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 ML 🤗

Recent Activity

updated a Space about 5 hours ago

prithivMLmods/Qwen-Image-Edit-2511-LoRAs-Fast

updated a Space about 6 hours ago

prithivMLmods/FireRed-Image-Edit-1.0-Fast

updated a Space about 8 hours ago

prithivMLmods/Qwen-Image-Edit-2509-LoRAs-Fast

View all activity

Organizations

prithivMLmods 's Spaces 63

Qwen3 VL Video Grounding

Text-guided object tracking, point tracking, reasoning.

Qwen3-TTS-Daggr-UI

custom voice, voice design, and voice cloning, asr nodes.

VLM Parsing

for document parsing task

Qwen3-VL-abliterated-MAX-Fast

Unredacted: Ask Anything with Near-Zero Refusal Rates

Molmo2 HF Demo

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

SAGE Video Reasoning

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

Multimodal VLM Thinking

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

POINTS Reader OCR

Vision-Language Models for Document Conversion

Super OCRs Demo

Experiment with small super OCR models here.

Nanobanana Sketch Board [PRO]

Sketch / Draw -> Edit

Nano Banana AIO

All in One Banana for you!

Metaclip 2

high performance image classification model

Gemini Image Studio

generate new images from text or edit existing ones

Banana Zoom

lossless zoom app powered by nano banana

IMAGEN4 AIO

An All-in-One image generation studio powered by Imagen 4