Max Ku
vinesmsuic
AI & ML interests
Computer Vision, World Models
Recent Activity
upvoted a paper about 22 hours ago
TT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining upvoted a paper about 23 hours ago
PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation new activity 2 months ago
TIGER-Lab/VisPhyWorld-Sub-Generated-Videos:Add paper link and task categoriesOrganizations
Add paper link and task categories
#2 opened 4 months ago
by 
nielsr
Thank you.
🔥 1
#2 opened 12 months ago
by 
Kjay
Link to paper
#2 opened over 1 year ago
by nielsr
Add AuraFlow
👍 2
2
#15 opened about 2 years ago
by 
MohamedRashad
Unable to edit images for Edition (battle)
1
#14 opened over 2 years ago
by 
aggr8
Add paper link to connect the Space to the paper on Daily Papers page.
#13 opened over 2 years ago
by 
AdinaY
PixArt Sigma?
2
#11 opened over 2 years ago
by 
sayakpaul
Adding `safetensors` variant of this model
#6 opened over 2 years ago
by 
squidWorm
Make the header mini to focus on the arena
#1 opened over 2 years ago
by 
multimodalart
Fix deprecation warning by changing `CLIPFeatureExtractor` to `CLIPImageProcessor`.
#3 opened over 3 years ago
by 
patrickvonplaten
Fix deprecation warning by changing `CLIPFeatureExtractor` to `CLIPImageProcessor`.
#5 opened over 3 years ago
by patrickvonplaten
Add `scale_factor` to vae config.
#2 opened over 3 years ago
by 
valhalla
Add `scale_factor` to vae config.
#4 opened over 3 years ago
by valhalla
How to install this
2
#3 opened almost 4 years ago
by 
HadrianMaximus
Add `clip_sample=False` to scheduler to make model compatible with DDIM.
1
#1 opened almost 4 years ago
by patrickvonplaten
Add `clip_sample=False` to scheduler to make model compatible with DDIM.
1
#2 opened almost 4 years ago
by patrickvonplaten
Correct `sample_size` of Stable Diffusion 1's unet to have correct width and height default
1
#1 opened almost 4 years ago
by patrickvonplaten