Riza Velioglu
AI & ML interests
Multimodal Models, Diffusion Models, Object Detection & Segmentation
Recent Activity
liked
a model 2 months ago
Tongyi-MAI/Z-Image-Turbo updated
a Space 3 months ago
rizavelioglu/fr-iqa updated
a Space 3 months ago
rizavelioglu/vae-comparison Organizations
upvoted an article 3 months ago
Article
Continuous batching from first principles
- +1
โข
333
upvoted a paper 7 months ago
replied to their post 8 months ago
A follow-up work named Multi-Garment TryOffDiff (MGT) is now available, which extends capabilities of TryOffDiff to support multi-garment reconstruction, including upper-body, lower-body, and full-body (dress) garments, enabling more comprehensive scenarios.
๐ All scripts for training, inference, and evaluation are included.
Check it out on GitHub: https://github.com/rizavelioglu/tryoffdiff/
replied to their post 8 months ago
๐ฅณ The code has now been published!
Find the training, inference, and evaluation scripts in the repo: https://github.com/rizavelioglu/tryoffdiff/
posted an
update 9 months ago
Post
939
TryOffDiff goes multi-garment!
We're excited to share TryOffDiff v2, extending our approach to support multiple garment categories. Key updates include:
- Training on the multi-garment DressCode dataset, covering upper-body, lower-body, and dresses.
- A simplified adapter design for improved training efficiency and modularity.
- Introduction of four specialized models:
- One model per category (upper, lower, dress),
- Plus a multi-garment model capable of generating multiple garments sequentially from a single image.
*PS:* Visit us this Friday at 10:30 AM in ExHall-B for our live demo @CVPR '25!
Demo: rizavelioglu/tryoffdiff
Project page: https://rizavelioglu.github.io/tryoffdiff
We're excited to share TryOffDiff v2, extending our approach to support multiple garment categories. Key updates include:
- Training on the multi-garment DressCode dataset, covering upper-body, lower-body, and dresses.
- A simplified adapter design for improved training efficiency and modularity.
- Introduction of four specialized models:
- One model per category (upper, lower, dress),
- Plus a multi-garment model capable of generating multiple garments sequentially from a single image.
*PS:* Visit us this Friday at 10:30 AM in ExHall-B for our live demo @CVPR '25!
Demo: rizavelioglu/tryoffdiff
Project page: https://rizavelioglu.github.io/tryoffdiff
upvoted a paper 12 months ago
Fixes 500 error for some users
๐ 1
#2 opened 12 months ago
by
Tonic
great space
๐ ๐ค 2
1
#1 opened 12 months ago
by
altayavci
posted an
update 12 months ago
Post
3707
Comparing reconstruction quality of various VAEs with an interactive demo
rizavelioglu/vae-comparison
rizavelioglu/vae-comparison