Tolga Cangöz

tolgacangoz's activity

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

liked a model 6 days ago

OzzyGT/minimax_h3_preview_blocks

Text-to-Video • Updated 6 days ago • 14 • 1

upvoted a paper 6 days ago

Sol-H3: Recursive Self-Improvement for MiniMax-H3 Inference Acceleration on Sol-Engine across Cloud and Edge

Paper • 2609.35110 • Published 9 days ago • 1

upvoted an article 6 days ago

view article

Article

Using Krea with reference images

• 

OzzyGT

•

7 days ago

• 1

liked a Space 7 days ago

Running on Zero

Agents

Featured

55

Qwen-Image 2.1 Move

🎁

55

Move & resize objects with Qwen-Image 2.1 turbo, no LoRA

liked a Space 8 days ago

Running

16

World Models: The Simulation Strikes Back

🌍

16

The Simulation Strikes Back -- what even is a world model?

upvoted an article 13 days ago

view article

Article

FLUX 3 Action: a world action model you can fine-tune

• 

black-forest-labs

•

13 days ago

• 15

liked a model 16 days ago

Qwen/Qwen-Image-2.1

Text-to-Image • 7B • Updated 6 days ago • 103k • 3.02k

liked a model 17 days ago

nvidia/Cosmos3-Nano

16B • Updated 20 days ago • 97.5k • 383

liked a model 18 days ago

tolgacangoz/matryoshka-diffusion-models

Text-to-Image • Updated Oct 20, 2024 • 89 • 4

upvoted a collection 19 days ago

Cosmos3

Collection

Omnimodal World Models for Physical AI • 6 items • Updated Aug 28 • 207

liked a Space 21 days ago

Running

Featured

92

Flow Matching for Image Generation

🌊

92

Visualize how noise transforms into images in your browser

liked a Space 26 days ago

Running

Featured

92

A Hitchhiker's Guide to the 3D Ecosystem

💡

92

An interactive guide to 3D representations.

liked a model 26 days ago

deepseek-ai/DeepSeek-V4.1-Flash

Image-Text-to-Text • 763B • Updated 5 days ago • 1.16M • • 4.16k

upvoted an article 30 days ago

view article

Article

Harness, Scaffold, and the AI Agent Terms Worth Getting Right

• 
• 

sergiopaniego, ariG23498

•

May 25

• 150

upvoted a paper about 1 month ago

MONET: A Massive, Open, Non-redundant and Enriched Text-to-image dataset

Paper • 2605.21272 • Published May 20 • 5

upvoted a collection about 1 month ago

MONET - Massive Open Non-redundant, Enriched, Text-to-image

Collection

A curated, deduped & recaptioned open image–text dataset of 104.9M samples released under the Apache2.0 licence. https://huggingface.co/blog/jasperai/ • 4 items • Updated May 28 • 12

liked a Space about 1 month ago

Running

23

T2I — Interactive Technical Report

🌸

23

A journey to build a T2I model from scratch

upvoted a paper about 1 month ago

LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

Paper • 2603.19312 • Published Mar 13 • 55

upvoted a collection about 1 month ago

LeWM

Collection

Official checkpoints and datasets related to LeWM paper. • 9 items • Updated Mar 27 • 60

upvoted a paper about 1 month ago

VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models

Paper • 2502.02492 • Published Feb 4, 2025 • 67