3 6 21

AHN DONGHOON

sunovivid

https://scholar.google.com/citations?user=b_m86AoAAAAJ&hl=ko&oi=sra

AI & ML interests

image & video generation, author of PAG

Recent Activity

liked a model 3 days ago

XLabs-AI/flux-lora-collection

upvoted a paper 4 days ago

URECA: Unique Region Caption Anything

liked a model 29 days ago

RE-N-Y/aesthetic-shadow-v2

View all activity

Organizations

sunovivid's activity

liked a model 3 days ago

XLabs-AI/flux-lora-collection

Text-to-Image • Updated Aug 14, 2024 • 538

upvoted a paper 4 days ago

URECA: Unique Region Caption Anything

Paper • 2504.05305 • Published 5 days ago • 33

liked a model 29 days ago

RE-N-Y/aesthetic-shadow-v2

Image Classification • Updated Jan 15 • 72 • 1

liked a dataset about 1 month ago

laion/laion2B-en-aesthetic

Viewer • Updated Jul 13, 2024 • 51.9M • 2.28k • 42

liked a dataset 3 months ago

JourneyDB/JourneyDB

Updated Aug 10, 2023 • 4.32k • 73

commented a paper 4 months ago

A Noise is Worth Diffusion Guidance

Paper • 2412.03895 • Published Dec 5, 2024 • 31 •

upvoted a paper 4 months ago

A Noise is Worth Diffusion Guidance

Paper • 2412.03895 • Published Dec 5, 2024 • 31

commented a paper 4 months ago

A Noise is Worth Diffusion Guidance

Paper • 2412.03895 • Published Dec 5, 2024 • 31 •

authored a paper 4 months ago

Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance

Paper • 2403.17377 • Published Mar 26, 2024 • 2

updated a dataset 5 months ago

sunovivid/pag-uncond

Updated Nov 9, 2024 • 8

liked a model 5 months ago

stabilityai/stable-diffusion-3.5-medium

Text-to-Image • Updated Oct 31, 2024 • 327k • • 669

liked a model 6 months ago

stable-diffusion-v1-5/stable-diffusion-v1-5

Text-to-Image • Updated Sep 7, 2024 • 6.93M • • 493

New activity in rsortino/ColorizeNet 6 months ago

Error while model loading

#2 opened 6 months ago by

sunovivid

upvoted a collection 8 months ago

Diffusion-based Inverse Problem Solvers

Collection

Papers on solving Imaging as Inverse problems using diffusion priors. • 9 items • Updated Aug 8, 2024 • 1

liked a model 8 months ago

timm/ViT-SO400M-14-SigLIP-384

Zero-Shot Image Classification • Updated Oct 27, 2023 • 338k • 79

upvoted a paper 8 months ago

ProCreate, Dont Reproduce! Propulsive Energy Diffusion for Creative Generation

Paper • 2408.02226 • Published Aug 5, 2024 • 12

liked a model 9 months ago

stabilityai/stable-video-diffusion-img2vid-xt-1-1

Image-to-Video • Updated Jul 10, 2024 • 89.8k • 891

liked a dataset 10 months ago

argilla/distilabel-intel-orca-dpo-pairs

Viewer • Updated 24 days ago • 12.9k • 3.51k • 172

New activity in hyoungwoncho/sd_perturbed_attention_guidance 10 months ago

PAG's compatibility with IP-Adapter

#1 opened 12 months ago by

HiPenguin

liked a model 11 months ago

hyoungwoncho/sd_perturbed_attention_guidance_controlnet

Image-to-Image • Updated Apr 22, 2024 • 3