Update README.md

README.md

@@ -56,36 +56,13 @@ I merged these with hll4-p3-ep8, which is the newest vtuber-finetuned model. The
 
 # Loras
 
-All known holo Loras will be linked to and backed up here. Put them in your `stable-diffusion-webui/models/Lora` folder. Use them in your prompt like this: `<lora:filename:0.7>`  
-Most Loras work best with a weight of `0.7`, but some recent ones work well at the default of `1`.
-
-**Locons** and **Lohas** are new types of Lora, they work the exact same but you need [this extension](https://github.com/KohakuBlueleaf/a1111-sd-webui-locon) to use them.
+Most useful holo Loras will be linked to and backed up here. Put them in your `stable-diffusion-webui/models/Lora` folder. Use them in your prompt like this: `<lora:filename:1>`  
+Most Loras work well with a weight of `1.0`, but some older ones work best at `0.7`.
 
 Learn to make your own Loras [with my guide](https://civitai.com/models/22530).
 
 &nbsp;
 
-## Small Loras
-
-These were scaled down from 144 MB to 18 MB or 36 MB and perform almost the same. They need a higher weight than the original to preserve detail. If one performs poorly for you, try the original instead.
-
-This works because dim 128 used to be the default setting for making Loras but that was completely overkill and dim 8/16/32 work just as well.
-
-This was done by me. Find them [here](https://huggingface.co/hollowstrawberry/holotard/tree/main/lora-small).
-
-<details>
-<summary>Click here for a comparison</summary>
-
-![A comparison between a vtuber made with the original Lora and the compressed Lora](lora-small-1.png)
-![A comparison between a vtuber made with the original Lora and the compressed Lora](lora-small-2.png)
-![A comparison between a vtuber made with the original Lora and the compressed Lora](lora-small-3.png)
-![A comparison between a vtuber made with the original Lora and the compressed Lora](lora-small-4.png)
-![A comparison between a vtuber made with the original Lora and the compressed Lora](lora-small-5.png)
-![A comparison between a vtuber made with the original Lora and the compressed Lora](lora-small-6.png)
-</details>
-
-&nbsp;
-
 ## Multi Outfit Loras
 
 These are the most modern and have several outfits of each talent in a single Lora, or the main outfit if no other options are available. Check the model page / text files for examples.
@@ -162,7 +139,28 @@ These are the most modern and have several outfits of each talent in a single Lo
 * [Harusaki Nodoka](https://civitai.com/models/33130)
 * [Mano Aloe](https://civitai.com/models/35099)
 
-## (Legacy) Outfits
+&nbsp;
+
+## Small Loras
+
+Some older Loras were manually scaled down from 144 MB to 18 MB or 36 MB and perform almost the same. They need a higher weight than the original to preserve detail.
+
+This works because dim 128 used to be the default setting for making Loras but that was completely overkill and dim 8/16/32 work just as well.
+
+<details>
+<summary>Click here for a comparison</summary>
+
+![A comparison between a vtuber made with the original Lora and the compressed Lora](lora-small-1.png)
+![A comparison between a vtuber made with the original Lora and the compressed Lora](lora-small-2.png)
+![A comparison between a vtuber made with the original Lora and the compressed Lora](lora-small-3.png)
+![A comparison between a vtuber made with the original Lora and the compressed Lora](lora-small-4.png)
+![A comparison between a vtuber made with the original Lora and the compressed Lora](lora-small-5.png)
+![A comparison between a vtuber made with the original Lora and the compressed Lora](lora-small-6.png)
+</details>
+
+&nbsp;
+
+## Legacy Loras
 
 <details>
 <summary>Click here for old outfit loras</summary>