19 73 157

Hyoung-Kyu Song

deepkyu

https://linktr.ee/deepkyu

AI & ML interests

Efficient model for image/video generation

Recent Activity

commented on a paper about 1 month ago

Efficient LLaMA-3.2-Vision by Trimming Cross-attended Visual Features

upvoted a paper about 1 month ago

Efficient LLaMA-3.2-Vision by Trimming Cross-attended Visual Features

upvoted a paper about 2 months ago

SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation

View all activity

Organizations

deepkyu's activity

liked a Space 4 months ago

531

The Tokenizer Playground

📝

Experiment with and compare different tokenizers

liked a model 5 months ago

BadToBest/EchoMimicV2

Updated Jan 6 • 116

liked a Space 5 months ago

902

LTX-Video-Playground

🚀

Generate videos from text or images

liked a model 5 months ago

Lightricks/LTX-Video

Text-to-Video • Updated 16 days ago • 165k • • 1.18k

liked a Space 5 months ago

2.09k

Anycoder

🏢

Select and view code snippets for different providers

liked a dataset 6 months ago

WenhaoWang/TIP-I2V

Viewer • Updated Mar 14 • 1.81M • 497 • 14

liked a Space 6 months ago

8.6k

Kolors Virtual Try-On

👕

Try on virtual garments on person images

liked 4 models 6 months ago

liked a Space 6 months ago

1.87k

Stable Diffusion 3.5 Large

🏃

Generate images with SD3.5

liked a model 6 months ago

genmo/mochi-1-preview

Text-to-Video • Updated Dec 18, 2024 • 27.4k • • 1.22k

liked 2 Spaces 7 months ago

344

TANGO

🐠

Co-Speech Gesture Video Generation

AiOS

⚡

liked a model 7 months ago

yisol/IDM-VTON

Image-to-Image • Updated Apr 22, 2024 • 78.5k • 599

liked 4 Spaces 7 months ago

1.9k

IDM VTON

👕

High-fidelity Virtual Try-on

479

FLUX LoRa Lab

🧪

Generate images using selected LoRAs and prompts

2.27k

F5-TTS

🗣

F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)

650

Pyramid Flow

⚱

Generate videos from text or images