Docs updates

DOCS.md

@@ -4,19 +4,26 @@ TL;DR: Enter a prompt or roll the `🎲` and press `Generate`.
 
 ## Prompting
 
-Positive and negative prompts are embedded by [Compel](https://github.com/damian0815/compel) for weighting. See [syntax features](https://github.com/damian0815/compel/blob/main/doc/syntax.md) to learn more and read [Civitai](https://civitai.com)'s guide on [prompting](https://education.civitai.com/civitais-prompt-crafting-guide-part-1-basics/) for best practices.
+Positive and negative prompts are embedded by [Compel](https://github.com/damian0815/compel) for weighting. See [syntax features](https://github.com/damian0815/compel/blob/main/doc/syntax.md) to learn more.
 
-### Arrays
+Use `+` or `-` to increase the weight of a token. The weight grows exponentially when chained. For example, `blue+` means 1.1x more attention is given to `blue`, while `blue++` means 1.1^2 more, and so on. The same applies to `-`.
 
-Arrays allow you to generate different images from a single prompt. For example, `[[cat,corgi]]` will expand into 2 separate prompts. Make sure `Images` is set accordingly (e.g., 2). Only works for the positive prompt. Inspired by [Fooocus](https://github.com/lllyasviel/Fooocus/pull/1503).
+For groups of tokens, wrap them in parentheses and multiply by a float between 0 and 2. For example, `a (birthday cake)1.3 on a table` will increase the weight of both `birthday` and `cake` by 1.3x. This also means the entire scene will be more birthday-like, not just the cake. To counteract this, you can use `-` inside the parentheses on specific tokens, e.g., `a (birthday-- cake)1.3`, to reduce the birthday aspect.
 
-## Styles
+This is the same syntax used in [InvokeAI](https://invoke-ai.github.io/InvokeAI/features/PROMPTS/) and it differs from AUTOMATIC1111:
 
-Styles are prompt templates from twri's [sdxl_prompt_styler](https://github.com/twri/sdxl_prompt_styler) Comfy node. Start with a subject like "cat", pick a style, and iterate from there.
+| Compel      | AUTOMATIC1111 |
+| ----------- | ------------- |
+| `blue++`    | `((blue))`    |
+| `blue--`    | `[[blue]]`    |
+| `(blue)1.2` | `(blue:1.2)`  |
+| `(blue)0.8` | `(blue:0.8)`  |
 
-## Scale
+### Arrays
+
+Arrays allow you to generate multiple different images from a single prompt. For example, `an adult [[blonde,brunette]] [[man,woman]]` will expand into **4** different prompts. This implementation was inspired by [Fooocus](https://github.com/lllyasviel/Fooocus/pull/1503).
 
-Rescale up to 4x using [Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN) from [ai-forever](https://huggingface.co/ai-forever/Real-ESRGAN).
+> NB: Make sure to set `Images` to the number of images you want to generate. Otherwise, only the first prompt will be used.
 
 ## Models
 
@@ -29,6 +36,16 @@ Each model checkpoint has a different aesthetic:
 * [SG161222/RealVisXL_V5.0](https://huggingface.co/SG161222/RealVisXL_V5.0): photorealistic
 * [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0): base
 
+## Styles
+
+[Styles](https://huggingface.co/spaces/adamelliotfields/diffusion/blob/main/data/styles.json) are prompt templates that wrap your positive and negative prompts. They were originally derived from the [twri/sdxl_prompt_styler](https://github.com/twri/sdxl_prompt_styler) Comfy node, but have since been entirely rewritten.
+
+Start by framing a simple subject like `portrait of a young adult woman` or `landscape of a mountain range` and experiment.
+
+## Scale
+
+Rescale up to 4x using [Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN) with weights from [ai-forever](ai-forever/Real-ESRGAN). Necessary for high-resolution images.
+
 ## Advanced
 
 ### DeepCache

README.md

@@ -47,11 +47,10 @@ Gradio app for Stable Diffusion XL featuring:
 
 * txt2img pipeline with refiner (img2img with IP-Adapter and ControlNet coming soon)
 * Curated models (LoRAs and TIs coming soon)
-* 100+ styles from sdxl_prompt_styler
-* 150+ prompts from StableStudio
 * Compel prompt weighting
+* Dozens of styles and starter prompts
 * Multiple samplers with Karras scheduling
-* DeepCache for speed
+* DeepCache available
 * Real-ESRGAN upscaling
 
 ## Usage