Update README.md

README.md

@@ -21,6 +21,18 @@ metrics:
 
 <img src="https://huggingface.co/hollowstrawberry/hololive/resolve/main/out.jpg" width="800"/>
 
+# Preamble
+
+These resources are intended to be used with [stable-diffusion-webui](https://github.com/AUTOMATIC1111/stable-diffusion-webui/).
+
+Recommended additional resources:
+
+* [orangemix.vae.pt](https://huggingface.co/WarriorMama777/OrangeMixs/blob/main/VAEs/orangemix.vae.pt) - without a VAE selected in the settings your colors will look faded.
+* [TagComplete](https://github.com/DominikDoom/a1111-sd-webui-tagcomplete) to view all available image tags as you write your prompt.
+* [Image Browser (bugfix fork)](https://github.com/aka7774/sd_images_browser) to view your past images and their prompt metadata.
+* [EasyNegative](https://huggingface.co/datasets/gsdf/EasyNegative/blob/main/EasyNegative.safetensors) - put it in your `stable-diffusion-webui/embeddings` folder and write `EasyNegative` in your **negative** prompt to drastically improve your images.
+
+&nbsp;
 
 # Models
 
@@ -48,7 +60,10 @@ All known holo Loras will be linked to and backed up here. Put them in your `sta
 
 Most Loras work best with a weight of `0.7` as the default of `1` might fry your image.
 
-This repo also has image previews next to each file, they will appear in your Loras list. They also have prompt metadata, which you can access easily with the [Image Browser extension (bugfix fork)](https://github.com/aka7774/sd_images_browser).
+`{TI}` indicates a textual inversion embedding, an older but lighter alternative. They go into your `stable-diffusion-webui/embeddings` folder and are used like a normal word in your prompt.
+
+Next to each file is a preview image (with prompt metadata) which will appear in your extra networks menu.
+
 &nbsp;
 
 ## All Vtubers
@@ -57,6 +72,7 @@ These can do a wide variety of vtubers with only 1 Lora, but may have lower qual
 
 * [hll1 and hll3.1 extracted into a Lora](https://civitai.com/models/10664/all-vtubers-lora)
 * [Original source](https://mega.nz/folder/rBVGjIpQ#WCl9DL65mMRyaBmyIPA9WQ)
+
 &nbsp;
 
 ## Small Loras
@@ -75,12 +91,12 @@ This was done by me. Find them [here](https://huggingface.co/hollowstrawberry/ho
 <img src="https://huggingface.co/hollowstrawberry/hololive/resolve/main/lora-small-5.png" width="600"/>
 <img src="https://huggingface.co/hollowstrawberry/hololive/resolve/main/lora-small-6.png" width="600"/>
 </details>
-&nbsp;
 
+&nbsp;
 
 ## Outfits
 
-Main purpose of this repo. Format: `(Source 1) (Source 2)...` where each source can have multiple outfits. `{TI}` indicates a textual inversion (embedding) which goes in a different folder and is used as a normal word in your prompt.
+Main purpose of this repo. Format: `(Source 1) (Source 2)...` where each source can have multiple outfits.
 
 The default outfit is the first/main one for that talent. Generic means it's not trained on a particular outfit and can do various clothing. In any case, most Loras can change clothes.