●
Stable Diffusion is starting..
or
Add default negative prompt
Add img2img source image using the Browse button, via drag & drop from external file or browser image (incl. rendered image) or by pasting an image from the clipboard using Ctrl+V.

You may also reload the metadata embedded in a PNG, WEBP or JPEG image (enable embedding from the Settings).
Browse
Draw
Inpaint

➕ Image Settings Paste Image SettingsCopy Image Settings Reset Image Settings

Image Settings
Click to learn more about custom models
Click to learn more about ControlNets


Click to learn more about VAEs
Click to learn more about samplers
Swap width and height
Advanced sizes
Custom size:
×
Resize:

    
Recently used:








Common sizes:








Small image sizes can cause bad image quality
Click to learn more about Seamless Tiling
  • Render Settings
  • with
Type a prompt and press the "Make Image" button.

You can set an "Initial Image" if you want to guide the AI.

You can also add modifiers like "Realistic", "Pencil Sketch", "ArtStation" etc by browsing through the "Image Modifiers" section and selecting the desired modifiers.

Click "Image Settings" for additional settings like seed, image size, number of images to generate etc.

Enjoy! :)
 %
If you found this project useful and want to help keep it alive, please consider buying me a coffee to help cover the cost of development and maintenance! Thanks for your support!

System Settings

customize the look and feel of the ui
automatically saves images to the specified location
will be saved to disk in this format
Path to the 'models' folder. Please save and refresh the page after changing this.
blurs out NSFW images
plays a sound on task completion
reverse the normal processing order
Automatically extract lora tags like <lora:name:0.4> from the prompt, and apply the correct LoRA (if present)
starts the default browser on startup
Faster performance requires more GPU memory (VRAM)

Balanced: nearly as fast as High, much lower VRAM usage
High: fastest, maximum GPU memory usage
Low: slowest, recommended for GPUs with 3 to 4 GB memory
warning: this will be *very* slow
to process in parallel
restores settings on browser load
Actions that might lead to data loss must either be clicked with the shift key pressed, or confirmed in an 'Are you sure?' dialog
Name of the profile for model manager settings, e.g. thumbnails for embeddings. Use this to have different settings for different users.
Get the latest features immediately (but could be less stable). Please restart the program after changing this.
Use our new v3 engine, with additional features like LoRA, ControlNet, SDXL, Embeddings, Tiling and lots more! Please press Save, then restart the program after changing this.


Optional Packages

Faster image generation by converting your Stable Diffusion models to the NVIDIA TensorRT format. You can choose the models to convert. Download size: approximately 2 GB.

Early access version: support for LoRA is still under development.

Build Config:

Batch size range:

Build for resolutions:
512x512 to 768x768
768x768 to 1024x1024
1024x1024 to 1280x1280
1280x1280 to 1536x1536
1536x1536 to 1792x1792


Share Easy Diffusion

Other devices on your network can access this web page. Please restart the program after changing this.
Port that this server listens to. The '9000' part in 'http://localhost:9000'. Please restart the program after changing this.
Create a VPN tunnel to share your Easy Diffusion instance with your friends. This will generate a web server address on the public Internet for your Easy Diffusion instance.
This Easy Diffusion server is available on the Internet using the address:
Anyone knowing this address can access your server. The address of your server will change each time you share a session.
Uses Cloudflare services.


System Info

 

Help

Community

Download all images

Instead of downloading individual files, generate one zip file with all images
Place images into job folders
For each image, also download a JSON file with all the settings used to generate the image

Image Modifiers

(drawing style, camera, etc.)
Add Custom Modifiers
Expand Categories

Custom Modifiers

Set your custom modifiers (one per line)
Tip: You can include special characters like {} () [] and |. You can also put multiple comma-separated phrases in a single line, to make a single modifier that combines all of those.

Embeddings

Add embeddings to the prompt (click) or negative prompt (shift-click) Add embeddings to the negative prompt
 

Use as thumbnail

Use a pictures as thumbnail for embeddings, LORAs, etc.