diff --git a/.gitignore b/.gitignore index 5931190..90b9508 100644 --- a/.gitignore +++ b/.gitignore @@ -4,4 +4,5 @@ model/SCHP/__pycache__ resource/demo/output resource/demo/example/.DS_Store model/SCHP/*/__pycache__ -densepose_ \ No newline at end of file +densepose_ +.vscode \ No newline at end of file diff --git a/resource/index.html b/index.html similarity index 94% rename from resource/index.html rename to index.html index 4db1f11..e3e0b56 100644 --- a/resource/index.html +++ b/index.html @@ -21,20 +21,20 @@ - - - - + + + + - - + + - - - - + + + + @@ -139,7 +139,7 @@

🐈 CatVTON: Concatenation Is All You
- teaser + teaser

CatVTON is a simple and efficient virtual try-on diffusion model with 1) Lightweight Network (899.06M parameters totally), 2) Parameter-Efficient Training (49.57M parameters trainable) and 3) Simplified Inference (< 8G VRAM for 1024X768 @@ -195,7 +195,7 @@

Abstract

Architecture

- +

Our method achieves the high-quality try-on by simply concatenating the conditional image (garment or reference person) with the target person image in the spatial dimension, ensuring they remain in the same feature space throughout the @@ -218,7 +218,7 @@

Structure Comparison

requires the heavy ReferenceNet for additional garment encoding; it only needs simple concatenation of the garment and person images as input to obtain high-quality try-on results.

- +
@@ -233,7 +233,7 @@

Efficiency Comparison

area proportional to the parameter number. CatVTON achieves lower FID on the VITONHD dataset with fewer total parameters, trainable parameters, and memory usage.

- +