The definitive Stable Diffusion experience ™
---NEW FEATURE SHOWCASE & HOWTO---
Notable: Inpainting/Outpainting, Live generation preview, Tiling, Upscaling, <4gb VRAM support, Negative prompts, CLIP
(Basic) CPU-only guide available Here
Japanese guide here 日本語ガイド
Special thanks to all anons who contributed
-Nvidia Maxwell-architecture or newer GPU with at least 2gb vram
-Linux or Windows 7/8/10+ (See tab for W7-specific instructions)
-20gb disk space
Step 2: Clone the WebUI repo to your desired location:
-Right-click and select 'Git Bash here'
git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui
(Note: to update, all you need to do is is type
git pull within the newly made webui folder)
Step 3: Download the 1.4 AI model from huggingface (requires signup) or HERE
(Alternate) 1.4 Waifu model trained on an additional 56k Danbooru images HERE (mirror)
(Note: Several GB larger than normal model, see instructions below for pruning)
Step 4: Rename your .ckpt file to "model.ckpt", and place it in the
Step 6 (Optional):
This reduces VRAM, and allows you to generate larger images or batches for a <10% loss in raw generation speed
Step 7: Run
webui-user.bat from Windows Explorer. Run it as normal user, not as administrator.
- Wait patiently while it installs dependencies and does a first time run.
It may seem "stuck" but it isn't. It may take up to 10-15 minutes.
And you're done!
- Open webui-user.bat
- After loading the model, it should give you a LAN address such as '127.0.0.1:7860'
- Enter the address into your browser to enter the GUI environment
Tip: Hover your mouse over UI elements for tooltips about what they do
- To exit, close the CMD window
RUNNING ON 4GB (And lower!)
These parameters are also useful for regular users who want to make larger images or batch sizes!
It is possible to drastically reduce VRAM usage with some modifications:
- Step 1: Edit
- Step 2: After
COMMANDLINE_ARGS=, enter your desired parameters:
- If you have 4GB VRAM and want to make 512x512 (or maybe up to 640x640) images,
- If you have 4GB VRAM and want to make larger images, or you get an out of memory error with --medvram,
- If you have 4GB VRAM and you still get an out of memory error,
--lowvram --always-batch-cond-uncond --opt-split-attentioninstead.
- If you have 2GB VRAM or 4GB VRAM and want to make images larger (but slower) than you can with --medvram,
- If you have more VRAM and want to make larger images than you can usually make,
(Generation will be moderately slower but some swear on these parameters)
-Otherwise, do not use any of these (Increases generation time)-
- If you get a green/black screen instead of generated pictures, you have a card that doesn't support half precision floating point numbers (known problem on 16xx cards):
You must use
--precision full --no-halfin addition to other flags, and the model will take much more space in VRAM
- Make sure to disable hardware acceleration in your browser and close anything which might be occupying VRAM if you are getting out-of-memory errors, and possibly remove GFPGAN (if you have it)
- Textual Inversion guide (Allows you to teach Stable Diffusion to understand new concepts!)
- Artist list with pictures
- Check out the wiki https://wiki.installgentoo.com/wiki/Stable_Diffusion
- Inpainting Tips
- Anon's guide for anime vectors (Waifu Diffusion)
- Remacri Upscaler(Landscapes) Lollypop Upscaler(Anthropomorphic Figures)
- Other Upscaler Models
(Place upscaler models in ESRGAN folder)
- Trinart Alternate .cpkt (Pixiv-esque illustrations, not as cohesive as waifu diffusion)
- Build great aesthetic prompts using the prompt builder
- Japanese keywords: https://chara-zokusei.jp/question_list
- Use Darkreader to change your Gradio theme to dark mode
- Informal Training guide (30gb vram+)
- Stable diffusion WebUI repo
- Waifu Diffusion huggingface page
- Make sure your folder paths do not have spaces
- Make sure you have the latest CUDA toolkit and GPU drivers you can run
- if your version of Python is not in PATH (or if another version is)
create or modify webui.settings.bat in the root folder (same place as webui.bat)
add the line set PYTHON=python to say the full path to your python executable:
You can do this for python, but not for git.
- The installer creates a python virtual environment, so none of installed modules will affect your system installation of python if you had one prior to installing this.
- To prevent the creation of virtual environment and use your system python, edit webui.bat replacing set
- webui.bat installs requirements from files
requirements_versions.txt, which lists versions for modules specifically compatible with Python 3.10.6.
If you choose to install for a different version of python, editing webui.bat to have set REQS_FILE=requirements.txt instead of set REQS_FILE=requirements_versions.txt may help (but I still reccomend you to just use the recommended version of python).
- If you feel you broke something and want to reinstall from scratch, delete directories: venv, repositories.
- If your output is a jumbled rainbow mess your image resolution is set TOO LOW
- Having too high of a CFG level will also introduce rainbow distortion, your CFG shouldn't be set above 20
- On older systems, you may have to change
- Make sure your installation is on the C: drive
- This guide is designed for NVIDIA GPUs only, as stable diffusion requires cuda cores.
AMD users should try THIS GUIDE
- Even though you might be able to generate larger, 512x512 is the optimal resolution for accurate results, as the model was trained on that resolution
Typically it is better to upscale a 512x image than render larger
- The Waifu model and normal .cpkt have their own pros and cons;
Non-anime promps done with the waifu .cpkt will be biased toward anime stylization, making realistic faces and people more difficult
- The outpainting script requires HIGH DENOISING to work properly (eg. 0.9)
Outpainting benefits from high steps
- Use ((( ))) around keywords to increase their strength and [[[ ]]] to decrease their strength
- Save prompt as style allows you to save a prompt as an easily selectable output. A box to select will appear to the left of Roll after you save your first style, allowing you to make a selection. Prompts can be deleted by accessing
(This can be helpful if you find a combination that generations really good images and want to repeatedly use it with varied subjects.)
- You can drag your favorite result from the output tab on the right back into img2img for further iteration
- The k_euler_a and k_dpm_2_a samplers give vastly different, more intricate results from the same seed & prompt
- Unlike other samplers, k_euler_a can generate high quality results from low steps. Try it with 10-25 instead of 50
- The seed for each generated result is in the output filename if you want to revisit it
- Using the same keywords as a generated image in img2img produces interesting variants
- It's recommended to have your prompts be at least 512 pixels in one dimension, or a 384x384 square at the smallest
Anything smaller will have heavy artifacting
- 512x512 will always yield the most accurate results as the model was trained at that resolution
- Try Low strength (0.3-0.4) + High CFG in img2img for interesting outputs
- You can use Japanese Unicode characters in prompts
-----Launching Different Models----- If you have multiple models installed and you want to switch between them conveniently, you can make another .bat
- Make a copy of webui-user.bat and name it whatever you want
--ckptfollowed by the desired model to your launch parameters:
-----Pruning Waifu .cpkt-----
The Waifu diffusion model is normally 7gb due to redundant training data,
but it can be reduced to 3.6gb without any loss of quality, reducing ram usage and loading time drastically
(The original model is not lost, a new pruned copy is made)
- Download https://github.com/harubaru/waifu-diffusion/blob/main/scripts/prune.py
- Place it in your main
- Edit the last line in prune.py to the name of your waifu-diffusion ckpt:
python prune.pyin cmd from your main folder,
You will now have a pruned .ckpt
-----Changing UI Defaults-----
After running once, a
ui-config.json file appears in the webui directory:
Edit values to your liking and the next time you launch the program they will be applied.
-----Running Online or through LAN-----
Edit webui-user.bat and add the necessary parameters after
COMMANDLINE_ARGS=, along with any existing parameters you have
--shareoption to run online. You will get a xxx.app.gradio link. This is the intended way to use the program in collabs.
--listento make the server listen to network connections. This will allow computers on your local network to access the UI, and if you configure port forwarding, also computers on the internet.
--port xxxxto make the server listen on a specific port,
xxxxbeing the wanted port. Remember that all ports below 1024 needs root/admin rights, for this reason it is advised to use a port above 1024. Defaults to port 7860 if available.
--share --gradio-auth username:passwordto add shared authentication
Optionally, you can provide multiple sets of usernames and passwords separated by commas (user1:pw1, user2:pw2).
Note: This only applies to those who used
git clone to install the repo, and not those who used the .zip
You can set your script to automatically update by editing
git pull one line above
-----Setting Different Output Location-----
-Copy the text Here and save it as
output.bat, Move it to wherever you want your images to output to.
Run it, and it will create the appropriate sub-folders. You can delete the .bat after this is complete.
-Go to the Settings tab of the UI and assign your new file locations accordingly. Once you’ve assigned the locations, make sure to hit Apply Settings
It is also recommended to enable the following setting if you want your outputs to be organized
-[x] When writing images/grids, create a directory with name derived from the prompt
GFPGAN is used for correcting realistic faces, it was replaced with CodeFormer face correction which comes with the main install and is generally better.
To install GFPGAN, download and place GFPGANv1.3.pth into the main webUI directory
-----Enabling Negative Prompts-----
Negative prompts are a powerful tool to remove unwanted features and elements from your generations
They should be enabled by default, but if not:
- Edit webui-user.bat
--show-negative-promptto your launch parameters:
RUNNING ON WINDOWS 7/CONDA
(You can also try this method if the traditional install isn't working)
Windows 7 does not allow for directly installing the version of Python recommended in this guide on it's own.
However, it does allow for installing the latest versions of Python within Conda:
- Follow Steps 1-4 on the main guide
- Download Miniconda HERE. Download Miniconda 3
- Install Miniconda in the default location. Install for all users.
Uncheck "Register Miniconda as the system Python 3.9" unless you want to
- Open Anaconda Prompt (miniconda3)
- In Miniconda, navigate to the
/stable-diffusion-webuifolder wherever you downloaded using "cd" to jump folders.
(Or just type "cd" followed by a space, and then drag the folder into the Anaconda prompt.)
- Type the following commands to make an environment and install the necessary dependencies:
conda create --name qwe
(You can name it whatever you want instead of qwe)
conda activate qwe
conda install python
conda install git
(Note: it may seem like it's stuck on "Installing torch" in the beginning. This is normal and should take 10-15 minutes)
It should now be ready to use
- NOTE: On Windows 7, you may get "api-ms-win-core-path-l1-1-0.dll is missing" in Conda.
This is because new versions of Python and programs that rely on Python (Like Blender, etc.) require a system file only present in newer versions of Windows
Luckily, it has been backported to be compatible with W7, and can be downloaded HERE (Github page)
Upzip and copy the x86 .dll into
C:\Windows\SysWOW64and the x64 .dll into
C:\Windows\System32and reboot, then Python should install successfully
- Navigate to
conda activate qwe
(You will need to type 'conda activate qwe' every time you wish to run webui)
- After loading the model it should give you a LAN address such as '127.0.0.1:7860'
Enter the address into your browser to enter the GUI environment
The original v1.3 leaked model from June can be downloaded here:
Backup Download: https://download1980.mediafire.com/3nu6nlhy92ag/wnlyj8vikn2kpzn/sd-v1-3-full-ema.ckpt
Torrent Magnet: https://rentry.co/6gocs
The original hlky guide (replaced as of 9/8/22) is here: https://rentry.org/GUItard
Japanese hlky guide https://news.livedoor.com/article/detail/22794512/
The original guide (replaced as of 8/25/22) is here: https://rentry.org/kretard
APPROXIMADE RENDER TIME BY GPU (50 steps)