Movatterモバイル変換


[0]ホーム

URL:


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

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

A downloadable tool

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

Customizable chatbots run with Mistral-7b, allowing you to have real-time text-to-speech / speech-to-text conversations. You can set unique system instructions, bot names, and even personalities. The bots will change their mood based on the context of your conversations.

img_1.png


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.


CategoryFeatures
Image GenerationGenerate images using Stable Diffusion 1.5, SDXL 1.0 and SDXL Turbo models
Flexible prompts and weighting
LoRA and Textual Inversion / Embeddings
Support forsafetensors andckpt 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 PerformanceEasy 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
ChatbotCustomizable chatbots with personalities, names and moods
Store and revisit your past conversations
Generate images using the chatbot or take full control of your prompts.
ArchitectureTorch 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

OSUbuntu 20.04
ProcessorRyzen 2700K or Intel Core i7-8700K
Memory16 GB RAM
GraphicsNVIDIA RTX 3060 or better
NetworkBroadband (used to download models)
Storage36 GB available space

Recommended

OSUbuntu 22.04
ProcessorRyzen 5800X or Intel Core i7-11700K
Memory32 GB RAM
GraphicsNVIDIA RTX 4090 or better
NetworkBroadband (used to download models)
Storage50 GB available space

Development log

View all posts

itch.io·View all by Capsize Games·Report·Embed
ToolsFree

[8]ページ先頭

©2009-2025 Movatter.jp