Prithiv Sakthi's picture

Building on HF

Prithiv Sakthi PRO

prithivMLmods

hugging-science

·

https://linktr.ee/prithivsakthi

AI & ML interests

computer vision, nlp, multimodality - HuggingFace Fellow🤗

Recent Activity

upvoted an article about 10 hours ago

Introducing Modular Diffusers - Composable Building Blocks for Diffusion Pipelines

liked a model about 11 hours ago

prithivMLmods/Qwen3.5-9B-Unredacted-MAX

published a model about 11 hours ago

prithivMLmods/Qwen3.5-9B-Unredacted-MAX

View all activity

Organizations

prithivMLmods 's Spaces 53

VLM Parsing

for document parsing task

Multimodal OCR2

nanonets ocr / smoldocling / monkey ocr / typhoon ocr

DeepSeek OCR Experimental

Testing for the latest transformers (DeepSeek-OCR).

Multimodal OCR3

demo of a collection of impressive ocr models on the hub

core OCR

camel doc ocr / core ocr / docscope ocr / monkey ocr

Qwen3 VL HF Demo

object detection, visual grounding, keypoint detection

Molmo2 HF Demo

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

Multimodal VLM Thinking

thinking / ocr / reasoning

Multimodal VLM v1.0

OCR, VQA, Thinking and Object Detection.

VisionScope-R2

demo of a collection of multimodal vlms on hf [ocr / others]

DocScope-R1

cosmos reason1 / docscopeocr / visionocr / captioner relaxed

Florence2 Vision Models

Florence-2 vision models demo. (transformers)

Florence-2 Models

Florence-2-large / Florence-2-base

Florence-2-Image-Caption-Daggr

Image Caption : Florence-2 Models

TRELLIS.2-Text-to-3D (Rerun)

Text-to-Image → 3D or Image-to-3D

Qwen-Image-2512-LoRA-DLC

Qwen-Image-2512 + LoRAs

FLUX.1 Kontext Photo Mate v2

Image manipulation with Kontext adapters - v2

FLUX REALISM

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

Vision To VibeVoice En

Image-Text to Voice (en)

SAM3 Demo

SAM 3 is a foundation model for promptable segmentation

POINTS Reader OCR

Vision-Language Models for Document Conversion

Qwen Image LoRA DLC

Qwen Image LoRA's

NVIDIA Nemotron Parse OCR

understand document semantics, extract text and tables.

Nanobanana Sketch Board [PRO]

Sketch / Draw -> Edit