From 21c4e5a5b9b644b12c4547fd3cbd5ce7857e6fa8 Mon Sep 17 00:00:00 2001 From: painebenjamin <57536852+painebenjamin@users.noreply.github.com> Date: Sat, 29 Jul 2023 14:43:02 -0400 Subject: [PATCH] Update README.md --- README.md | 40 +++++++++++++++++++++++++--------------- 1 file changed, 25 insertions(+), 15 deletions(-) diff --git a/README.md b/README.md index 065ea6b1..66af08cb 100644 --- a/README.md +++ b/README.md @@ -6,12 +6,11 @@ Enfugue is a feature-rich self-hosted Stable Diffusion web application.
- Forever open source, forever free. +Forever open source and totally free.
- - +
# Feature Summary @@ -27,7 +26,8 @@ Enfugue is a feature-rich self-hosted Stable Diffusion web application. - 🕹️ **Take Control:** Region prompting and Controlnet are standard. - 🔌 **Plug Away:** All features are available via JSON API, or can be added to your Python scripts using our `diffusers` extensions. - 👁️ **Eye Queue:** Have things to do? Send an unlimited\* number of invocations at once, let Enfugue take care of making sure they all get done. -- ☁️ **Your Own Cloud:** All of the best features you would expect from a SaaS application, with the security of knowing nothing ever leaves your computer. Results are kept by the app until you no longer need them, and your browser keeps a lengthy history of workspaces so you can always revisit where you left off. +- ☁️ **Your Own Cloud:** All of the best features you would expect from a SaaS application, with the security of knowing nothing ever leaves your computer. Results are kept by the app until you no longer need them, and your browser keeps a lengthy history of workspaces so you can always revisit where you left off. +- ⚙️ **Configurable:** Numerous configuration options are available, both in the GUI and via configuration file. Change IP addresses, ports, SSL configuration, directories, and much more. *\* configurable in-app, defaults to five queued invocations* @@ -35,9 +35,9 @@ Enfugue is a feature-rich self-hosted Stable Diffusion web application. ## As Easy as Possible: Self-Contained Executable -1. Navigate to [the Releases page](https://github.com/painebenjamin/app.enfugue.ai/releases) and download the latest release as a `.zip` (Windows) or `.tar.gz` (Linux). +1. Navigate to [the Releases page](https://github.com/painebenjamin/app.enfugue.ai/releases) and download the latest release as `.zip` (Windows) or `.tar.gz` (MacOS & Linux). 2. Extract the archive anywhere. See the releases page for details on extraction. -3. Navigate to the archive folder and run the executable file - `enfugue-server.exe` for Windows, or `enfugue.sh` for Linux. +3. Navigate to the archive folder and run the executable file - `enfugue-server.exe` for Windows, or `enfugue.sh` for Linux and MacOS. Some situations may require additional commands, see the releases page for more details. On windows, you will now see the Enfugue icon in the bottom-right-hand corner of your screen. Click on this to exit the server when you wish. To enable TensorRT for Windows follow the steps under **Windows TensorRT Support** below. @@ -54,7 +54,7 @@ This instruction assumes you are using a variant of [Conda](https://docs.conda.i ## À la Carte -You can install `enfugue` into any other latent diffusion environment using `pip install enfugue`. If you are on Linux and want to install TensorRT support as well, use `pip install enfugue[tensorrt]`. If you are on Windows, this will not work, you will need to install the python packages from source as detailed below. +You can install `enfugue` into any other latent diffusion Python environment using `pip install enfugue`. If you are on Linux and want to install TensorRT support as well, use `pip install enfugue[tensorrt]`. If you are on Windows, this will not work, you will need to install the python packages from source as detailed below. ## Windows Nvidia TensorRT Support @@ -124,9 +124,9 @@ While making images, the canvas will be replaced with in-progress samples, and t -You can move the entire canvas (pan) by placing your cursor over it then holding down the **middle-mouse** button, or alternatively **Ctrl+Left-Mouse-Button**, and move the canvas around. +You can move the entire canvas (pan) by placing your cursor over it then holding down the **middle-mouse** button, or alternatively **Ctrl+Left-Mouse-Button** or **Alt+Left-Mouse-Button** (**Option⌥+Left-Mouse-Button on MacOS**) , and move the canvas around. -Zoom in and out using the scroll wheel or scroll gestures. You can also click the `+` and `-` icons in the bottom-right-hand corner. Click 'RESET' at any time to bring the canvas back. +Zoom in and out using the scroll wheel or scroll gestures. You can also click the `+` and `-` icons in the bottom-right-hand corner. Click 'RESET' at any time to bring the canvas back to the initial position.@@ -186,14 +186,24 @@ The header contains useful information about your GPU, as well as two important ### The Model Picker -A special callout should be made to the Model Picker, the input in the top-left-hand corner of the Canvas: +A special callout should be made to the Model Picker, the input in the top-left-hand corner of the Canvas. This allows you to pick between installed checkpoints and pre-configured models: -![image](https://github.com/painebenjamin/app.enfugue.ai/assets/57536852/122837ea-52d7-45db-b1fe-47b655515efa) +
+
+ Selecting between installed checkpoints and preconfigured models.
+
+
+ Using advanced configuration after selecting a checkpoint.
+
- +
Once enabled in the settings menu, you will be taken to a login screen. The default user and password are both `enfugue`, all lowercase. You can change any other user's password as an administrator. @@ -261,7 +271,7 @@ Additional resources will be made available as they are needed, so don't hesitat ## The Enfugue Diffusion Pipeline -Enfugue uses an extension of `transformers.StableDiffusionPipeline` that provides a number of additional arguments over the typical signature, weaving between `txt2img`, `img2img`, `inpaint` and `controlnet` as necessary. It also has TensorRT support for all models in the pipeline. Start [here](https://github.com/painebenjamin/app.enfugue.ai/tree/main/src/python/enfugue) for documentation on how it is used. +Enfugue uses an extension of `diffusers.StableDiffusionPipeline` that provides a number of additional arguments over the typical signature, weaving between `txt2img`, `img2img`, `inpaint` and `controlnet` as necessary. It also has TensorRT support for all models in the pipeline. Start [here](https://github.com/painebenjamin/app.enfugue.ai/tree/main/src/python/enfugue) for documentation on how it is used. ## Building @@ -283,4 +293,4 @@ For anyone interested in building from source themselves, simply check out this ## Running directly from Source -To run directly from source (in development mode,) use the `scripts/run-dev.sh` script. This works on Windows (in Cygwin) and on Linux. +To run directly from source (in development mode,) use the `scripts/run-dev.sh` script. This works on Windows (in Cygwin) and on Linux, it has not been tested on MacOS.