Prithiv Sakthi's picture

Building on HF

Prithiv Sakthi

prithivMLmods

hugging-science

·

https://linktr.ee/prithivsakthi

AI & ML interests

computer vision, nlp, multimodality - HuggingFace Fellow🤗

Recent Activity

upvoted an article about 16 hours ago

SynthVision: Building a 110K Synthetic Medical VQA Dataset with Cross-Model Validation

upvoted an article about 16 hours ago

Falcon Perception

reacted to theirpost with 🚀 about 16 hours ago

The demo for Image Detection (*Filter) based on SAM3 and Qwen-3.5 is now available on Hugging Face Spaces using Transformers inference, with multimodal reasoning for processed images, and it also supports video segmentation (mask), video segmentation (annotation), and image click segmentation. 🤗 Demo Space: https://huggingface.co/spaces/prithivMLmods/SAM3-Plus-Qwen3.5 🥽 SAM3: https://huggingface.co/facebook/sam3 🔗 Qwen-3.5: https://huggingface.co/Qwen/Qwen3.5-2B To learn more, visit the app page or the respective model pages.

View all activity

Organizations

prithivMLmods 's Spaces 56

KV Edit Consistency

Fast Editing with Robust Consistency

SAM3 + Qwen3.5

Multi-object tracking

SAM3 Demo

Unified foundation model for promptable segmentation

Qwen 3.5 HF Demo

Demo of the Qwen 3.5 Multimodal Model

FLUX.2 Klein LoRA Studio

Demo of a Collection of FLUX.2-Klein Model LoRAs

Qwen-Image-Edit-2511-LoRAs-Fast

Demo of the Collection of Qwen Image Edit LoRAs

FireRed Image Edit 1.0 Fast

FireRed-Image-Edit × Qwen-Image-Edit-Rapid (Transformers)

QIE Bbox Studio

Draw a Bbox and Edit Anything!

QIE Object Remover Bbox

Draw a box and remove the designs, objects, and accessories.

Qwen-Image-Edit-3D-Lighting-Control

Control lighting directions using the 3D viewport

Qwen-Image-Edit-2509-LoRAs-Fast

Demo of the Collection of Qwen Image Edit LoRAs

Qwen Image Edit Object Manipulator

Text-Guided Object Manipulation Using Qwen Image Edit + LoRA

Qwen Image Edit 2509 LoRAs Fast Fusion

Qwen Image Editing Fusion Collection LoRA Demo

FLUX LoRA DLC

270+ Impressive LoRAs for Flux.1

FLUX REALISM

flux.1-dev / flux.1-krea-dev

FLUX.1 Kontext Photo Mate v2

Image manipulation with Kontext adapters - v2

Photo Mate i2i

Image manipulation with Kontext adapters.[demo]

FLUX LoRA DLC2

100+ Impressive LoRA's For Flux.1

LTX-2-LoRAs-Camera-Control-Dolly

Camera Control Dolly [Distilled]

Z Image Turbo LoRA DLC

Demo of a Collection of Impressive LoRAs for Z-Image-Turbo

SAGE Video Reasoning

Smart Any-Horizon Agents for Long Video Reasoning. [SAGE]

Super OCRs Demo

Experiment with small super OCR models here.

DeepSeek OCR Experimental

Testing for the latest transformers (DeepSeek-OCR).

NVIDIA Nemotron Parse OCR

understand document semantics, extract text and tables.