PRITHIV SAKTHI U R

Computer Vision

https://www.opentalent.in/prithiv-sakthi-u-r-1

Computer Vision, Multimodal AI

TN, India

Key Strengths

Extensive practical experience with various Vision-Language Models (VLMs) and image generation/editing techniques.
Demonstrated ability to work with advanced AI models like Qwen, SigLIP, and FLUX.
Proficiency in Python and Jupyter Notebooks for AI/ML development and experimentation.
Strong focus on real-world application of computer vision concepts, including image editing, classification, and OCR.
Experience with Hugging Face ecosystem for model deployment and experimentation.

Cultural & Operational Fit

Cultural Fit Analysis

The candidate's projects demonstrate a strong interest in cutting-edge AI/ML research and open-source contributions, which aligns well with an innovative and collaborative culture. The diversity of projects, from image editing to OCR and VLM exploration, indicates a broad curiosity and willingness to tackle different challenges. However, the lack of team-based projects or professional experience makes it difficult to fully assess cultural fit in a corporate environment.

Soft Skills & Operational Fit

Insufficient data to assess soft skills and operational fit. No psychometric test results or interview feedback provided.

AI is analyzing your overall score…

Identifying your key strengths…

Evaluating your skill match against the job requirements…

Assessing your cultural and operational fit

Projects

FireRed-Image-Edit-1.0-Fast

February 26, 2026 – Present

FireRed-Image-Edit-1.0-Fast is a high-performance, AI-driven image editing application that utilizes advanced diffusers and the QIE+ Pipeline for precise, prompt-based image modifications.

View Project

Qwen-Image-Edit-2511-LoRAs-Fast-Lazy-Load

January 1, 2026 – Present

Demonstration for the Qwen-Image-Edit-2511 model with lazy-loaded LoRA adapters for advanced single- and multi-image editing. Supports 7+ specialized LoRAs including photo-to-anime, multi-angle camera control, pose transfer (Any-Pose), upscaling, style transfer, light migration, and manga tone. Features fast inference (4 steps default).

View Project

Qwen-Image-Edit-2509-LoRAs-Fast

November 13, 2025 – Present

Qwen-Image-Edit-2509-LoRAs-Fast is a high-performance, user-friendly web application built with Gradio that leverages the advanced Qwen/Qwen-Image-Edit-2509 model from Hugging Face for seamless image editing tasks.

View Project

Multimodal-Outpost-Notebooks

July 29, 2025 – Present

This repository contains a curated collection of notebooks for implementing state-of-the-art multimodal Vision-Language Models (VLMs).

View Project

OCR-ReportLab-Notebooks

July 3, 2025 – Present

A dedicated Colab notebooks to experiment (Nanonets OCR, Monkey OCR, OCRFlux 3B, Typhoo OCR 3B & more..) On T4 GPU - free tier

View Project

FineTuning-SigLIP-2

March 8, 2025 – July 22, 2025

Fine-Tuning SigLIP 2 for Single/Multi-Label Image Classification. Image classification vision-language encoder model fine-tuned for Image Classification Tasks

View Project

FLUX-REALISM

September 8, 2024 – Present

FLUX-REALISM is an experimental, advanced image generation application designed to provide highly realistic image synthesis workflows. Powered by the state-of-the-art FLUX architecture, the suite offers a dual-model workspace featuring FLUX.1-Krea-dev and a specialized FLUX.1-dev.

View Project

Save-web-as-zip

June 18, 2024 – May 17, 2025

Save any web url as zip ( image + assets + html + css + js )

View Project

How-to-run-huggingface-spaces-on-local-machine-demo

June 17, 2024 – July 17, 2024

Running Hugging Face Spaces on a local machine / colab T4 GPU involves several steps. Hugging Face Spaces is a platform to host machine learning demos and applications using Streamlit, Gradio, or other frameworks.

View Project

Huggingface-Android-Application

May 2, 2024 – May 31, 2024

URL to App Conversion

View Project

Key Strengths

Extensive practical experience with various Vision-Language Models (VLMs) and image generation/editing techniques.
Demonstrated ability to work with advanced AI models like Qwen, SigLIP, and FLUX.
Proficiency in Python and Jupyter Notebooks for AI/ML development and experimentation.
Strong focus on real-world application of computer vision concepts, including image editing, classification, and OCR.
Experience with Hugging Face ecosystem for model deployment and experimentation.

Cultural & Operational Fit

Cultural Fit Analysis

Soft Skills & Operational Fit

Insufficient data to assess soft skills and operational fit. No psychometric test results or interview feedback provided.

PRITHIV SAKTHI U R

Key Strengths

Cultural & Operational Fit

Top Skills

Skills

Projects

Key Strengths

Cultural & Operational Fit