diff --git a/README.md b/README.md
index 16107f8..7ef4ffa 100644
--- a/README.md
+++ b/README.md
@@ -108,13 +108,16 @@ Available command line arguments:
| FcF | :+1: Better structure and texture generation
:neutral_face: Only support fixed size (512x512) input | |
| SD1.4 | :+1: SOTA text-to-image diffusion model | |
-### LaMa vs LDM
+
+ See model comparison detail
+
+**LaMa vs LDM**
| Original Image | LaMa | LDM |
| ----------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------- |
|  |  |  |
-### LaMa vs ZITS
+**LaMa vs ZITS**
| Original Image | ZITS | LaMa |
| ---------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------- |
@@ -122,21 +125,23 @@ Available command line arguments:
Image is from [ZITS](https://github.com/DQiaole/ZITS_inpainting) paper. I didn't find a good example to show the advantages of ZITS and let me know if you have a good example. There can also be possible problems with my code, if you find them, please let me know too!
-### LaMa vs FcF
+**LaMa vs FcF**
| Original Image | Lama | FcF |
| ----------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------- |
|  |  |  |
+
+
## Inpainting Strategy
Lama Cleaner provides three ways to run inpainting model on images, you can change it in the settings dialog.
-| Strategy | Description | VRAM |
-| ------------ | ---------------------------------------------------------------------------------------------------------------------------------------------- | -------------------- |
-| **Original** | Use the resolution of the original image | :tada: |
-| **Resize** | Resize the image to a smaller size before inpainting. Lama Cleaner will make sure that the area of the image outside the mask is not degraded. | :tada: :tada: |
-| **Crop** | Crop masking area from the original image to do inpainting | :tada: :tada: :tada: |
+| Strategy | Description | VRAM | Speed |
+| ------------ | ------------------------------------------------------------------------------------------------------ | ------ | ----------------- |
+| **Original** | Use the resolution of the original image | High | :zap: |
+| **Resize** | Resize the image to a smaller size before inpainting. The area outside the mask will not loss quality. | Midium | :zap: :zap: |
+| **Crop** | Crop masking area from the original image to do inpainting | Low | :zap: :zap: :zap: |
## Download Model Mannually