Seait Versions Save

Added:

• LoRA_Easy_Training_Scripts

Fixed:

• InvokeAI installation

Fixed bark gui installation ModuleNotFoundError: No module named 'pytorch_seed'

Added:

• AudioLDM2

  This my fork and the 10 sec limit removed and increased to 50 sec, depends on GPU. about 16GB, VRAM requirements might be reduced. Original project: https://github.com/haoheliu/audioldm2 Also added 2 other models:

  • audioldm2-full-large-650k
  • audioldm2-music-665k

Change:

• Minor UI fixes.

SEAIT 0.1.4.5 Dev Build available for public download https://www.patreon.com/distyx

This version hasn't been released here because it contains some significant changes that could disrupt functionality. It's still under development and might not yet provide best user experience.

I've had a bit of a strange month due to some personal circumstances and recently, updates have slowed down due to a temporary issue with hardware access. However, this issue is on its way to being resolved, and I will get back on track and resume frequent updates. This change will also open the door to integrating more advanced features into the SEAIT.

If you like what I'm doing and wish to assist, you can do so at https://www.patreon.com/distyx Your support will contribute to improving and accelerating the development, and enhance the Super Easy AI Installer Tool (SEAIT) to be better and more efficient. This will help you access to the latest and best open-source projects with the fewest possible clicks.

As always, SEAIT will be available for public download, with major versions continually being released here. However, I'll initially release minor versions featuring new or experimental functionalities on Patreon. Don't worry if you can't contribute right now - after a while, these minor versions will also be available to the public on Patreon. Rest assured, these minor versions will be incorporated into the major versions, which will always be available to the public.

For more info about SEAIT 0.1.4.5 https://www.patreon.com/distyx

UPCOMING: A series of video tutorials on how to correctly set up and use SEAIT. Improved Projects layout with categories Improved Project layout with more custom settings Additional tools in the toolbox Projects will update remotely, eliminating the need to wait for the app to update. Ability to add custom projects.

I'm also planning to release two of my older projects:

An interface for SimSwap that allows for face swapping images and videos, among other features.

An video editor that utilizes Google's MediaPipe. This project can segment videos based on person detection, face presence, or face angle. It helps extract scenes with humans, scenes without humans, scenes without a face, scenes with a face, and faces at specific angles. Additionally, it allows you to stitch these segments back together. Please note, these older projects will require updates before release, which will take some time. Expect video demos within the week.

There's a lot on the plate. Let's go!

Update [0.1.4]

To create a symbolic link using the symlink tool, you need to run the 'RunAsAdministratorSymlink_seait.bat' file as an administrator:

1. Right-click on the 'RunAsAdministratorSymlink_seait.bat' file.
2. Select 'Run as Administrator' from the context menu.
3. Click 'Yes' when prompted by User Account Control.

This will grant the necessary permissions for creating symbolic links using the symlink tool.

For regular usage of seait.exe, you don't need to perform these steps. Simply start seait.exe as you normally would. @asashledombos thank you for the script.

Added

bark-gui and openai whisper-ui both tested on GTX 970 4GB and worked great.

• bark-gui [text-to-speech and voice cloning]

  https://github.com/suno-ai/bark

  Bark is a transformer-based text-to-audio model created by Suno. Bark can generate highly realistic, multilingual speech as well as other audio - including music, background noise and simple sound effects. The model can also produce nonverbal communications like laughing, sighing and crying. To support the research community, we are providing access to pretrained model checkpoints ready for inference.

  https://github.com/C0untFloyd/bark-gui

  bark-gui is This is a simple Web UI for an extended Bark Version using Gradio, meant to be run locally.

• whisper-ui [speech-to-text]

  https://github.com/openai/whisper

  Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multitasking model that can perform multilingual speech recognition, speech translation, and language identification.

  A bit old maybe there new GUIs for whisper but i used this one.

  https://github.com/hayabhay/whisper-ui

  whisper-ui is a simple Streamlit UI for OpenAI's Whisper speech-to-text model. It let's you download and transcribe media from YouTube videos, playlists, or local files. You can then browse, filter, and search through your saved audio files.

  I have also have an old fork of this project with some differences that let chose gpu or cpu but its older then this one i might added later if requested.

Minor fixes and changes to the code.

Added

• Toolbox tab

• Under toolbox tab, added symlink link creator

  • Out of space? No problem, now you can put all your models in one directory and create symbolic links to them. you can do this for any directory you want including virtual environments if you want it too.

• Symlink Tool - a tool that creates symbolic links.

• Models Treasury - a centralized folder for all the popular model directories. Simply assign to use on all your projects.

Video tutorial soon.

• Quick launch menu, Launch projects even faster.
• Arguments for text-generation-webui , try it out.
• 2 other old projects of mine.
  • Safe-and-Stable-Ckpt2Safetensors-Conversion-Tool-GUI
  • Stable-Diffusion-Pickle-Scanner-GUI

Added

• Your Creation some social fun.
• A Kandinsky web user interface for https://github.com/ai-forever/Kandinsky-2, requires more than a 8GB VRAM GPU.

Changed

• Python detection improved.
• Minor bug fixes.

0.1.0

Added

• Argument Saving: Users can now save their preferred arguments.
• xformers Arguments Default: The xformers argument is now set to "automatic 1111 webui" by default. it will install xformers by default unless unchecked.
• Project Stable Diffusion web UI-UX (A1111 fork): Stable Diffusion web UI-UX project. Beautiful user interface and a more intuitive making it easier to navigate and interact with the project.

Fixed

• InvokeAI Launch Issue: Previously, there was an issue causing InvokeAI to not launch correctly. NOTE: For now please make sure you only launch with "--web" argument after install, will be improved later.

• Update Checker Bug: A problem with the update checker resulted in incorrect update notifications.

Added automatic - Auto1111 webui fork Added lama-cleaner Updated Auto-GPT to load the correct file

Update 0.0.8

Added custom project path

Modified Python detection

And more

Custom project path:

• Now you can install and launch existing installations from any drive or location, as well as perform other actions
• Please note, avoid using paths with spaces

Modified Python detection:

• Python will now detect system environment PATH