Thinh Le PRO

thinhlpg's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 3 articles about 5 hours ago

view article

Article

CUGA on Hugging Face: Democratizing Configurable AI Agents

• 

Dec 15, 2025

•

66

view article

Article

New in llama.cpp: Model Management

• 

Dec 11, 2025

•

110

view article

Article

Introducing OptiMind, a research model designed for optimization

• 

4 days ago

•

20

liked a model about 18 hours ago

black-forest-labs/FLUX.2-klein-9b-fp8

Image-to-Image • Updated 3 days ago • 9.91k • 38

liked a Space about 24 hours ago

Running

Featured

221

PaddleOCR-VL Online Demo

📈

221

Parse and recognize text in images

liked a model 1 day ago

ekwek/Soprano-80M

Text-to-Speech • 79.7M • Updated 5 days ago • 9.22k • 305

liked a Space 1 day ago

Running on Zero

MCP

Featured

118

Soprano TTS

🗣

118

Now with upgraded v1.1 model!

liked 2 Spaces 2 days ago

Running on Zero

Featured

265

Qwen Image 2512

👀

265

Generate photorealistic images from text descriptions

Running on Zero

36

GLM Image

💻

36

liked 3 models 2 days ago

google/translategemma-12b-it

Image-Text-to-Text • 13B • Updated 4 days ago • 12.7k • 144

THU-KEG/LongWriter-Zero-32B

Text Generation • 33B • Updated Jul 3, 2025 • 13 • • 111

Wan-AI/Wan2.1-I2V-14B-720P

Image-to-Video • Updated Feb 26, 2025 • 12k • • 558

liked 2 models 3 days ago

black-forest-labs/FLUX.2-klein-4b-fp8

Image-to-Image • Updated 4 days ago • 18.2k • 12

google/translategemma-4b-it

Image-Text-to-Text • 5B • Updated 4 days ago • 17.6k • 322

liked a dataset 3 days ago

PosterCraft/Poster100K

Viewer • Updated Sep 17, 2025 • 48.4k • 686 • 3

liked a model 3 days ago

tulvgengenr/MixGRPO

Updated Aug 5, 2025 • 8 • 8

liked a Space 3 days ago

Running on L40S

519

MinerU OCR

📚

519

A data extraction tool to convert PDF to Markdown and JSON

liked a dataset 3 days ago

BLIP3o/BLIP3o-60k

Viewer • Updated May 25, 2025 • 7.1k • 1.37k • 34

upvoted a paper 3 days ago

BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset

Paper • 2505.09568 • Published May 14, 2025 • 99

liked a dataset 3 days ago

pickapic-anonymous/pickapic_v1

Viewer • Updated May 4, 2023 • 616k • 2.55k • 8