Stefan Smiljkovic's picture

Stefan Smiljkovic PRO

shtefcs

·

https://automatio.ai

AI & ML interests

Hi, I'm Stefan 👋, creator of Automatio. My work focuses on web automation, extracting data from websites, AI, building workflows, and agents that simplify online tasks. Feel free to check out the Automatio website or connect with me on social media!

Recent Activity

liked a Space 2 days ago

ByteDance-Seed/Seed1.5-VL

liked a model 3 days ago

google/medgemma-4b-it

liked a Space 3 days ago

tencent/SongGeneration

View all activity

Organizations

liked a Space 2 days ago

Seed1.5 VL

Seed1.5-VL API Demo

liked a model 3 days ago

google/medgemma-4b-it

Image-Text-to-Text • 5B • Updated 13 days ago • 106k • • 522

liked a Space 3 days ago

Song Generation

Generate a custom song from lyrics

liked a model 3 days ago

tencent/SongGeneration

Text-to-Audio • Updated 4 days ago • 1.97k • 191

liked a Space 3 days ago

OCR

nanonets ocr / qwen2vl ocr / rolmocr / aya vision / lh41

liked a model 3 days ago

nanonets/Nanonets-OCR-s

Image-Text-to-Text • 4B • Updated Jun 20 • 180k • 1.42k

liked 2 Spaces 3 days ago

GLM-4.1V-9B-Thinking-API-Demo

THUDM/GLM-4.1V-9B-Thinking Demo

GLM-4.1V-9B-Thinking-Demo

THUDM/GLM-4.1V-9B-Thinking Demo

liked a model 3 days ago

THUDM/GLM-4.1V-9B-Thinking

Image-Text-to-Text • 10B • Updated 14 days ago • 53.8k • • 650

liked a model 4 days ago

Qwen/Qwen2.5-VL-32B-Instruct

Image-Text-to-Text • 33B • Updated Apr 14 • 465k • • 408

liked a Space about 2 months ago

DALLE 3 XL v2

Generate images from text prompts

liked 3 models about 2 months ago

jinaai/jina-reranker-m0

Text Classification • 2B • Updated Apr 15 • 8.95k • 91

jinaai/jina-clip-v2

Feature Extraction • 0.9B • Updated Apr 28 • 29.3k • • 264

jinaai/jina-clip-v1

Feature Extraction • 0.2B • Updated May 20 • 65.6k • 251

liked 6 Spaces 3 months ago

Moseca

HoloPart

Decompose a 3D model into separate parts

TripoSG

Transform an image into a textured 3D model

Advance Blur

Advance Blur anonymizes your images with "Vance Blurring."

Hunyuan3D 2mv Turbo

MultiImages-to-3D Generation

FLUX.1 Dev

Generate imaginative images from text prompts