Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -3,7 +3,6 @@ license: cc-by-nc-sa-4.0
|
|
| 3 |
tags:
|
| 4 |
- virtual-try-on
|
| 5 |
- diffusion
|
| 6 |
-
- controlnet
|
| 7 |
- image-to-image
|
| 8 |
- computer-vision
|
| 9 |
datasets:
|
|
@@ -18,7 +17,9 @@ arxiv: 2605.01296
|
|
| 18 |
|
| 19 |
SIFT-VTON is a diffusion-based virtual try-on model that uses SIFT feature correspondences between a garment image and a person image to supervise cross-attention maps during training, improving geometric alignment in the generated results.
|
| 20 |
|
| 21 |
-
|
|
|
|
|
|
|
| 22 |
|
| 23 |
The code repository is available at [takesukeDS/SIFT-VTON](https://github.com/takesukeDS/SIFT-VTON).
|
| 24 |
|
|
|
|
| 3 |
tags:
|
| 4 |
- virtual-try-on
|
| 5 |
- diffusion
|
|
|
|
| 6 |
- image-to-image
|
| 7 |
- computer-vision
|
| 8 |
datasets:
|
|
|
|
| 17 |
|
| 18 |
SIFT-VTON is a diffusion-based virtual try-on model that uses SIFT feature correspondences between a garment image and a person image to supervise cross-attention maps during training, improving geometric alignment in the generated results.
|
| 19 |
|
| 20 |
+
Paper: [arXiv:2605.01296](https://arxiv.org/abs/2605.01296)
|
| 21 |
+
|
| 22 |
+
This model is derived from [StableVITON](https://github.com/rlawjdghek/stableviton) and built on a Stable Diffusion backbone.
|
| 23 |
|
| 24 |
The code repository is available at [takesukeDS/SIFT-VTON](https://github.com/takesukeDS/SIFT-VTON).
|
| 25 |
|