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.
📌 All scripts for training, inference, and evaluation are included.
Check it out on GitHub: https://github.com/rizavelioglu/tryoffdiff/
Riza Velioglu
rizavelioglu
AI & ML interests
Multimodal Models, Diffusion Models, Object Detection & Segmentation
Recent Activity
upvoted an article 4 days ago
Profiling in PyTorch (Part 1): A Beginner's Guide to torch.profiler updated a Space 15 days ago
rizavelioglu/tryoffdiff new activity 3 months ago
fal/virtual-tryoff-lora:Comfy Converted Version?Organizations
replied to their post 11 months ago
replied to their post 11 months ago
🥳 The code has now been published!
Find the training, inference, and evaluation scripts in the repo: https://github.com/rizavelioglu/tryoffdiff/
posted an update 12 months ago
Post
1026
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
- 1 reply
posted an update over 1 year ago
Post
3791
Comparing reconstruction quality of various VAEs with an interactive demo
rizavelioglu/vae-comparison
rizavelioglu/vae-comparison
- 1 reply
replied to their post over 1 year ago
The code for TryOffDiff is now officially released! 🤗
You can find all scripts for training, prediction, and evaluation included.
Check it out at: https://github.com/rizavelioglu/tryoffdiff/
reacted to their post with 👍 over 1 year ago
Post
2312
Introducing Virtual Try-Off (VTOFF), a novel task focused on generating standardized garment images from single photos of clothed individuals. Unlike traditional Virtual Try-On (VTON), which digitally dresses models, VTOFF aims to extract a canonical garment image, posing unique challenges in capturing garment shape, texture, and intricate patterns.
Try it out: rizavelioglu/tryoffdiff
Paper: TryOffDiff: Virtual-Try-Off via High-Fidelity Garment Reconstruction using Diffusion Models (2411.18350)
Project page: https://rizavelioglu.github.io/tryoffdiff
Try it out: rizavelioglu/tryoffdiff
Paper: TryOffDiff: Virtual-Try-Off via High-Fidelity Garment Reconstruction using Diffusion Models (2411.18350)
Project page: https://rizavelioglu.github.io/tryoffdiff
- 3 replies
posted an update over 1 year ago
Post
2312
Introducing Virtual Try-Off (VTOFF), a novel task focused on generating standardized garment images from single photos of clothed individuals. Unlike traditional Virtual Try-On (VTON), which digitally dresses models, VTOFF aims to extract a canonical garment image, posing unique challenges in capturing garment shape, texture, and intricate patterns.
Try it out: rizavelioglu/tryoffdiff
Paper: TryOffDiff: Virtual-Try-Off via High-Fidelity Garment Reconstruction using Diffusion Models (2411.18350)
Project page: https://rizavelioglu.github.io/tryoffdiff
Try it out: rizavelioglu/tryoffdiff
Paper: TryOffDiff: Virtual-Try-Off via High-Fidelity Garment Reconstruction using Diffusion Models (2411.18350)
Project page: https://rizavelioglu.github.io/tryoffdiff
- 3 replies