October revision

README.md

@@ -48,7 +48,7 @@ Stable Diffusion is a very powerful AI image generation software you can run on
 
 The images you create may be used for any purpose, depending on the used model's license. Whether they are "yours" in a legal sense varies by local laws and is often inconclusive. Neither I or any of the people involved in Stable Diffusion or its models are responsible for anything you make, and you are expressively forbidden from creating illegal or harmful content.
 
-This guide is up to date with the best practices as of March 2023. One month is like a year in AI time, so hopefully it is still useful by the time you read it.
+This guide was finished in March 2023 and was last revised in October 2023. One month is like a year in AI time, so hopefully it is still useful by the time you read it.
 
  
 
@@ -56,6 +56,8 @@ This guide is up to date with the best practices as of March 2023. One month is
 
 The easiest way to use Stable Diffusion is through Google Colab. It borrows Google's computers to use AI, with variable time limitations, usually a few hours every day. You will need at least one Google account and we will be using Google Drive to store your settings and resulting images.
 
+**Revision:** Google Colab now requires a subscription to run Stable Diffusion instances.
+
 If you instead want to run it on your own computer, [scroll down ▼](#install).
 
 1. Open [THIS PAGE](https://colab.research.google.com/drive/1wEa-tS10h4LlDykd87TF5zzpXIIQoCmq).
@@ -82,11 +84,6 @@ To run Stable Diffusion on your own computer you'll need at least 16 GB of RAM a
 
 1. Run the program. You will see a few options. First, turn on **medvram** and **xformers**. You may skip medvram if you have 12 or more GB of VRAM.
 
-1. Set your **Additional Launch Options** to: `--opt-channelslast --no-half-vae --theme dark` . Any extra options should be separated by spaces.
-    * If your graphics card has 4-6 GB of VRAM, add `--opt-split-attention-v1` as it may lower vram usage even further.
-    * If you want to run the program from your computer but want to use it in another device, such as your phone, add `--listen --enable-insecure-extension-access` . After launching, use your computer's local IP in the same WiFi network to access the interface. You can also add a password like `--gradio-auth name:1234` .
-    * Full list of possible parameters [here](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Command-Line-Arguments-and-Settings)
-
 1. Click **Launch** and wait for a browser window to open with the interface. It may take a while the first time.
 
 1. The page is now open. It's your own private website. The starting page is where you can make your images. But first, we'll go to the **Settings** tab. There will be sections of settings on the left.
@@ -110,8 +107,7 @@ Here you can select your checkpoint and VAE. We will go over what these are and
 1. **Models** <a name="model"></a>[▲](#index)
 
    The **model**, also called **checkpoint**, is the brain of your AI, designed for the purpose of producing certain types of images. There are many options, most of which are on [civitai](https://civitai.com). But which to choose? These are my recommendations:
-   * For anime, [7th Heaven Mix](https://civitai.com/models/4669/corneos-7th-heaven-mix) has a nice aesthetic similar to anime movies, while [Abyss Orange Mix 3](https://civitai.com/models/9942/abyssorangemix3-aom3) *(__Note:__ scroll down there and choose the AOM3 option)* offers more realism in the form of advanced lighting and softer shading, as well as more lewdness. I merged these two options into [Heaven Orange Mix](https://civitai.com/models/14305/heavenorangemix).
-   * While AOM3 is extremely capable for NSFW, the popular [Grapefruit](https://civitai.com/models/2583/grapefruit-hentai-model) hentai model may also fit your needs.
+   * For anime, [MeinaMix](https://civitai.com/models/7240/meinamix) and its family of models should serve most purposes very well. I also merged my own model called [Limbo Mix](https://civitai.com/models/155337) which you may try if you'd like.
    * For general art go with [DreamShaper](https://civitai.com/models/4384/dreamshaper), there are few options quite like it in terms of creativity. An honorable mention goes to [Pastel Mix](https://civitai.com/models/5414/pastel-mix-stylized-anime-model), which has a beautiful and unique aesthetic with the addition of anime.
    * For photorealism go with [Deliberate](https://civitai.com/models/4823/deliberate). It can do almost anything, but specially photographs. Very intricate results.
    * The [Uber Realistic Porn Merge](https://civitai.com/models/2661/uber-realistic-porn-merge-urpm) is self-explanatory.
@@ -130,10 +126,10 @@ Here you can select your checkpoint and VAE. We will go over what these are and
 
    If you're using the colab in this guide, you should already have the below VAEs, as I told you to select them before running.
 
-   There are mainly 3 different VAEs in circulation:
-   * [anything vae](https://huggingface.co/WarriorMama777/OrangeMixs/resolve/main/VAEs/orangemix.vae.pt), also known as the orangemix vae. All anime models use this.
+   Most people use one of 3 different VAEs:
+   * [anything vae](https://huggingface.co/WarriorMama777/OrangeMixs/resolve/main/VAEs/orangemix.vae.pt), also known as the orangemix vae. Used to be the most popular for anime, but it's the least vibrant of all vaes.
    * [vae-ft-mse](https://huggingface.co/stabilityai/sd-vae-ft-mse-original/blob/main/vae-ft-mse-840000-ema-pruned.safetensors), the latest from Stable Diffusion itself. Used by photorealism models and such.
-   * [kl-f8-anime2](https://huggingface.co/hakurei/waifu-diffusion-v1-4/resolve/main/vae/kl-f8-anime2.ckpt), also known as the Waifu Diffusion VAE, it is older and produces more saturated results. Used by Pastel Mix.
+   * [kl-f8-anime2](https://huggingface.co/hakurei/waifu-diffusion-v1-4/resolve/main/vae/kl-f8-anime2.ckpt), also known as the Waifu Diffusion VAE, it is older and produces more saturated results. 
 
    The VAEs normally go into the `stable-diffusion-webui/models/VAE` folder.
    
@@ -146,7 +142,9 @@ Here you can select your checkpoint and VAE. We will go over what these are and
    On the first tab, **txt2img**, you'll be making most of your images. This is where you'll find your *prompt* and *negative prompt*.  
    Stable Diffusion is not like Midjourney or other popular image generation software, you can't just ask it what you want. You have to be specific. *Very* specific.  
    Most people have found a prompt that works for them and they swear by it, often recommended by other people. I will show you my own personal example of a prompt and negative prompt:
-   
+
+   **Revision:** These generic prompts have become less and less useful, as modern models don't really need them to work nicely. A simple negative prompt is often all you need.
+
    * Anime
       * `2d, masterpiece, best quality, anime, highly detailed face, highly detailed background, perfect lighting`
       * `EasyNegative, worst quality, low quality, 3d, realistic, photorealistic, (loli, child, teen, baby face), zombie, animal, multiple views, text, watermark, signature, artist name, artist logo, censored`
@@ -163,11 +161,10 @@ Here you can select your checkpoint and VAE. We will go over what these are and
    ![Prompts](images/prompt.png)
 
    After a "base prompt" like the above, you may then start typing what you want. For example `young woman in a bikini in the beach, full body shot`. Feel free to add other terms you don't like to your negatives such as `old, ugly, futanari, furry`, etc.  
-   You can also save your prompts to reuse later with the buttons below Generate. Click the small 💾 *Save style* button and give it a name. Later, you can open your *Styles* dropdown to choose, then click 📋 *Apply selected styles to the current prompt*.
-
+   
    <a name="promptweight"></a>One important technique when writing prompts are emphasis and de-emphasis. When you surround something in `(parentheses)`, it will get more emphasis or **weight** in your resulting image, basically telling the AI that part is more important. The normal weight for every word is 1, and each parentheses will multiply by 1.1 (you can use multiple). You can also specify the weight yourself, like this: `(full body:1.4)`. You can also go below 1 to de-emphasize a word: `[brackets]` will multiply by 0.9, but you'll still need parentheses to go lower, like `(this:0.5)`.
 
-   Also note that hands and feet are famously difficult for AI to generate. These methods improve your chances, but you may need to do photoshopping, inpainting, or advanced techniques with [ControlNet ▼](#controlnet) to get it right.
+   Also note that hands and feet are famously difficult for AI to generate. Models have become better at them over time, but you may need to do photoshopping, inpainting, or advanced techniques with [ControlNet ▼](#controlnet) to get it right.
 
 1. **Generation parameters** <a name="gen"></a>[▲](#index)
 
@@ -178,7 +175,7 @@ Here you can select your checkpoint and VAE. We will go over what these are and
    * **Sampling method:** This is the algorithm that formulates your image, and each produce different results. The default of `Euler a` is often the best. There are also very good results for `DPM++ 2M Karras` and `DPM++ SDE Karras`. See below for a comparison.
    * **Sampling steps:** These are "calculated" beforehand, and so more steps doesn't always mean more detail. I always go with 30, you may go from 20-50 and find consistently good results. See below for a comparison.
    * **Width and Height:** 512x512 is the default, and you should almost never go above 768 in either direction as it may distort and deform your image. To produce bigger images see `Hires fix`.
-   * **Batch Count and Batch Size:** Batch *size* is how many images your graphics card will generate at the same time, which is limited by its VRAM. Batch *count* is how many times to repeat those. Batches have consecutive seeds, more on seeds below.
+   * **Batch Count and Batch Size:** Batch *size* is how many images your graphics card will generate at the same time, which is limited by its VRAM. Batch *count* is how many times to repeat that batch size. Batches have consecutive seeds, more on seeds below.
    * **CFG Scale:** "Lower values produce more creative results". You should almost always stick to 7, but 4 to 10 is an acceptable range.
    * **Seed:** A number that guides the creation of your image. The same seed with the same prompt and parameters produces the same image every time, except for small details and under some circumstances.
   
@@ -187,10 +184,7 @@ Here you can select your checkpoint and VAE. We will go over what these are and
    * **Hires steps:** I recommend at least half as many as your sampling steps. Higher values aren't always better, and they take a long time, so be conservative here.
    * **Denoising strength:** The most important parameter. Near 0.0, no detail will be added to the image. Near 1.0, the image will be changed completely. I recommend something between 0.2 and 0.6 depending on the image, to add enough detail as the image gets larger, without *destroying* any original details you like.
     
-   Others:
-   * **Restore faces:** May improve realistic faces. I never need it with the models and prompts listed in this guide as well as hires fix.
-   * **Tiling:** Used to produce repeating textures to put on a grid. Not very useful.
-   * **Script:** Lets you access useful features and extensions, such as [X/Y/Z Plot ▼](#plot) which lets you compare images with varying parameters on a grid. Very powerful.
+   **Script:** Lets you access useful features and extensions, such as [X/Y/Z Plot ▼](#plot) which lets you compare images with varying parameters on a grid. Very powerful.
 
    Here is a comparison of a few popular samplers and various sampling steps:
 
@@ -217,9 +211,9 @@ Here you can select your checkpoint and VAE. We will go over what these are and
 ![Extensions](images/extensions.png)
 
 Here are some useful extensions. If you're using the colab in this guide you already have most of these, otherwise I hugely recommend you manually add the first 2:
+* [ADetailer](https://github.com/Bing-su/adetailer) - Improves the faces or other features of your generated images by refining those details.
 * [Image Browser (updated)](https://github.com/AlUlkesh/stable-diffusion-webui-images-browser) - This will let you browse your past generated images very efficiently, as well as directly sending their prompts and parameters back to txt2img, img2img, etc.
 * [TagComplete](https://github.com/DominikDoom/a1111-sd-webui-tagcomplete) - Absolutely essential for anime art. It will show you the matching booru tags as you type. Anime models work via booru tags, and prompts without them usually don't work, so knowing them is godmode. Not all tags will work well in all models though, specially if they're rare.
-* [Locon](https://github.com/KohakuBlueleaf/a1111-sd-webui-locon) - Lets you use LoCons and LoHas. More info [below ▼](#lycoris).
 * [ControlNet](https://github.com/Mikubill/sd-webui-controlnet) - A huge extension deserving of [its own guide ▼](#controlnet). It lets you analyze any image and use it as an referene for your own image. Practically speaking, it can create any pose or environment you want.
 * [Ultimate Upscale](https://github.com/Coyote-A/ultimate-upscale-for-automatic1111) - A script usable from the img2img section to make really large images, where normally you can only go as high as your VRAM allows. See [Ultimate Upscaler ▼](#ultimate).
 * [Two-shot](https://github.com/opparco/stable-diffusion-webui-two-shot) - Normally you can't create more than one distinct character in the same image without them blending together. This extension lets you divide the image into parts; full, left side, right side; allowing you to make nice 2-character images.
@@ -232,7 +226,7 @@ Here are some useful extensions. If you're using the colab in this guide you alr
 
 LoRA or *Low-Rank Adaptation* is a form of **Extra Network** and the latest technology that lets you append a sort of smaller model to any of your full models. They are similar to embeddings, one of which you might've seen [earlier ▲](#promptneg), but Loras are larger and often more capable. Technical details omitted.
 
-Loras can represent a character, an artstyle, poses, clothes, or even a human face (though I do not endorse this). Checkpoints are usually capable enough for general work, but when it comes to specific details with little existing examples, you'll need a Lora. They can be downloaded from [civitai](https://civitai.com) or [elsewhere (NSFW)](https://gitgud.io/gayshit/makesomefuckingporn#lora-list) and are 144 MB by default, but they can go as low as 1 MB. Bigger Loras are not always better. They come in `.safetensors` format, same as most checkpoints.
+Loras can represent a character, an artstyle, poses, clothes, or even a human face (though I do not endorse this). Checkpoints are usually capable enough for general work, but when it comes to specific details with little existing examples, you'll need a Lora. They can be downloaded from [civitai](https://civitai.com) or [elsewhere (NSFW)](https://gitgud.io/gayshit/makesomefuckingporn#lora-list) and are usually between 9 MB and 144 MB. Note that bigger Loras are not necessarily better. They come in `.safetensors` format, same as most checkpoints.
 
 Place your Lora files in the `stable-diffusion-webui/models/Lora` folder, or if you're using the colab in this guide paste the direct download link into the `custom_urls` text box. Then, look for the 🎴 *Show extra networks* button below the big orange Generate button. It will open a new section either directly below or at the very bottom. Click on the Lora tab and press the **Refresh** button to scan for new Loras. When you click a Lora in that menu it will get added to your prompt, looking like this: `<lora:filename:1>`. The start is always the same. The filename will be the exact filename in your system without the `.safetensors` extension. Finally, the number is the weight, like we saw [earlier ▲](#promptweight). Most Loras work between 0.5 and 1 weight, and too high values might "fry" your image, specially if using multiple Loras at the same time.
 
@@ -240,15 +234,7 @@ Place your Lora files in the `stable-diffusion-webui/models/Lora` folder, or if
 
 An example of a Lora is [Thicker Lines Anime Style](https://civitai.com/models/13910/thicker-lines-anime-style-lora-mix), which is perfect if you want your images to look more like traditional anime.
 
-* Lycoris <a name="lycoris"></a>[▲](#index)
-
-   LyCORIS is a new development that lets LoRAs learn more layers. [Learn about it here](https://github.com/KohakuBlueleaf/Lycoris). You'll need [this extension](https://github.com/KohakuBlueleaf/a1111-sd-webui-locon) to use them.
-
-   As of now there are 2 new LoRA types:
-   * **LoCon** - Said to be good with styles
-   * **LoHa** - Said to be good with styles that also contain characters
- 
-   You can make your own in the [trainer further down ▼](#traincolab).
+There are other types of Lora under the umbrella term **Lycoris**, but webui treats them the same now, and you don't need to know much about it as the end user.
 
 &nbsp;
 
@@ -262,7 +248,7 @@ The colab in this guide comes with several of them, including **Remacri**, which
 
 * A few notable ones can be [found here](https://huggingface.co/hollowstrawberry/upscalers-backup/tree/main/ESRGAN).
 * LDSR is an advanced yet slow upscaler, its model and config can be [found here](https://huggingface.co/hollowstrawberry/upscalers-backup/tree/main/LDSR) and both must be placed in `stable-diffusion-webui/models/LDSR`.
-* The [Upscale Wiki](https://upscale.wiki/wiki/Model_Database) contains dozens of historical choices.
+* This [upscaler model database](https://openmodeldb.info/) contains a ton of possible choices.
 
 Here are some comparisons. All of them were done at 0.4 denoising strength. Note that some of the differences may be completely up to random chance.
 
@@ -443,7 +429,6 @@ You can also train a Lora on your own computer if you have at least 8 GB of VRAM
 That's it, that's the end of this guide for now. I'd be grateful if you want to contribute on missing topics like:
 * img2img
 * Inpainting
-* Controlnet t2i adapters
 
 Thank you for reading!