QR Monster Illusion Diffusion - Turn anything into AI art

No video

QR Monster Illusion Diffusion - Turn anything into AI art - Six QR Code Controlnet Models

Рет қаралды 8,435

Ai Voice Tutor

Күн бұрын

Пікірлер: 18

@WolfHunter502 10 ай бұрын

The “Thank you for watching” at the outro🔥

@AiVOICETUTOR 10 ай бұрын

Glad you like it 🙏

@ParanoidAmerican 11 ай бұрын

Subbed. This is the video I needed to save hours of research.

@AiVOICETUTOR 11 ай бұрын

Awesome! Glad it was helpful to you

@theaieyee 11 ай бұрын

Absolute quality bro 👍

@AiVOICETUTOR 11 ай бұрын

Thanks bro, glad you like it

@vaishnav7 11 ай бұрын

Nice work bro👍

@AiVOICETUTOR 11 ай бұрын

Thanks man 🙏

@enesnesnese 11 ай бұрын

Thanks mate.

@AiVOICETUTOR 11 ай бұрын

You're welcome!

@zephirix9141 11 ай бұрын

Its not blending my provided image into the prompt, for example If I give image of a face and give prompt to have a forest. it just gives 2 images where one is the forest and 2nd is inverted image of what I provided

@AiVOICETUTOR 11 ай бұрын

Make sure you use the same settings as in the video (especially hires fix) and set the control weight to 2

@zephirix9141 11 ай бұрын

@@AiVOICETUTOR got it, ty, should you use refiner?

@AiVOICETUTOR 11 ай бұрын

Nope you only need the refiner for using SDXL

@gregorysayegh 8 ай бұрын

awesome! would that work on a mac too ? and is it for free?

@AiVOICETUTOR 8 ай бұрын

Yeah in theory everything should work on a Mac but no guarantees. You can install Stable Diffusion Web UI easily via Pinokio (kzfaq.info/get/bejne/otRhpKiY0dTUfaM.html) which is available on Mac. And everything is free.

@jurandfantom 11 ай бұрын

thank you for your video :) I hear that you use your own voice. Anything changed since Free AI Text-To-Speech Voice Cloning - TTS With Any Voice! - Easy AI Voice Cloning - TorToiSe TTS ?

@AiVOICETUTOR 11 ай бұрын

Thanks for watching! I'm using RVC V2 to clone my own voice: kzfaq.info/get/bejne/a8-Pg9yolc2sXYE.html. From what I can tell, the method in the video you referenced is still the best free way to create a TTS model from any voice.