from transformers import AutoModel
import numpy as np
from PIL import Image
import torch
import os
images = [
        "path_to_image1.jpg",
        "path_to_image2.png",
def read_image_as_np_array(image_path):
    with open(image_path, "rb") as file:
        image = Image.open(file).convert("L").convert("RGB")
        image = np.array(image)
    return image
images = [read_image_as_np_array(image) for image in images]
model = AutoModel.from_pretrained("ragavsachdeva/magi", trust_remote_code=True).cuda()
with torch.no_grad():
    results = model.predict_detections_and_associations(images)
    text_bboxes_for_all_images = [x["texts"] for x in results]
    ocr_results = model.predict_ocr(images, text_bboxes_for_all_images)
for i in range(len(images)):
    model.visualise_single_image_prediction(images[i], results[i], filename=f"image_{i}.png")
    model.generate_transcript_for_single_image(results[i], ocr_results[i], filename=f"transcript_{i}.txt")

from PIL import Image
import numpy as np
from transformers import AutoModel
import torch
model = AutoModel.from_pretrained("ragavsachdeva/magiv2", trust_remote_code=True).cuda().eval()
def read_image(path_to_image):
    with open(path_to_image, "rb") as file:
        image = Image.open(file).convert("L").convert("RGB")
        image = np.array(image)
    return image
chapter_pages = ["page1.png", "page2.png", "page3.png" ...]
character_bank = {
    "images": ["char1.png", "char2.png", "char3.png", "char4.png" ...],
    "names": ["Luffy", "Sanji", "Zoro", "Ussop" ...]
chapter_pages = [read_image(x) for x in chapter_pages]
character_bank["images"] = [read_image(x) for x in character_bank["images"]]
with torch.no_grad():
    per_page_results = model.do_chapter_wide_prediction(chapter_pages, character_bank, use_tqdm=True, do_ocr=True)
transcript = []
for i, (image, page_result) in enumerate(zip(chapter_pages, per_page_results)):
    model.visualise_single_image_prediction(image, page_result, f"page_{i}.png")
    speaker_name = {
        text_idx: page_result["character_names"][char_idx] for text_idx, char_idx in page_result["text_character_associations"]
    for j in range(len(page_result["ocr"])):
        if not page_result["is_essential_text"][j]:
            continue
        name = speaker_name.get(j, "unsure") 
        transcript.append(f"<{name}>: {page_result['ocr'][j]}")
with open(f"transcript.txt", "w") as fh:
    for line in transcript:
        fh.write(line + "\n")