Junyoung Seo

jyseo's activity

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

upvoted a paper 12 days ago

Fine-Grained Perturbation Guidance via Attention Head Selection

Paper • 2506.10978 • Published 14 days ago • 26

liked a Space 5 months ago

Running on Zero

1.98k

1.98k

Chat With Janus-Pro-7B

🌍

A unified multimodal understanding and generation model.

liked a dataset 5 months ago

nkp37/OpenVid-1M

Viewer • Updated 7 days ago • 1.45M • 25.8k • 203

liked a Space 8 months ago

Running on Zero

58

58

MoGe

🏆

MoGe live demo

liked a model 8 months ago

genmo/mochi-1-preview

Text-to-Video • Updated Dec 18, 2024 • 17k • • 1.23k

liked a Space 9 months ago

Running

37

37

KoolCogVideoX

🎥

Text-to-Video

liked a Space 10 months ago

Running on Zero

68

68

GenWarp

🌃

Generate novel views from a single image

liked a model 10 months ago

Sony/genwarp

Image-to-Image • Updated Feb 27 • 12

liked a Space 11 months ago

Running on Zero

7

7

LocoTrack

🐈

Track objects in your video by marking points

authored 3 papers 12 months ago

Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation

Paper • 2303.07937 • Published Mar 14, 2023

Retrieval-Augmented Score Distillation for Text-to-3D Generation

Paper • 2402.02972 • Published Feb 5, 2024

GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warping

Paper • 2405.17251 • Published May 27, 2024 • 2

liked a Space about 1 year ago

Running on Zero

61

61

ChronoDepth

🔥

Generate depth video from input video

liked 2 Spaces over 1 year ago

Runtime error

162

162

Moore AnimateAnyone

🏃

Running on Zero

532

532

Depth Anything

🌖

Generate depth map from image

liked a Space almost 2 years ago

Runtime error

81

81

SyncDreamer

🚀

liked a model almost 2 years ago

stabilityai/control-lora

Text-to-Image • Updated Aug 19, 2023 • 944

liked 3 Spaces almost 2 years ago

Sleeping

40

40

MasaCtrl

😻

Running on L40S

2.34k

2.34k

Whisper

📉

Transcribe audio from microphone, files, or YouTube

Running on L4

407

407

One-2-3-45

📸

Create 3D mesh from a single image