🌀 Building on HF

Prithiv Sakthi PRO

prithivMLmods

hugging-science

·

https://prithivsakthiur.github.io/

AI & ML interests

computer vision, nlp, multimodality - HuggingFace Fellow ML 🤗

Recent Activity

new activity 26 minutes ago

prithivMLmods/Qwen-Image-2512-LoRA-DLC:Can't load QwenImage2512 LoRAs

updated a collection about 1 hour ago

updated a collection about 1 hour ago

View all activity

Organizations

prithivMLmods 's Spaces 75

VisionScope-R2

DeepCaption / SkyCaptioner / SpaceThinker / Core / SpaceOm

SAM3 Demo

Unified foundation model for promptable segmentation

PiD Image Upscaler

Pixel-Diffusion Decoder

Multimodal OCR3

Chandra-OCR / Nanonets-OCR2 / olmOCR-2 / Dots.OCR

Z Image Turbo LoRA DLC

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

HY World 2.0 Demo

A Multi-Modal World Model for Reconstruction

LTX-2-LoRAs-Camera-Control-Dolly

Camera Control Dolly [Distilled]

Multimodal VLM Thinking

Lumian-VLR / VisionThink / MiniCPM-V / Typhoon-OCR / olmOCR

Qwen Image LoRA DLC

Qwen Image LoRA's

Super OCRs Demo

Experiment with small super OCR models here.

Qwen 3.5 HF Demo

Demo of the Qwen 3.5 Multimodal Model

QIE Object Remover Bbox

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

Qwen-Image-2512-LoRA-DLC

Qwen-Image-2512 + LoRAs

Qwen3 VL HF Demo

Object Detection, Visual Grounding, Keypoint Detection

Multimodal VLM v1.0

OCR, VQA, Thinking and Object Detection.

Qwen3.8 27B Object Detection

Unleash the Power of Visual Grounding

Flux.2-Klein-KV-Edit-Consistency-Ultra-Fast

Fast Editing with Robust Consistency

Molmo2 HF Demo

Molmo2 - Image, Video (QA, Pointing & Tracking)

DeepSeek-OCR-2-Unlimited

DeepSeek-OCR 2: Visual Causal Flow

SAM3-Gemma4-CUDA

Object Multiplex

SAM3 + Qwen3.5

Multi-object tracking

Qwen3-VL-abliterated-MAX-Fast

Unredacted: Ask Anything with Near-Zero Refusal Rates

FLUX.1 Kontext Photo Mate v2

Image manipulation with Kontext adapters - v2

POINTS Reader OCR

Vision-Language Models for Document Conversion