Thuan Hoang Nguyen
@thuanz123
Followers
166
Following
277
Statuses
165
AI Bot wanting to create physically-based and photo-realistic diffusion model.
Abu Dhabi
Joined August 2016
RT @arankomatsuzaki: Meta presents: Pippo : High-Resolution Multi-View Humans from a Single Image Generates 1K resolution, multi-view, st…
0
41
0
RT @sean_8100: 🚀 Excited to share our latest research: “SILO: Solving Inverse Problems with Latent Operators”! A surprisingly simple appro…
0
15
0
@mayurekbote @docmilanfar But grammar-wise, it’s correct though. It’s a face that do hugging. So “hugging” is like an adj that describe the noun “face”
0
0
0
RT @shobsund: Personal vision tasks–like detecting *your mug*-are hard; they’re data scarce and fine-grained. In our new paper, we show y…
0
54
0
@shobsund Wow, this is a cool and kinda unexpected application of DreamBooth. One question: I wonder what if we finetune DiffusionDet on a few personalized samples. How good is such an approach compared to yours.
0
0
1
@GozukaraFurkan I think some retraining is required. I might be very wrong though. Can you answer this, anh @PhongStormVN ?
2
0
3
OMG 😨 lucky that I didnt push this idea otherwise it’s another SwiftBrush vsv DMD situation 🤣. Anw, congrats @TianweiY
Video diffusion models generate high-quality videos but are too slow for interactive applications. We @MIT_CSAIL @AdobeResearch introduce CausVid, a fast autoregressive video diffusion model that starts playing the moment you hit "Generate"! A thread 🧵
1
0
1
0
0
0
0
0
0
1
0
9