Unlock Uncensored AI Adventures: Install TextGen WebUI Locally in 1 Click

To install the TextGen AI WebUI locally in just 1 click, follow these steps:

1. Visit my Patreon page (link in the description) and become a supporter.
2. Download the 1-click installer file provided for Patreon supporters.
3. Double-click the installer file to run it.
4. Choose "Start Windows Installation" and let the installer do its job.

That's it! The installer will automatically download and set up everything you need to run the TextGen AI WebUI on your local computer. No complicated manual steps required.

Once the installation is complete, you can launch the WebUI and start exploring the various AI text models available, including uncensored and multi-modal capabilities. Enjoy your newfound freedom to experiment with AI without restrictions!

To manually install the Whisper-based text generation web UI, follow these steps:

1. Download and install Git for Windows by clicking the link in the description and downloading the 64-bit G for Windows setup.
2. Uncheck the box and click "Finish" after the installation is complete.
3. Click the second link in the description to go to the repository page. Click on "Code" and copy the entire line.
4. Create a new folder on your computer (e.g., "ubaba") and avoid using spaces in the name.
5. Open the command prompt by navigating to the folder path, typing "CMD", and pressing Enter.
6. In the command prompt, type "git clone" and then press Ctrl+V to paste the copied line. Press Enter to clone the repository onto your computer.
7. Inside the newly created "text generation webui" folder, the only two files you need to know are "start_windows.bat" and "update_windows.bat". The first file is used to run the installation and launch the web UI, while the second file is for updating the software.
8. Double-click the "start_windows.bat" file, which will download and install all the necessary files.
9. When prompted, select the appropriate GPU option (Nvidia, AMD, Apple M series, Intel Arc, or no GPU) and press Enter.
10. If you have a newer GPU, choose "n" when asked about using CUDA 11.8 instead of 12.1.
11. After a few minutes, the installation will be complete, and you will be provided with a local URL. Press Ctrl+Click on the URL to open the web UI.

Now that the interface is set up, you can proceed to download and load the desired AI text models to start using the uncensored capabilities of the Whisper-based text generation web UI.

To download and run AI models using the Uabat Text Generation Web UI, follow these steps:

1. Click on the "Model" tab in the web UI. This will display the available models you can download.
2. Use the Hugging Face website to find the AI model you want to use. The user code of the block has a large list of models available for download.
3. Determine the appropriate model format based on your hardware:
   • If you have a GPU, download the "awq" model format.
   • If you don't have a GPU and want to use your CPU, download the "ggf" model format.
4. Copy the model name and paste it into the "Download Model or Load" field in the web UI.
5. Click the "Download" button to download the selected model.
6. Once the download is complete, click the "Refresh" button to see the model in the list.
7. Select the downloaded model and click "Load" to load it into the web UI.

Now you can start using the loaded AI model for various tasks, such as chatting with virtual characters or analyzing images.

One of the coolest things you can do with the Ubisoft Text Generation Web UI is chat with virtual characters that have their own unique personalities. This allows you to engage in conversations with characters that respond in their own distinct voice and manner, rather than just a generic AI assistant.

To do this, simply click on the "Character Gallery" section of the web UI. Here you'll find a variety of pre-made characters to choose from, each with their own background, interests, and way of communicating.

For example, you can start a conversation with "Chiharu Yamada", who describes herself as having an "obsession with computers" and enjoying reading fantasy novels. Or you can create your own custom character, like "Sandra the Loving Girlfriend", and have natural conversations with her as if she were a real person.

The characters will respond to your messages with appropriate dialogue, and you can even use your microphone to speak to them directly. The web UI will then convert your speech to text and generate an audio response from the character.

This allows for a much more immersive and personalized experience compared to a typical chatbot. You can really let your imagination run wild, engaging in all kinds of conversations and scenarios with these virtual companions.

So dive in, choose a character, and see where the conversation takes you! The possibilities for creative and entertaining exchanges are endless.

To enable text-to-speech and speech-to-text functionality in the Webui, follow these steps:

1. Click on the "Session" tab and then enable the following extensions:
   • 11 Labs
   • Whisper
   • Srow
2. Click on "Apply Flags & Extensions" and then restart the Webui.
3. In the 11 Labs section, enter your 11 Labs API key to enable high-quality text-to-speech.
4. Choose a voice, such as "Charlotte", and enable "Play text-to-speech automatically".
5. In the Whisper section, click on "Record from microphone" to enable speech-to-text conversion.
6. When you start a new conversation, the character will respond with audio, and you can reply using your microphone.

If you want to use a free text-to-speech option, you can use the Srow extension instead of 11 Labs. Select a voice, enable "Play text-to-speech automatically", and deactivate the 11 Labs extension.

To upload your own custom character, click on the "Parameters" tab, then "Upload Character". Provide a JSON file and a profile picture, and the new character will be available for you to use.

To use the web UI for image analysis and conversation, you first need to download a specialized model called Lava. The Lava 13B model is a 13 billion parameter multimodal AI that can perceive and analyze images.

After downloading the Lava 13B model and loading it into the web UI, you need to enable the "Multimodel" extension. This will allow you to use the "Instruct" mode, which provides a special template for image-based conversations.

To analyze an image, simply drag and drop it into the "Send the picture" field. Then, you can ask questions about the image, and the AI will generate a response describing what it sees and any interesting observations.

For example, if you upload an image of a monkey wearing sunglasses and a pink jacket, you could ask "What is funny about this image?". The AI would then analyze the image and provide a response describing the humorous, humanlike appearance of the monkey.

This image analysis capability, while not as advanced as DALL-E or ChatGPT Vision, still provides a fun and interesting way to interact with multimodal AI models. It allows you to have conversations about images, just like you can with text-based prompts.

Thanks for tuning in to today's video! If you enjoyed it, please give it a thumbs up and subscribe to my channel if you haven't already.

I hope you found the information on how to install and use the Ubisoft Text Generation Web UI helpful. This tool provides a great way to explore uncensored large language models and have fun with interactive conversations.

Remember, if you have any issues with the installation, I offer a one-click installer and technical support on my Patreon page. Feel free to reach out if you need any assistance.

Once again, thank you so much for watching. I'll see you in the next video! Bye-bye.