some smaller fixes to linux and windows install

This commit is contained in:
mauwii 2022-09-18 04:09:42 +02:00
parent 66e9fd4771
commit 6d09f8c6b2
No known key found for this signature in database
GPG Key ID: D923DB04ADB3F5AB
2 changed files with 25 additions and 24 deletions

View File

@ -2,6 +2,8 @@
title: Linux title: Linux
--- ---
## Installation
1. You will need to install the following prerequisites if they are not already 1. You will need to install the following prerequisites if they are not already
available. Use your operating system's preferred installer. available. Use your operating system's preferred installer.
@ -96,15 +98,15 @@ title: Linux
launch the dream script (step 8). If you forget to activate the ldm launch the dream script (step 8). If you forget to activate the ldm
environment, the script will fail with multiple `ModuleNotFound` errors. environment, the script will fail with multiple `ModuleNotFound` errors.
### Updating to newer versions of the script ## Updating to newer versions of the script
This distribution is changing rapidly. If you used the `git clone` method This distribution is changing rapidly. If you used the `git clone` method
(step 5) to download the stable-diffusion directory, then to update to the (step 5) to download the stable-diffusion directory, then to update to the
latest and greatest version, launch the Anaconda window, enter latest and greatest version, launch the Anaconda window, enter
`stable-diffusion` and type: `stable-diffusion` and type:
```bash ```bash
(ldm) ~/stable-diffusion$ git pull (ldm) ~/stable-diffusion$ git pull
``` ```
This will bring your local copy into sync with the remote one. This will bring your local copy into sync with the remote one.

View File

@ -28,17 +28,16 @@ in the wiki
### **Conda** ### **Conda**
1. Install Anaconda3 (miniconda3 version) from here: 1. Install Anaconda3 (miniconda3 version) from [here](https://docs.anaconda.com/anaconda/install/windows/)
https://docs.anaconda.com/anaconda/install/windows/
2. Install Git from here: https://git-scm.com/download/win 2. Install Git from [here](https://git-scm.com/download/win)
3. Launch Anaconda from the Windows Start menu. This will bring up a command 3. Launch Anaconda from the Windows Start menu. This will bring up a command
window. Type all the remaining commands in this window. window. Type all the remaining commands in this window.
4. Run the command: 4. Run the command:
```bash ```batch
git clone https://github.com/lstein/stable-diffusion.git git clone https://github.com/lstein/stable-diffusion.git
``` ```
@ -48,15 +47,15 @@ in the wiki
5. Enter the newly-created stable-diffusion folder. From this step forward make 5. Enter the newly-created stable-diffusion folder. From this step forward make
sure that you are working in the stable-diffusion directory! sure that you are working in the stable-diffusion directory!
```bash ```batch
cd stable-diffusion cd stable-diffusion
``` ```
6. Run the following two commands: 6. Run the following two commands:
```bash ```batch
conda env create -f environment.yaml (step 6a) conda env create -f environment.yaml
conda activate ldm (step 6b) conda activate ldm
``` ```
This will install all python requirements and activate the "ldm" environment This will install all python requirements and activate the "ldm" environment
@ -64,7 +63,7 @@ in the wiki
7. Run the command: 7. Run the command:
```bash ```batch
python scripts\preload_models.py python scripts\preload_models.py
``` ```
@ -77,9 +76,9 @@ in the wiki
8. Now you need to install the weights for the big stable diffusion model. 8. Now you need to install the weights for the big stable diffusion model.
- For running with the released weights, you will first need to set up an - For running with the released weights, you will first need to set up an
acount with Hugging Face (https://huggingface.co). acount with [Hugging Face](https://huggingface.co).
- Use your credentials to log in, and then point your browser at - Use your credentials to log in, and then point your browser at
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original. [https://huggingface.co/CompVis/stable-diffusion-v-1-4-original](https://huggingface.co/CompVis/stable-diffusion-v-1-4-original).
- You may be asked to sign a license agreement at this point. - You may be asked to sign a license agreement at this point.
- Click on "Files and versions" near the top of the page, and then click on - Click on "Files and versions" near the top of the page, and then click on
the file named `sd-v1-4.ckpt`. You'll be taken to a page that prompts you the file named `sd-v1-4.ckpt`. You'll be taken to a page that prompts you
@ -90,7 +89,7 @@ in the wiki
Now run the following commands from **within the stable-diffusion directory** Now run the following commands from **within the stable-diffusion directory**
to copy the weights file to the right place: to copy the weights file to the right place:
```bash ```batch
mkdir -p models\ldm\stable-diffusion-v1 mkdir -p models\ldm\stable-diffusion-v1
copy C:\path\to\sd-v1-4.ckpt models\ldm\stable-diffusion-v1\model.ckpt copy C:\path\to\sd-v1-4.ckpt models\ldm\stable-diffusion-v1\model.ckpt
``` ```
@ -102,7 +101,7 @@ in the wiki
9. Start generating images! 9. Start generating images!
```bash ```batch
# for the pre-release weights # for the pre-release weights
python scripts\dream.py -l python scripts\dream.py -l
@ -122,14 +121,14 @@ in the wiki
--- ---
### Updating to newer versions of the script ## Updating to newer versions of the script
This distribution is changing rapidly. If you used the `git clone` method This distribution is changing rapidly. If you used the `git clone` method
(step 5) to download the stable-diffusion directory, then to update to the (step 5) to download the stable-diffusion directory, then to update to the
latest and greatest version, launch the Anaconda window, enter latest and greatest version, launch the Anaconda window, enter
`stable-diffusion`, and type: `stable-diffusion`, and type:
```bash ```batch
git pull git pull
conda env update -f environment.yaml conda env update -f environment.yaml
``` ```