Rafael Magalhães PRO

rafaelmm's activity

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

liked a model 4 days ago

netflix/void-model

Video-to-Video • Updated 8 days ago • 799

liked a Space 4 days ago

Running on Zero

Featured

2.23k

Qwen Image Multiple Angles 3D Camera

🎥

2.23k

Edit image camera angle with interactive 3D controls

liked a model 4 days ago

k2-fsa/OmniVoice

Text-to-Speech • Updated 1 day ago • 531k • 552

liked a Space 2 months ago

Running on T4

26

Qwen3-TTS-Daggr-UI

🔥

26

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

upvoted an article 2 months ago

view article

Article

Open Responses: What you need to know

• 
• 
• +2

Jan 15

•

111

upvoted an article 3 months ago

view article

Article

LightOnOCR-2-1B: a lightweight high-performance end-to-end OCR model family

• 

Jan 19

•

91

liked a model 4 months ago

fastino/gliner2-large-v1

Updated Feb 26 • 165k • 64

upvoted a collection 4 months ago

gliner2 family

Collection

GLiNER2 extends the original GLiNER architecture to support multi-task information extraction with a schema-driven interface. This base model provid • 4 items • Updated Feb 10 • 42

liked a Space 5 months ago

Running on CPU Upgrade

Featured

3.1k

The Smol Training Playbook

📚

3.1k

The secrets to building world-class LLMs

updated a collection 8 months ago

Image to text experiments

Collection

2 items • Updated Aug 7, 2025

upvoted an article 11 months ago

view article

Article

nanoVLM: The simplest repository to train your VLM in pure PyTorch

• 
• 
• +5

May 21, 2025

•

254

liked 5 Spaces about 1 year ago

Running on Zero

Featured

203

4M Demo

⚡

203

4M: Massively Multimodal Masked Modeling

Running

30

MultiMAE

😻

30

Reconstruct images using masked autoencoders

Running on CPU Upgrade

244

Open Portuguese LLM Leaderboard

🏆

244

Track, rank and evaluate open LLMs in Portuguese

Runtime error

32

UniK3D Demo

🏢

32

UniK3D (CVPR 2025)

Running on Zero

Featured

865

TripoSG

🔮

865

Generate textured 3D model from a single image

updated a Space about 1 year ago

Sleeping

First Agent Template

⚡

Get time, sum numbers, and more with this versatile assistant

liked a model about 1 year ago

stepfun-ai/GOT-OCR2_0

Image-Text-to-Text • Updated Feb 4, 2025 • 57.1k • 1.53k

upvoted a paper about 1 year ago

YOLOE: Real-Time Seeing Anything

Paper • 2503.07465 • Published Mar 10, 2025 • 16

liked a Space about 1 year ago

Runtime error

1

BFM Segmentation

🏃

1

Segment building materials and generate color palettes