from flask import Flask, request, jsonify, render_template_string
from transformers import AutoProcessor, AutoModelForCausalLM
import subprocess
import re
from PIL import Image
import io
# Install the necessary packages
subprocess.run('pip install flash-attn einops flask', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
app = Flask(__name__)
model = AutoModelForCausalLM.from_pretrained('gokaygokay/Florence-2-SD3-Captioner', trust_remote_code=True).eval()
processor = AutoProcessor.from_pretrained('gokaygokay/Florence-2-SD3-Captioner', trust_remote_code=True)
def modify_caption(caption: str) -> str:
"""
Removes specific prefixes from captions if present, otherwise returns the original caption.
Args:
caption (str): A string containing a caption.
Returns:
str: The caption with the prefix removed if it was present, or the original caption.
"""
# Define the prefixes to remove
prefix_substrings = [
('captured from ', ''),
('captured at ', '')
]
# Create a regex pattern to match any of the prefixes
pattern = '|'.join([re.escape(opening) for opening, _ in prefix_substrings])
replacers = {opening.lower(): replacer for opening, replacer in prefix_substrings}
# Function to replace matched prefix with its corresponding replacement
def replace_fn(match):
return replacers[match.group(0).lower()]
# Apply the regex to the caption
modified_caption = re.sub(pattern, replace_fn, caption, count=1, flags=re.IGNORECASE)
# If the caption was modified, return the modified version; otherwise, return the original
return modified_caption if modified_caption != caption else caption
@app.route('/')
def index():
html = '''
Florence-2 SD3 Long Captioner
Florence-2 SD3 Long Captioner
Florence-2 Base fine-tuned on Long SD3 Prompt and Image pairs. Check the Hugging Face link for datasets that are used for fine-tuning.
'''
return render_template_string(html)
@app.route('/generate', methods=['POST'])
def generate():
if 'image' not in request.files:
return jsonify({"error": "No image provided"}), 400
image_file = request.files['image']
image = Image.open(image_file.stream)
task_prompt = ""
prompt = task_prompt + "Describe this image in great detail."
# Ensure the image is in RGB mode
if image.mode != "RGB":
image = image.convert("RGB")
inputs = processor(text=prompt, images=image, return_tensors="pt")
generated_ids = model.generate(
input_ids=inputs["input_ids"],
pixel_values=inputs["pixel_values"],
max_new_tokens=1024,
num_beams=3
)
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0]
parsed_answer = processor.post_process_generation(generated_text, task=task_prompt, image_size=(image.width, image.height))
caption = modify_caption(parsed_answer[""])
return jsonify({"caption": caption})
if __name__ == '__main__':
app.run(debug=True, port=7860, host="0.0.0.0")