AI Runner with Stable Diffusion | AI Art Editor and Custom Chatbots

Create AI Art and run custom chatbots on your own hardware

With AI Runner you are able to run Stable Diffusion, Kandinsky and other diffusion AI models on your own computer without any technical knowledge. Just download the app,

Canvas with collapsible panels

The canvas allows you to outpaint images to any size and collapsible panels make it easy to view your work on a clean interface as you do so.

pair it with your favorite model and run. 

---

Customizable Chatbot

---

Drawing tools

A simple but growing set of art tools paired with image-to-image allow you to convert sketches into works of art.

---

Image filters

Modify your creations with image filters, such as the pixel art filter and film filter to give them a unique look and feel.

---

Customizable

Choose custom paths to store your models, embedding, LoRAs, images, videos and gifs. Tweak memory settings and more.

---

Easy prompt storage

Save your favorite prompts, edit and reload them with the prompt browser.

---

Features

Please note that AI Runner is under active ongoing development. We work quickly to triage and fix any and all reported bugs. Certain features, such as real-time text-to-speech conversations with the Chatbot are prone to error.

You must download your own Stable Diffusion models in order to use the AI art features.

---

Category	Features
Image Generation	Generate images using Stable Diffusion 1.5, SDXL 1.0 and SDXL Turbo models
	Flexible prompts and weighting
	LoRA and Textual Inversion / Embeddings
	Support for safetensors and ckpt models
	Customizable metadata export options
	Optional automatic image export
	Control grid size, line width, and color
	Drawing tools for transforming sketches into art
	Outpainting for creating large-scale artwork
	Image filters for creative effects
	NSFW filter toggle
	Stored sessions - all of your settings and prompts for each section are stored and automatically loaded between sessions.
Usability and Performance	Easy setup and installation
	Fast image generation with GPU acceleration**
	CPU image generation†
	Memory preferences for optimized GPU RAM usage
	Fast load time and responsive interface
Chatbot	Customizable chatbots with personalities, names and moods
	Store and revisit your past conversations
	Generate images using the chatbot or take full control of your prompts.
Architecture	Torch 2 and memory enhancement settings
	Model downloader to get up and running quickly
* After running the program, you will need to download the stable diffusion models. This requires an active internet connection. Optional copy+paste requires xclip on Linux.
** Image generation results are dependent on hardware.
† CPU support is limited, and we do not recommend running AI Runner without a CUDA capable GPU.

Note: You must provide your own Stable Diffusion models

---

Memory options

Accelerated Transformers

Attention Slicing

Channels last memory

Sequential CPU offload

Model CPU offload

TF32

Vae slicing

Tile vae

---

System Requirements

Minimum

OS	Ubuntu 20.04
Processor	Ryzen 2700K or Intel Core i7-8700K
Memory	16 GB RAM
Graphics	NVIDIA RTX 3060 or better
Network	Broadband (used to download models)
Storage	36 GB available space

Recommended

OS	Ubuntu 22.04
Processor	Ryzen 5800X or Intel Core i7-11700K
Memory	32 GB RAM
Graphics	NVIDIA RTX 4090 or better
Network	Broadband (used to download models)
Storage	50 GB available space

---