airunner
automatic
Our great sponsors
airunner | automatic | |
---|---|---|
25 | 185 | |
192 | 4,717 | |
13.0% | - | |
9.9 | 9.9 | |
2 days ago | 2 days ago | |
Python | Python | |
GNU General Public License v3.0 only | GNU Affero General Public License v3.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
airunner
-
Show HN: Talk to an LLM (and interrupt it) with your voice [video]
AI Runner is an application that I have been developing for over a year. This next iteration is a near total rewrite and adds lots of new features - what started out as an AI Art application has evolved into a multi-modal AI assistant built with pure python. It runs locally and offline on your own hardware (I recommend using an RTX 2080s or higher).
You can get the source here: https://github.com/Capsize-Games/airunner/
-
AI Runner: real time voice to text conversation with PC preview [video]
Hi all, I've been working on this application for quite some time. It started out as a Stable Diffusion art app, and is now transitioning into a full featured AI assistant of sorts.
The video features me talking to the computer using my headphones. It records my speech, translates bytes to text, passes that to the LLM which generates text, and then uses another model for text to speech.
The video also shows me asking for an image at which point the LLM generates a prompt. Stable Diffusion is loaded and the prompt is passed to SD to generate the image.
The models I'm using:
- TTS: SpeechT5
- LLM: Mistral 7b
- Stable Diffusion: Turbo
- STT: whisper-tiny
- Vision: various, still in development
As I mentioned there at the end, vision is still in development. I have a working prototype in which images are taken every second, translated into text and then passed to my chat prompt. It works OK but is often wrong.
The project is open source under GPL-3, written with Python using PyQT6. You can find it here:
https://github.com/Capsize-Games/airunner
The compiled stable version is available for download on itch, but only includes image generation capabilities, everything else is in the unreleased 3.0.0 version
https://capsizegames.itch.io/ai-runner
-
Show HN: AI RUNNER – LLMs and Stable Diffusion on local hardware
I am the creator of AI Runner, an application that allows you to run Stable Diffusion and LLMs locally on your own hardware. It is built with pure python using PyQT6, Huggingface and many more libraries. The goal is to create a local AI Assistant that can run on local hardware.
Although the current compiled production version 2.2.0 is limited to Stable Diffusion, I have added LLM support and much more to the upcoming v3.0.0.
With it you can run chatbots, connect your camera and microphone to pull images and text for use with the chat bot (a work in progress) and much more.
I test heavily using a 2080s. Version 2.2.0 has also been tested with a 1080GTX and also runs on the CPU (albeit very slowly).
I'm using agents and tools for the bot as well, so you can make it do things like RAG, control the application, launch apps on your computer, generate prompts for stable diffusion and much more.
Additionally I have added text to speech (there are currently two options with various settings to choose from, SpeechT5 and Bark).
AI Runner is GPL 3.0 and uses pyinstaller to create a compiled version for Windows and Ubuntu, available here https://capsizegames.itch.io/ai-runner
Version 3.0.0 is still under development. I hope to launch within the next month or so, but if you'd like to get a pre-release preview you can install the latest version from master.
This is a passion project of mine that I've been working on since 2022. The upcoming version has been in development for around 7 months and during that time I got Covid and the flu which slowed me down by a little over a month.
If you have questions please don't hesitate to ask.
- I have a distributed app with active users, how can I become profitable?
-
AI Runner now with Kandinsky
Hi, I am the creator of AI Runner - a GUI that allows you to run Stable Diffusion and Kandinsky locally from your own hardware without installing any additional libraries. It is a compiled open source application. Its currently 50% off during the itch.io summer sale (or free if you want to install the requirements from source - see link at the end of this post for more info)
-
Controlnet v1.1 Lineart
I created a lowcost opensource no-install stable diffusion / kandinsky app called AI Runner that you might be interested in checking out https://capsizegames.itch.io/ai-runner
-
Help
Bummer tho bud, sorry we couldn't get you up and running but good luck and don't give up yet lol, there are plenty of other UIs you can try out :D That reminds me, there's this one I tried a bit ago that someone on here released, it was easy to set up and would probably work for you.
-
Portable windows install/app for stable diffusion with GUI (or WebGUI)
AI Runner
- AI Runner vs automatic1111 webui
-
AI Runner v1.10.2: Extensions, LoRA and ControlNet v.1.1
As always, this is a work in progress. If you run into bugs, feel free to DM or join my Discord server or file a report on github
automatic
-
Open-source project ZLUDA lets CUDA apps run on AMD GPUs
> it won't ever be a viable option
For production workloads, I generally agree. It's an unsupported hack with a questionable future, I wouldn't do anything money-making with it.
However, for tinkering and consumer workloads, it already works pretty well. Enough of cuDNN and cuBLAS work to run PyTorch and in turn, Stable Diffusion with https://github.com/lshqqytiger/ZLUDA - there's even a fairly user-friendly setup process already in https://github.com/vladmandic/automatic .
I was able to get a personal non-ML related project working on my AMD card in just a few minutes, which saved me a lot of development time before I then deployed the production workload on NV hardware (this is probably why AMD pulled the plug on the project - it's almost more of a boost to NV than anything else, AMD really need people to be writing code on ROCm to deploy on AMD datacenter hardware).
-
Show HN: Comflowy – A ComfyUI Tutorial for Beginners
While I currently use SD.Next[1], I have tested ComfyUI locally with my AMD card. The UI can be daunting, but you learn quite a great deal about how a Stable Diffusion pipeline works. In addition some innovations and advances find their way into ComfyUI first.
[1] https://github.com/vladmandic/automatic
-
Just me or SDXL is bad for rendering trees, grasses, vegetation in general ? Looks a stop motion or unfinished painting. How can I fix it ?
I used SD.NEXT ( https://github.com/vladmandic/automatic ) and https://civitai.com/models/82098/add-more-details-detail-enhancer-tweaker-lora and epicphotogasm_lastUnicorn
-
Is SDXL supposed to be this slow on my system?
I found this thread on GitHub talking about how this was fixed in the latest version with an optional setting. I tried enabling it, as they mentioned, but it just resulted in an immediate CUDA out of memory error when starting generation. So it seems I'm actually needing the shared memory, which I assume is my issue.
-
Another Monday, another big release from SDNext!
As always, do check out our more detailed changelog, give us a quick install from our Repo, and stop by our Discord Server for any questions or help you may need.
-
What's the best stable diffusion client for base m1 MacBook air?
SD.Next
- Intel Arc 770 with Linux Mint, support requested!
-
SDNext - Controlnet keeps being disabled after installing SDXL ?
Today I finally wanted to give SDXL a chance, so I set everythin up according to Vladmandic's Wiki https://github.com/vladmandic/automatic/wiki/SD-XL
-
Vlad SD.Next SDXL DirectML: 'StableDiffusionXLPipeline' object has no attribute 'alphas_cumprod'
I'm trying to get SDXL working on Vlad's SDNext, but I keep getting the error in the title when trying to run basic operations. I'm not sure what's going on, I followed his guide for it to a T.
-
[P] Stable Diffusion XL (SDXL) Benchmark - 769 images per dollar on consumer GPUs
We used an inference container based on SDNext, along with a custom worker written in Typescript that implemented the job processing pipeline. The worker used HTTP to communicate with both the SDNext container and with our batch framework.
What are some alternatives?
aihandler - A simple engine to help run diffusers and transformers models
SHARK - SHARK - High Performance Machine Learning Distribution
stable_diffusion_sketch - Stable Diffusion Sketch, an Android client app that connect to your own automatic1111's Stable Diffusion Web UI
stable-diffusion-webui-colab - stable diffusion webui colab
StableDiffusion-Windows-GUI
kohya_ss
chatai - Official Repo for Chat AI
InvokeAI - InvokeAI is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, supports terminal use through a CLI, and serves as the foundation for multiple commercial products.
Stable-Diffusion-Video2Video - Small script for AUTOMATIC1111/stable-diffusion-webui to run video through img2img.
stable-diffusion-webui-ux - Stable Diffusion web UI UX
Magnetic_Drawing_Board - Digital version of the beloved Magnetic Drawing Board
stable-diffusion-webui-wd14-tagger - Labeling extension for Automatic1111's Web UI