#!/usr/bin/env python3
from diffusers import DiffusionPipeline, DDIMScheduler
import argparse
import torch
from datasets import load_dataset
import PIL

IMAGE_OUTPUT_SIZE = (256, 256)
NUM_INFERENCE_STEPS = 100

def resize(image: PIL.Image):
    return image.resize(IMAGE_OUTPUT_SIZE, resample=PIL.Image.Resampling.LANCZOS)

def get_sd_eval(ckpt, guidance_scale=7.5):
    pipe = DiffusionPipeline.from_pretrained(ckpt, torch_dtype=torch.float16)
    pipe.to("cuda")
    pipe.scheduler = DDIMScheduler.from_config(pipe.config)

    def sd_eval(prompt):
        images = pipe(prompt, num_inference_steps=100, guidance_scale=guidance_scale).images
        images = [resize(image) for image in images]
        return images

    return sd_eval

def get_karlo_eval(ckpt):
    pipe = DiffusionPipeline.from_pretrained(ckpt, torch_dtype=torch.float16)
    pipe.to("cuda")

    def karlo_eval(prompt):
        images = pipe(prompt, prior_num_inference_steps=50, decoder_num_inference_steps=100).images
        return images

    return karlo_eval

def get_if_eval(ckpt):
    pipe_low = DiffusionPipeline.from_pretrained(ckpt, torch_dtype=torch.float16)
    pipe_low.enable_model_cpu_offload()

    pipe_up = DiffusionPipeline.from_pretrained("DeepFloyd/IF-II-L-v1.0", text_encoder=pipe_low.text_encoder, torch_dtype=torch.float16)
    pipe_up.enable_model_cpu_offload()

    def sd_eval(prompt):
        images = pipe_low(prompt, num_inference_steps=100, output_type="pt").images
        images = pipe_up(promtp=prompt, images=images, num_inference_steps=100).images
        return images

    return sd_eval

MODELS = {
    "runwayml/stable-diffusion-v1-5": get_sd_eval,
    "stabilityai/stable-diffusion-v2-1": get_sd_eval,
    "kakaobrain/karlo-alpha": get_karlo_eval,
    "DeepFloyd/IF-I-XL-v1.0": get_if_eval,
}




if __name__ == "__main__":
    parser = argparse.ArgumentParser(description='Run Parti Prompt Evaluation')
    parser.add_argument('model_repo_or_id', type=str, help='ID or URL of the model repository.', required=True)
    parser.add_argument('--dataset_repo_or_id', type=str, default='diffusers/prompt_generations', help='ID or URL of the dataset repository (default: "diffusers/prompt_generations")')
    parser.add_argument('--batch_size', type=int, default=8, help="Batch size for the eval function")
    parser.add_argument('--upload_to_hub', action='store_true', help='whether to upload the dataset to the Hugging Face dataset hub')

    args = parser.parse_args()

    eval_fn = MODELS[args.model_repo_or_id](args.model_repo_or_id)

    dataset = load_dataset("nateraw/parti-prompts")

    def map_fn(batch):
        batch["images"] = eval_fn(batch["prompt"])
        return batch

    dataset_images = dataset.map(map_fn, batched=True, batch_size=8)

    if args.upload_to_hub:
        dataset.push_to_hub(args.dataset_repo_or_id)
    else:
        dataset.save_to_disk(args.dataset_repo_or_id.split("/")[-1])