Update README.md

README.md

@@ -12,7 +12,7 @@ tags:
 base_model: "stabilityai/stable-diffusion-xl-base-1.0"
 ---
 
-<h1 align="center">ArtiWaifu Diffusion 1.0</h1>
+<h1 align="center"><strong style="font-size: 48px;">ArtiWaifu Diffusion 1.0</strong></h1>
 
 We have released the **A**rti**Wa**ifu Diffusion V1.0 model, designed to generate aesthetically pleasing and faithfully restored anime-style illustrations.
 The AWA Diffusion is an iteration of the Stable Diffusion XL model, mastering over 6000 artistic styles and more than 4000 anime characters, generating images through [trigger words](#trigger-words).
@@ -94,14 +94,14 @@ AWA Diffusion supports the following <span style="color:red">Painting Style Tags
 - All painting style tags supported by [AID XL 0.8](https://civitai.com/models/124189/anime-illust-diffusion-xl), such as `flat-pasto`, etc.;
 - All style tags supported by [Neta Art XL 1.0](https://civitai.com/models/410737/neta-art-xl), such as `gufeng`, etc.;
 
-See the [Painting Style Tags List](/references/style.csv) for full lists of painting style tags.
+See the [Painting Style Tags List](https://huggingface.co/Eugeoter/artiwaifu-diffusion-1.0/blob/main/references/style.csv) for full lists of painting style tags.
 
 AWA Diffusion supports the following <span style="color:blue">Artistic Style Tags</span>:
 
 - Artistic style tags available in the Danbooru tags, such as `by yoneyama mai`, `by wlop`, etc.;
 - All artistic style tags supported by [AID XL 0.8](https://civitai.com/models/124189/anime-illust-diffusion-xl), such as `by antifreeze3`, `by 7thknights`, etc.;
 
-See the [Artistic Style Tags List](/references/artist.csv) for full lists of artistic style tags.
+See the [Artistic Style Tags List](https://huggingface.co/Eugeoter/artiwaifu-diffusion-1.0/blob/main/references/artist.csv) for full lists of artistic style tags.
 
 The higher the tag count in the tag repository, the more thoroughly the artistic style has been trained, and the higher the fidelity in generation. Typically, artistic style tags with a count higher than **50** yield better generation results.
 
@@ -118,7 +118,7 @@ Similarly, when triggering characters, add a `1` as a prefix to the character tr
 
 Character tags describe the character IP in the generated image. Using character tags will guide the model to generate the **appearance features** of the character.
 
-Character tags also need to be sourced from the [Character Tag List](/references/character.csv). To generate a specific character, first find the corresponding trigger word in the tag repository, replace all underscores `_` in the trigger word with spaces ` `, and prepend `1 ` to the character name.
+Character tags also need to be sourced from the [Character Tag List](https://huggingface.co/Eugeoter/artiwaifu-diffusion-1.0/blob/main/references/character.csv). To generate a specific character, first find the corresponding trigger word in the tag repository, replace all underscores `_` in the trigger word with spaces ` `, and prepend `1 ` to the character name.
 For example, `1 ayanami rei` triggers the model to generate the character Rei Ayanami from the anime "EVA," corresponding to the Danbooru tag `ayanami_rei`; `1 asuna (sao)` triggers the model to generate the character Asuna from "Sword Art Online," corresponding to the Danbooru tag `asuna_(sao)`. [More examples](#examples)
 The higher the tag count in the tag repository, the more thoroughly the character has been trained, and the higher the fidelity in generation. Typically, character tags with a count higher than **100** yield better generation results.
 
@@ -144,18 +144,18 @@ The higher the tag count in the tag repository, the more thoroughly the characte
 
 ❓ **Question:** Why do some character tags contain bracket annotations, e.g., `lucy (cyberpunk)`, while others do not, e.g., `frieren`?
 
-💡 **Answer:** In different works, there may be characters with the same name, such as Asuna from "Sword Art Online" and "Blue Archive". To distinguish these characters with the same name, it is necessary to annotate the character's name with the work's name, abbreviated if the name is too long. For characters with unique names that currently have no duplicates, like `frieren`, no special annotations are required.
+💡 **Answer:** In different works, there may be characters with the same name, such as Asuna from "Sword Art Online" and "Blue Archive". To distinguish these characters with the same name, it is necessary to annotate the character's name with the work's name, abbreviated if the name is too long. For characters with unique names that currently have no duplicates, like `frieren`, no special annotations are required. Here is an example:
 
 #### Quality Tags and Aesthetic Tags
 
 For AWA Diffusion, including quality descriptors in your positive prompt is **very important**. Quality descriptions relate to quality tags and aesthetic tags.
 
 Quality tags directly describe the aesthetic quality of the generated image, impacting the detail, texture, human anatomy, lighting, color, etc. Adding quality tags helps the model generate higher quality images. Quality tags are ranked from highest to lowest as follows:
-<span style="color:orange">amazing quality</span> -> <span style="color:purple">best quality</span> -> <span style="color:blue">high quality</span> -> <span style="color:green">normal quality</span> -> <span style="color:black">low quality</span> -> <span style="color:grey">worst quality</span>
+<span style="color:orange">amazing quality</span> -> <span style="color:purple">best quality</span> -> <span style="color:blue">high quality</span> -> <span style="color:green">normal quality</span> -> low quality -> <span style="color:grey">worst quality</span>
 
 Aesthetic tags describe the aesthetic features of the generated image, aiding the model in producing artistically appealing images. In addition to typical aesthetic words like `perspective`, `lighting and shadow`, AWA Diffusion has been specially trained to respond effectively to aesthetic trigger words such as `beautiful color`, `detailed`, and `aesthetic`, which respectively express appealing colors, details, and overall beauty.
 
-The recommended generic way to describe quality is: <Your Prompt>, <span style="color:orange">beautiful color, detailed, amazing quality</span>
+The recommended generic way to describe quality is: _(Your Prompt), <span style="color:orange">beautiful color, detailed, amazing quality</span>_
 
 **Tips for Quality and Aesthetic Tags**
 
@@ -175,7 +175,7 @@ Rating tags describe the level of exposure in the content of the generated image
 
 **A**
 
-<span style="color:green">by yoneyama mai</span>, <span style="color:blue">1 frieren</span>, 1girl, solo, fantasy theme, smile, holding a magic wand, <span style="color:yellow">beautiful color</span>, <span style="color:red">amazing quality</span>
+_<span style="color:green">by yoneyama mai</span>, <span style="color:blue">1 frieren</span>, 1girl, solo, fantasy theme, smile, holding a magic wand, <span style="color:yellow">beautiful color</span>, <span style="color:red">amazing quality</span>_
 
 1. <span style="color:green">by yoneyama mai</span> triggers the artistic style of Yoneyama Mai, placed at the front to enhance the effect.
 2. <span style="color:blue">1 frieren</span> triggers the character Frieren from the series "Frieren at the Funeral."
@@ -184,7 +184,7 @@ Rating tags describe the level of exposure in the content of the generated image
 
 **B**
 
-<span style="color:green">by nixeu</span>, <span style="color:blue">1 lucy (cyberpunk)</span>, 1girl, solo, cowboy shot, gradient background, white cropped jacket, underneath bodysuit, shorts, thighhighs, hip vent, <span style="color:yellow">detailed</span>, <span style="color:red">best quality</span>
+_<span style="color:green">by nixeu</span>, <span style="color:blue">1 lucy (cyberpunk)</span>, 1girl, solo, cowboy shot, gradient background, white cropped jacket, underneath bodysuit, shorts, thighhighs, hip vent, <span style="color:yellow">detailed</span>, <span style="color:red">best quality</span>_
 
 #### Example 2: Style Mixing
 
@@ -192,13 +192,13 @@ By layering multiple different style tags, you can generate images with features
 
 **A** Simple Mixing
 
-**<span style="color:green">by ningen mame</span>, <span style="color:cyan">by ciloranko</span>, <span style="color:blue">by sho (sho lwlw)</span>**, 1girl, 1 hatsune miku, sitting, arm support, smile, detailed, amazing quality
+_**<span style="color:green">by ningen mame</span>, <span style="color:cyan">by ciloranko</span>, <span style="color:blue">by sho (sho lwlw)</span>**, 1girl, 1 hatsune miku, sitting, arm support, smile, detailed, amazing quality_
 
 **B** Weighted Mixing
 
 Using AUTOMATIC1111 WebUI prompt weighting syntax (parentheses weighting), weight different style tags to better control the generated image's style.
 
-**<span style="color:green">(by ningen mame:0.8)</span>, <span style="color:cyan">(by ciloranko:1.1)</span>, <span style="color:blue">(by sho \(sho lwlw\):1.2)</span>**, 1girl, 1 hatsune miku, sitting, arm support, smile, detailed, amazing quality
+_**<span style="color:green">(by ningen mame:0.8)</span>, <span style="color:cyan">(by ciloranko:1.1)</span>, <span style="color:blue">(by sho \(sho lwlw\):1.2)</span>**, 1girl, 1 hatsune miku, sitting, arm support, smile, detailed, amazing quality_
 
 #### Example 3: Multi-Character Scenes
 
@@ -206,11 +206,11 @@ By adding multiple character tags to your prompts, you can generate images with
 
 **A** Mixed Gender Scene
 
-**1girl and 1boy, <span style="color:blue">1 ganyu</span> girl, <span style="color:cyan">1 gojou satoru</span> boy**, beautiful color, amazing quality
+_**1girl and 1boy, <span style="color:blue">1 ganyu</span> girl, <span style="color:cyan">1 gojou satoru</span> boy**, beautiful color, amazing quality_
 
 **B** Same Gender Scene
 
-**2girls, <span style="color:blue">1 ganyu</span> girl, <span style="color:orange">1 yoimiya</span> girl**, beautiful color, amazing quality
+_**2girls, <span style="color:blue">1 ganyu</span> girl, <span style="color:orange">1 yoimiya</span> girl**, beautiful color, amazing quality_
 
 ## Future Work