daytime sky",
    "a car with no windows",
    "a cube made of porcupine",
    'The saying "BE EXCELLENT TO EACH OTHER" written on a red brick wall with a graffiti image of a green alien wearing a tuxedo. A yellow fire hydrant is on a sidewalk in the foreground.',
]

import torch

seed = 0
generator = torch.manual_seed(seed)

images = sd_pipeline(sample_prompts, num_images_per_prompt=1, generator=generator).images

from diffusers import StableDiffusionPipeline
import torch

model_ckpt = "CompVis/stable-diffusion-v1-4"
sd_pipeline = StableDiffusionPipeline.from_pretrained(model_ckpt, torch_dtype=torch.float16).to("cuda")

prompts = [
    "a photo of an astronaut riding a horse on mars",
    "A high tech solarpunk utopia in the Amazon rainforest",
    "A pikachu fine dining with a view to the Eiffel Tower",
    "A mecha robot in a favela in expressionist style",
    "an insect robot preparing a delicious meal",
    "A small cabin on top of a snowy mountain in the style of Disney, artstation",
]

images = sd_pipeline(prompts, num_images_per_prompt=1, output_type="np").images

print(images.shape)
# (6, 512, 512, 3)

from torchmetrics.functional.multimodal import clip_score
from functools import partial

clip_score_fn = partial(clip_score, model_name_or_path="openai/clip-vit-base-patch16")

def calculate_clip_score(images, prompts):
    images_int = (images * 255).astype("uint8")
    clip_score = clip_score_fn(torch.from_numpy(images_int).permute(0, 3, 1, 2), prompts).detach()
    return round(float(clip_score), 4)

sd_clip_score = calculate_clip_score(images, prompts)
print(f"CLIP score: {sd_clip_score}")
# CLIP score: 35.7038

seed = 0
generator = torch.manual_seed(seed)

images = sd_pipeline(prompts, num_images_per_prompt=1, generator=generator, output_type="np").images

model_ckpt_1_5 = "runwayml/stable-diffusion-v1-5"
sd_pipeline_1_5 = StableDiffusionPipeline.from_pretrained(model_ckpt_1_5, torch_dtype=weight_dtype).to(device)

images_1_5 = sd_pipeline_1_5(prompts, num_images_per_prompt=1, generator=generator, output_type="np").images

sd_clip_score_1_4 = calculate_clip_score(images, prompts)
print(f"CLIP Score with v-1-4: {sd_clip_score_1_4}")
# CLIP Score with v-1-4: 34.9102

sd_clip_score_1_5 = calculate_clip_score(images_1_5, prompts)
print(f"CLIP Score with v-1-5: {sd_clip_score_1_5}")
# CLIP Score with v-1-5: 36.2137

from datasets import load_dataset

dataset = load_dataset("sayakpaul/instructpix2pix-demo", split="train")
dataset.features

{'input': Value(dtype='string', id=None),
 'edit': Value(dtype='string', id=None),
 'output': Value(dtype='string', id=None),
 'image': Image(decode=True, id=None)}

idx = 0
print(f"Original caption: {dataset[idx]['input']}")
print(f"Edit instruction: {dataset[idx]['edit']}")
print(f"Modified caption: {dataset[idx]['output']}")

Original caption: 2. FAROE ISLANDS: An archipelago of 18 mountainous isles in the North Atlantic Ocean between Norway and Iceland, the Faroe Islands has 'everything you could hope for', according to Big 7 Travel. It boasts 'crystal clear waterfalls, rocky cliffs that seem to jut out of nowhere and velvety green hills'
Edit instruction: make the isles all white marble
Modified caption: 2. WHITE MARBLE ISLANDS: An archipelago of 18 mountainous white marble isles in the North Atlantic Ocean between Norway and Iceland, the White Marble Islands has 'everything you could hope for', according to Big 7 Travel. It boasts 'crystal clear waterfalls, rocky cliffs that seem to jut out of nowhere and velvety green hills'

dataset[idx]["image"]

from diffusers import StableDiffusionInstructPix2PixPipeline

instruct_pix2pix_pipeline = StableDiffusionInstructPix2PixPipeline.from_pretrained(
    "timbrooks/instruct-pix2pix", torch_dtype=torch.float16
).to(device)

import numpy as np


def edit_image(input_image, instruction):
    image = instruct_pix2pix_pipeline(
        instruction,
        image=input_image,
        output_type="np",
        generator=generator,
    ).images[0]
    return image

input_images = []
original_captions = []
modified_captions = []
edited_images = []

for idx in range(len(dataset)):
    input_image = dataset[idx]["image"]
    edit_instruction = dataset[idx]["edit"]
    edited_image = edit_image(input_image, edit_instruction)

    input_images.append(np.array(input_image))
    original_captions.append(dataset[idx]["input"])
    modified_captions.append(dataset[idx]["output"])
    edited_images.append(edited_image)

from transformers import (
    CLIPTokenizer,
    CLIPTextModelWithProjection,
    CLIPVisionModelWithProjection,
    CLIPImageProcessor,
)

clip_id = "openai/clip-vit-large-patch14"
tokenizer = CLIPTokenizer.from_pretrained(clip_id)
text_encoder = CLIPTextModelWithProjection.from_pretrained(clip_id).to(device)
image_processor = CLIPImageProcessor.from_pretrained(clip_id)
image_encoder = CLIPVisionModelWithProjection.from_pretrained(clip_id).to(device)

import torch.nn as nn
import torch.nn.functional as F


class DirectionalSimilarity(nn.Module):
    def __init__(self, tokenizer, text_encoder, image_processor, image_encoder):
        super().__init__()
        self.tokenizer = tokenizer
        self.text_encoder = text_encoder
        self.image_processor = image_processor
        self.image_encoder = image_encoder

    def preprocess_image(self, image):
        image = self.image_processor(image, return_tensors="pt")["pixel_values"]
        return {"pixel_values": image.to(device)}

    def tokenize_text(self, text):
        inputs = self.tokenizer(
            text,
            max_length=self.tokenizer.model_max_length,
            padding="max_length",
            truncation=True,
            return_tensors="pt",
        )
        return {"input_ids": inputs.input_ids.to(device)}

    def encode_image(self, image):
        preprocessed_image = self.preprocess_image(image)
        image_features = self.image_encoder(**preprocessed_image).image_embeds
        image_features = image_features / image_features.norm(dim=1, keepdim=True)
        return image_features

    def encode_text(self, text):
        tokenized_text = self.tokenize_text(text)
        text_features = self.text_encoder(**tokenized_text).text_embeds
        text_features = text_features / text_features.norm(dim=1, keepdim=True)
        return text_features

    def compute_directional_similarity(self, img_feat_one, img_feat_two, text_feat_one, text_feat_two):
        sim_direction = F.cosine_similarity(img_feat_two - img_feat_one, text_feat_two - text_feat_one)
        return sim_direction

    def forward(self, image_one, image_two, caption_one, caption_two):
        img_feat_one = self.encode_image(image_one)
        img_feat_two = self.encode_image(image_two)
        text_feat_one = self.encode_text(caption_one)
        text_feat_two = self.encode_text(caption_two)
        directional_similarity = self.compute_directional_similarity(
            img_feat_one, img_feat_two, text_feat_one, text_feat_two
        )
        return directional_similarity

dir_similarity = DirectionalSimilarity(tokenizer, text_encoder, image_processor, image_encoder)
scores = []

for i in range(len(input_images)):
    original_image = input_images[i]
    original_caption = original_captions[i]
    edited_image = edited_images[i]
    modified_caption = modified_captions[i]

    similarity_score = dir_similarity(original_image, edited_image, original_caption, modified_caption)
    scores.append(float(similarity_score.detach().cpu()))

print(f"CLIP directional similarity: {np.mean(scores)}")
# CLIP directional similarity: 0.0797976553440094

from zipfile import ZipFile
import requests


def download(url, local_filepath):
    r = requests.get(url)
    with open(local_filepath, "wb") as f:
        f.write(r.content)
    return local_filepath

dummy_dataset_url = "https://hf.co/datasets/sayakpaul/sample-datasets/resolve/main/sample-imagenet-images.zip"
local_filepath = download(dummy_dataset_url, dummy_dataset_url.split("/")[-1])

with ZipFile(local_filepath, "r") as zipper:
    zipper.extractall(".")

from PIL import Image
import os

dataset_path = "sample-imagenet-images"
image_paths = sorted([os.path.join(dataset_path, x) for x in os.listdir(dataset_path)])

real_images = [np.array(Image.open(path).convert("RGB")) for path in image_paths]

from torchvision.transforms import functional as F


def preprocess_image(image):
    image = torch.tensor(image).unsqueeze(0)
    image = image.permute(0, 3, 1, 2) / 255.0
    return F.center_crop(image, (256, 256))

real_images = torch.cat([preprocess_image(image) for image in real_images])
print(real_images.shape)
# torch.Size([10, 3, 256, 256])

from diffusers import DiTPipeline, DPMSolverMultistepScheduler

dit_pipeline = DiTPipeline.from_pretrained("facebook/DiT-XL-2-256", torch_dtype=torch.float16)
dit_pipeline.scheduler = DPMSolverMultistepScheduler.from_config(dit_pipeline.scheduler.config)
dit_pipeline = dit_pipeline.to("cuda")

words = [
    "cassette player",
    "chainsaw",
    "chainsaw",
    "church",
    "gas pump",
    "gas pump",
    "gas pump",
    "parachute",
    "parachute",
    "tench",
]

class_ids = dit_pipeline.get_label_ids(words)
output = dit_pipeline(class_labels=class_ids, generator=generator, output_type="np")

fake_images = output.images
fake_images = torch.tensor(fake_images)
fake_images = fake_images.permute(0, 3, 1, 2)
print(fake_images.shape)
# torch.Size([10, 3, 256, 256])

from torchmetrics.image.fid import FrechetInceptionDistance

fid = FrechetInceptionDistance(normalize=True)
fid.update(real_images, real=True)
fid.update(fake_images, real=False)

print(f"FID: {float(fid.compute())}")
# FID: 177.7147216796875