Merge branch 'main' into lstein-improve-migration

configs/INITIAL_MODELS.yaml

@@ -1,21 +1,21 @@
-stable-diffusion-2.1-768:
+stable-diffusion-2_1-768:
    description: Stable Diffusion version 2.1 diffusers model, trained on 768x768 images (5.21 GB)
    repo_id: stabilityai/stable-diffusion-2-1
    format: diffusers
    recommended: True
-stable-diffusion-2.1-base:
+stable-diffusion-2_1-base:
    description: Stable Diffusion version 2.1 diffusers base model, trained on 512x512 images (5.21 GB)
    repo_id: stabilityai/stable-diffusion-2-1-base
    format: diffusers
    recommended: False
-stable-diffusion-1.5:
+stable-diffusion-1_5:
    description: Stable Diffusion version 1.5 weight file (4.27 GB)
    repo_id: runwayml/stable-diffusion-v1-5
    format: diffusers
    recommended: True
    vae:
      repo_id: stabilityai/sd-vae-ft-mse
-stable-diffusion-1.4:
+stable-diffusion-1_4:
    description: The original Stable Diffusion version 1.4 weight file (4.27 GB)
    repo_id: CompVis/stable-diffusion-v1-4
    recommended: False
@@ -24,7 +24,7 @@ stable-diffusion-1.4:
       repo_id: stabilityai/sd-vae-ft-mse
    width: 512
    height: 512
-inpainting-1.5:
+inpainting-1_5:
    description: RunwayML SD 1.5 model optimized for inpainting (ckpt version) (4.27 GB)
    repo_id: runwayml/stable-diffusion-inpainting
    config: v1-inpainting-inference.yaml
@@ -36,12 +36,12 @@ inpainting-1.5:
    recommended: True
    width: 512
    height: 512
-waifu-diffusion-1.4:
+waifu-diffusion-1_4:
   description: Latest waifu diffusion 1.4 (diffusers version)
   format: diffusers
   repo_id: hakurei/waifu-diffusion
   recommended: True
-waifu-diffusion-1.3:
+waifu-diffusion-1_3:
    description: Stable Diffusion 1.4 fine tuned on anime-styled images (ckpt version) (4.27 GB)
    repo_id: hakurei/waifu-diffusion-v1-3
    config: v1-inference.yaml
@@ -53,14 +53,14 @@ waifu-diffusion-1.3:
    recommended: False
    width: 512
    height: 512
-trinart-2.0:
+trinart-2_0:
    description: An SD model finetuned with ~40,000 assorted high resolution manga/anime-style pictures (2.13 GB)
    repo_id: naclbit/trinart_stable_diffusion_v2
    format: diffusers
    recommended: False
    vae:
      repo_id: stabilityai/sd-vae-ft-mse
-trinart_characters-2.0:
+trinart_characters-2_0:
    description: An SD model finetuned with 19.2M anime/manga style images (ckpt version) (4.27 GB)
    repo_id: naclbit/trinart_derrida_characters_v2_stable_diffusion
    config: v1-inference.yaml
@@ -72,19 +72,19 @@ trinart_characters-2.0:
    recommended: False
    width: 512
    height: 512
-anything-4.0:
+anything-4_0:
    description: High-quality, highly detailed anime style images with just a few prompts
    format: diffusers
    repo_id: andite/anything-v4.0
    recommended: False
-papercut-1.0:
+papercut-1_0:
    description: SD 1.5 fine-tuned for papercut art (use "PaperCut" in your prompts) (2.13 GB)
    repo_id: Fictiverse/Stable_Diffusion_PaperCut_Model
    format: diffusers
    vae:
      repo_id: stabilityai/sd-vae-ft-mse
    recommended: False
-voxel_art-1.0:
+voxel_art-1_0:
    description: Stable Diffusion trained on voxel art (use "VoxelArt" in your prompts) (4.27 GB)
    repo_id: Fictiverse/Stable_Diffusion_VoxelArt_Model
    config: v1-inference.yaml

docs/installation/020_INSTALL_MANUAL.md

@@ -12,17 +12,18 @@ title: Installing Manually
 
 ## Introduction
 
-You have two choices for manual installation, the [first
+You have two choices for manual installation.
-one](#PIP_method) uses basic Python virtual environment (`venv`)
+The [first one](#pip-Install) uses basic Python virtual environment (`venv`)
-commands and the PIP package manager. The [second one](#Conda_method)
+command and `pip` package manager.
-based on the Anaconda3 package manager (`conda`). Both methods require
+The [second one](#Conda-method) uses Anaconda3 package manager (`conda`).
-you to enter commands on the terminal, also known as the "console".
+Both methods require you to enter commands on the terminal, also known as the
+"console".
 
-Note that the conda install method is currently deprecated and will not
+Note that the `conda` installation method is currently deprecated and will
-be supported at some point in the future.
+not be supported at some point in the future.
 
-On Windows systems you are encouraged to install and use the
+On Windows systems, you are encouraged to install and use the
-[Powershell](https://learn.microsoft.com/en-us/powershell/scripting/install/installing-powershell-on-windows?view=powershell-7.3),
+[PowerShell](https://learn.microsoft.com/en-us/powershell/scripting/install/installing-powershell-on-windows?view=powershell-7.3),
 which provides compatibility with Linux and Mac shells and nice
 features such as command-line completion.
 
@@ -37,7 +38,7 @@ manager, please follow these steps:
     ```bash
     python -V
     ```
-    
+
 2.  Clone the [InvokeAI](https://github.com/invoke-ai/InvokeAI) source code from
     GitHub:
 
@@ -52,15 +53,15 @@ manager, please follow these steps:
     environment named `invokeai`:
 
     ```bash
-    python -mvenv invokeai
+    python -m venv invokeai
     source invokeai/bin/activate
     ```
 
-4. Make sure that pip is installed in your virtual environment an up to date:
+4.  Make sure that pip is installed in your virtual environment an up to date:
 
     ```bash
-    python -mensurepip --upgrade
+    python -m ensurepip --upgrade
-    python -mpip install --upgrade pip
+    python -m pip install --upgrade pip
     ```
 
 5.  Pick the correct `requirements*.txt` file for your hardware and operating
@@ -199,20 +200,20 @@ manager, please follow these steps:
 
         You can permanently set the location of the runtime directory by setting the environment variable INVOKEAI_ROOT to the path of the directory.
 
-9. Render away!
+9.  Render away!
 
     Browse the [features](../features/CLI.md) section to learn about all the things you
     can do with InvokeAI.
 
     Note that some GPUs are slow to warm up. In particular, when using an AMD
     card with the ROCm driver, you may have to wait for over a minute the first
-    time you try to generate an image. Fortunately, after the warm up period
+    time you try to generate an image. Fortunately, after the warm-up period
     rendering will be fast.
 
-10. Subsequently, to relaunch the script, be sure to run "conda activate
+10. Subsequently, to relaunch the script, be sure to enter `InvokeAI` directory,
-    invokeai", enter the `InvokeAI` directory, and then launch the invoke
+    activate the virtual environment, and then launch `invoke.py` script.
-    script. If you forget to activate the 'invokeai' environment, the script
+    If you forget to activate the virtual environment,
-    will fail with multiple `ModuleNotFound` errors.
+    the script will fail with multiple `ModuleNotFound` errors.
 
     !!! tip
 

environments-and-requirements/requirements-base.txt

@@ -3,6 +3,7 @@ accelerate
 albumentations
 datasets
 diffusers[torch]~=0.11
+dnspython==2.2.1
 einops
 eventlet
 facexlib