Firdavs Shodiev Firdavs-coder

Hi there, I'm Firdavs 👋

I’m a Computer Science Engineering student at the University of Miskolc.
I enjoy working with Python, Java, and FastAPI, and I’m interested in AI, APIs, and backend development.

I like creating projects that combine AI and practical applications – for example, APIs for image processing, background removal, or summarizing audio. I also enjoy learning about operating systems, data structures, and algorithms to strengthen my computer science foundation.


AI Image and Video Background Remover Remove image and video backgrounds instantly	AI Picture Upscaler and Face Restoration Enhance image resolution with AI	AI Watermark Remover Erase watermarks from photos
Uzbek & Multiple Language Subtitler using AI Generate subtitles in multiple languages	AI Content Detector for 28 languages Check if text is AI-generated or human for 28 languages	AI Object Remover Remove unwanted objects from images
AI Picture Colorizer Turn black & white photos into color	Image and Video FaceSwap Swap faces in images and videos easily	AI Calorie Tracker Estimate calories from meal photos
AI Content Humanizer Make AI-generated text sound human

My Projects

AI Background Remover

Original	Result 1	Result 2	Result 3	Result 4	Result 5

Original	Prompt	Result	Original	Prompt	Result
	Elegant European plaza, soft afternoon sunlight, stone archways, old city charm, warm tones, clear sky, photorealistic			A futuristic cityscape with neon lights and flying cars, in a cyberpunk style

Original	Result 1	Result 2

Uzbek & Multiple Language Subtitler using AI

Preview	Preview	Preview	Preview
result3.mp4	result2.mp4	result.mp4	result1.mp4
result.mp4	result4.mp4	result.mp4	result.mp4

AI Picture Upscaler

Original	Result	Original	Result

AI Content Detector

Method	Description
Fast Detect Advanced	Uses larger parameter models (7B) for both sampling and scoring. Offers the highest accuracy among fast detection methods while maintaining good speed. Recommended for general-purpose detection when balance between accuracy and speed is needed.
Fast Detect Basic	Employs smaller parameter models (2.7B) for both sampling and scoring. Faster processing time but slightly lower accuracy. Good for quick initial assessments and situations where computational resources are limited.
Glimpse Premium	Top-tier multilingual detection supporting 26 languages. Uses the most powerful models for scoring text across multiple languages. Highest accuracy but more computationally intensive. Best for critical content verification.
Glimpse Standard	Balanced multilingual detection supporting 26 languages. Uses efficient models to provide good accuracy across languages. Less resource-intensive than Premium while maintaining solid detection capabilities. Suitable for routine multilingual content verification.