AaronGTV's AI Toolkit
Hey there! I wanted to share with you some of my favorite tools that have been incredibly helpful in my endeavors. While I won't claim they're the definitive best, there are some truly awesome resources here that I believe will give you a fantastic head start. Whether you're exploring language models, text-to-image synthesis, or engaging with AI-powered characters, these tools have proven to be invaluable. So, without further ado, let me introduce you to some remarkable options that can greatly enhance your projects.
If your looking to make your computer talk
Try AaronGPTfast our very own chat bot through Poe.com at:
Step 1.
Hear Poe AI's response in a natural voice: on
Add listen button to messages: on
Now, here are the basics:
This is what I have been working with.
OpenAI account: https://openai.com/ (log in with Google Chrome browser)
ChatGPT 3.0 (is free): https://chat.openai.com/ (online language model that is free to use)
Talk-To-ChatGPT: Chrome Extension that allows you to talk to ChatGPT for free.
Google Bard (Google's AI): https://bard.google.com/
Voice Control For BARD: Chrome Extension for voice control. https://chrome.google.com/webstore/detail/voice-control-for-bard/ameajnciachbdcneinbgnehihjolepkd
NEW POE.com/Sage another option that let's you try different Chatbots and create your own.
https://poe.com/Sage
Llama CPP: https://github.com/ggerganov/llama.cpp - A free and open-source C/C++ port of Facebook's LLaMA model. It is smaller and more performant than other large language models, making it a good option for those who don't have access to large amounts of data to train their own models.
GPT4All: https://gpt4all.io/index.html is an ecosystem to train and deploy powerful and customized large language models that run locally on consumer grade CPUs.
Tavern AI: https://tavernai.net/ - A web application that allows users to create and interact with AI-powered characters. It is designed for realistic and engaging role-playing using large language models like GPT-3.
Ooga booga web UI: https://github.com/oobabooga/text-generation-webui - A simple, text-based web interface often used for development and testing purposes. It provides a quick and easy way to create UIs for generating text.
Large Language Models:
Vicunia models: I like the 13b and 7b models (Uncensored). The repositories come and go, and it can be challenging to keep track of everything.
Tutorials by the YouTuber "Aitrepreneur": https://www.youtube.com/@Aitrepreneur
TiffInTech https://www.youtube.com/@TiffInTech
martin-thissen https://www.youtube.com/@martin-thissen
PrivatGPT: https://github.com/imartinez/privateGPT - A project I have been working on that allows you to chat with your documents using AI. Check out the video for more information.
Text-to-image synthesis
Stable Diffusion: https://stablediffusionweb.com/
Or install it locally here: https://github.com/AUTOMATIC1111/stable-diffusion-webui I have been running a version of "Stable Diffusion" (mine is called Easy Diffusion, lol). Here are the installation links for different operating systems:
Hardware requirements:
- Windows: NVIDIA graphics card (minimum 2 GB RAM), or run on your CPU.
- Linux: NVIDIA or AMD graphics card (minimum 2 GB RAM), or run on your CPU.
- Mac: M1 or M2, or run on your CPU.
- Minimum 8 GB of system RAM.
- At least 25 GB of space on the hard disk.
Mid Journey: https://www.midjourney.com/ - A freeish Text-to-Image tool that works on Discord [https://discord.com/]. Discord is a complex chat tool that works like a messaging app and Twitter all in one.
BlueWillow: https://www.bluewillow.ai/ - Another free tool for text-to-image synthesis that offers faster processing.
These tools work based on prompts, and crafting effective prompts is an art form in itself. You can even have AI help you generate prompts for them, which adds an interesting twist to the creative process!
Random tools worth mentioning
Ivona Minireader: allows you to easily select large bodies of text, and it will read out loud
VoiceGPT: https://voicegpt.net/ allows you to talk to chatgpt on your android device (sorry iphone users B)>+
Enable dictation in your operating system: hit windows + h to enable dictation. And on a MAC i have set up to hit the function key twice to enable dictation.
4K Video Downloader: dues what it says (well for now, who knows really lol) https://www.4kdownload.com/products/videodownloaderandroid-37
music Tools
- Magenta Studio Magenta Studio is a collection of music plugins built on Magenta’s open source tools and models. They use cutting-edge machine learning techniques for music generation. https://magenta.tensorflow.org/studio
Spleeter Gui
Lastly: SILERO SPEECH-TO-TEXT MODELS! If you know how to utilize them then please show me lol cause i’m sick of elevenlabs lol https://silero.ai/
Remember, the world of AI tools and resources is constantly evolving, so it's always a good idea to explore and stay updated. I hope these recommendations provide you with a solid foundation to dive into your projects. Happy exploring and creating!
(Note: Please make sure to visit the provided links for detailed information, installation instructions, and any updates related to the tools mentioned.)
If you like these tools please let us know in the comments below.
Like and follow us on social media, and if you’re a cool person then rach out to us, we should probably work together!
~AaronGTV B)>+
(Miss Me Terribly)
Comments
Post a Comment