![GRANDE AI](/img/default-banner.jpg)
- 11
- 21 792
GRANDE AI
เข้าร่วมเมื่อ 28 เม.ย. 2024
Welcome to GRANDE AI - your gateway to the world of artificial intelligence!
Kling AI vs Luma AI: Ultimate Prompt Battle! Which AI Video Generator is the Best?
Watch the ultimate showdown between Kling AI and Luma AI in this exciting prompt battle. We test and compare the capabilities of these top AI video generators to determine which one is the best.
Kling AI:
klingai.com/
Luma Dream Machine:
lumalabs.ai/dream-machine
How do I create my avatar? Check here:
th-cam.com/video/TqzDCuYlNRE/w-d-xo.html
#videoai #aivideocreation #aitools #imagetovideo #texttovideo
Kling AI:
klingai.com/
Luma Dream Machine:
lumalabs.ai/dream-machine
How do I create my avatar? Check here:
th-cam.com/video/TqzDCuYlNRE/w-d-xo.html
#videoai #aivideocreation #aitools #imagetovideo #texttovideo
มุมมอง: 352
วีดีโอ
New Local Text to Speech! CosyVoice Tutorial for Beginners
มุมมอง 2.8K14 วันที่ผ่านมา
Learn how to set up and use CosyVoice for local text to speech on your PC! This beginner tutorial will guide you through the process, enabling you to create unlimited TTS for FREE. Tutorial links: Pinokio: pinokio.computer/ CosyVoice ComfyUI: github.com/AIFSH/CosyVoice-ComfyUI CosyVoice Github: fun-audio-llm.github.io/ Tags: #texttospeech #voicecloning #aivoicegenerator #aivoice #aivoicecloning
New Text to Image Locally on Your PC! Free Midjourney Alternative | Kolors Tutorial
มุมมอง 4.4K21 วันที่ผ่านมา
Check out the free open-source text-to-image model that outperforms Midjourney and DALL-E! See stunning comparisons and learn why this AI tool is a game-changer for image generation. - Kolors tutorial. Official Kolors model: github.com/Kwai-Kolors/Kolors Tutorial links: Pinokio: pinokio.computer/ Kolors ComfyUI: github.com/kijai/ComfyUI-KwaiKolorsWrapper VAE: huggingface.co/stabilityai/sdxl-vae...
How to Make Disney Pixar Animations Using AI -Tutorial
มุมมอง 2.7K21 วันที่ผ่านมา
Learn how AI can create Disney Pixar-style animations! Discover the tools and techniques for making stunning animated videos with artificial intelligence. Prompt: docs.google.com/document/d/1waE25l_avaYyAcyl0h4CipddXNJUrG-3qOGHHupsMaA/edit?usp=sharing Tags: #aianimation #aitools #aianimationtutorial #imagetovideo #animation #aitechnology
How to Create Animated Bible Stories Using AI
มุมมอง 65128 วันที่ผ่านมา
Create engaging biblical animated stories with AI. This video shows you how to use AI to bring your stories to life and monetize your content. Perfect for beginners and pros alike, we'll cover the tools and techniques you need to succeed. Tags: #aianimation #facelessyoutubechannel #aitools #animatedstories
I Found Free ElevenLabs Alternative: Unlimited Text-to-Speech with HQ Voices
มุมมอง 1Kหลายเดือนก่อน
Discover a free alternative to ElevenLabs for text-to-speech. Enjoy unlimited features and high-quality voices. Perfect for TH-cam creators, content makers, and anyone needing professional-sounding speech synthesis. #texttospeech #aivoice #texttospeechai #freetts
New Local TTS! Create Unlimited AI Voices with 1-Click for FREE!
มุมมอง 2.1Kหลายเดือนก่อน
Generate unlimited AI voices locally and for free with Pinokio, OpenVoice, and RVC. Links: Pinokio: pinokio.computer/ Voice models: voice-models.com/ Music: "Arthur Vyncke - The Uprising" is under a Creative Commons (BY-SA 3.0) license: creativecommons.org/licenses/... / arthurvost Music powered by BreakingCopyright: • 👷 Free Sci Fi Dystopia Music (For Vid... Tags: #aivoice #aivoicegenerator #t...
New Free Lipsync Tool: Make Anyone Say Anything
มุมมอง 507หลายเดือนก่อน
New incredible AI avatar tool that's taking the internet by storm! In this video, I showcase Character-1 from Hedra Labs, a revolutionary AI that creates lifelike human characters for your videos! Hedra: www.hedra.com/ Tags: #aiavatars #aiavatar #freeavatar #aivideocreation #aianimation #talkingphoto #imagetovideo #talkingavatar #lipsync
FREE Text to Speech on Your PC! 1-Minute Voice Cloning! SoVITS tutorial
มุมมอง 2.1Kหลายเดือนก่อน
Hey everyone! 👋 In today’s tutorial, I’ll show you how to clone any voice with just 1 minute of audio and generate unlimited text-to-speech completely free, locally, and without any limits! 🚀 Sovit Webui - Download here: rentry.co/GPT-SoVITS-guide#/ 📌 Step-by-Step Guide: Download Sovit Webui - Click the first link in the description and download the latest prezip version. Installation - Extract...
New FREE Text To Video AI Tool: Create Videos from Text with Luma AI's Dream Machine
มุมมอง 315หลายเดือนก่อน
Revolutionary AI tool, Luma AI's Dream Machine, that lets you create high-quality, realistic videos from simple text prompts and images. Enter your desired prompt, and generate stunning videos in just 2 minutes. Whether you're a content creator, marketer, or AI enthusiast, this tool is a game-changer. Link: lumalabs.ai/dream-machine tags: #imagetovideo #texttovideoaifree #texttovideo
New Text to Speech AI: Locally, FREE and Unlimited!
มุมมอง 5K3 หลายเดือนก่อน
New Text-to-Speech AI tool that you can use locally, for free, and without any limitations! Say goodbye to expensive TTS services and start generating unlimited, high-quality voices for your projects. In this video, we'll show you step-by-step how to use this amazing tool to create realistic AI voices effortlessly. Don't miss out - start creating amazing audio content today! Links: applio.org w...
a short video but with all required info, exactly what i needed. thanks
Can these videos be used for commercial purposes?
Hi, could you please specify which videos you mean? If you mean animations from Luma AI, you can use them for commercial purposes if you purchase the Standard plan. However, you cannot use them commercially if you're only using free credits from their website.
97.3% of your video was about how to create VOICES, not actually create a useful application to read text on our PC to us. It would be awesome if you would tell us how to do something truly useful, as in read text out displayed by an (any) application on our PC. Thanks in advance.
Make more videos like this
Thanks, I definitely will!
Congratulations for 500
Thanks a lot! Reaching 500 subscribers means the world to me. Your support is amazing!
thanks dude, helpful video :) one question tho, are there any other websites like weights with a big database of voices? Ik that there're models on huggingface, but maybe there's something else close to weights where I can find voices for commercial use?
@@SilentNyan Hi, check this bro voice-models.com/
@@Grandeai yoo tysm, you're the most helpful AI-related youtuber I've seen :D
@@SilentNyan I love your comment ❤
Sir, how can I make a video like yours?
To make a video like mine, try using CapCut or similar apps for editing. They’re pretty user-friendly!
Nice video
Glad you liked it! Thanks for the comment!
I really appreciate that. Waiting for more like that.
Thank you! I'm glad you enjoyed it.
Nice one
Thanks!
SIR can you please train this in colab
can i use it for commercial purpose?
Hi, yes, you can use it for commercial purposes.
@@Grandeai thanks for the response
there does seem to be something wrong with CosyVoice itself when it comes to the nodes- even when installing manually, cosyvoice does not work, just leaving this comment here for anyone else experiencing issues- you're not alone 👍
You can monetize with the background audio? It is polygon by Ben Elson
Hi, I have all the necessary licenses to use this track because I use Epidemic Sound.
I had to insatll a load audio node and then that worked. however the save audio node is red and is not listed in the comfy UI manager. No way to save the resulting audio file.
Thank you for doing all the research and work to benefit us.🥲
Unbelievable, this model do exactly what i prompted, and it can handle Hands. Gamechanger, i think.
hey i came across this error [When loading the graph, the following node types were not found: TextNode CosyVoiceNode ] any fixes ?
Hi, go to the custom nodes manager, type cosyvoice, and check if it is installed. If it says "restart required" next to it, restart ComfyUI and Pinokio. Remember to also refresh the browser window.
@@Grandeai ya it's all done still getting the error as in missing nodes
I checked now, and everything works for me. If you have any red windows, or missing nodes it means that cosyvoice is not installed in your ComfyUI, the browser window is not refreshed, or a restart is required. So that I can help you further, please send me links to two screenshots: one showing cosyvoice in custom nodes manager and the other showing your workflow and the error.
Thanks for deleting my comment because I pointed out their terms of service. 😂 Guys, you are not allowed to use it. Read their terms of service. Even though they say you can use it to make money, their terms of service say otherwise. They own everything you make with it, and you are not allowed to change or modify the output that you generate, which includes basically everything related to editing.
What I do. Error occurred when executing KolorsTextEncode: Allocation on device File "C:\Users\akash\Documents\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all)
Hi, This might be due to various reasons such as insufficient GPU memory,, ensure that your GPU has enough available memory to handle this.
Any suggestions for live TTS conversion? If I by example type a text and want to get the spoken word of this text in nearly real time?
Omigod, it means messing with Comfy? That stuff is nightmare fuel. I already have Pinokio but Comfy is just plain cancer, I hate it
I see that you've had bad experiences with ComfyUI. I get that it might not be for everyone. But really, it's just Python on steroids. Instead of messing with code, you connect windows with wires. I've been using ComfyUI for a few months now, and I'm really happy with it. It's super simple and easy to understand. Almost everything new in the AI world can be done with ComfyUI. I think it's worth giving it another try, it really might be more user-friendly than it first seems. Thanks for your comment, and best regards.
@@Grandeai it makes me irrationally angry just looking at it... It's like they asked "What's user friendly?" and then did the opposite. 3 times I've installed, 3 times uninstalled in a fit of rage. I hate it.
Under Windows error after error, even "play audio" node isn't working -.-
Hi, as you can see in the video, everything works correctly on my Windows 11 system. Could you please specify the error you're encountering? If any nodes are not working or appear in red, it likely means that some step was missed during the installation process.
@@Grandeai Thanks for reply, I've uninstalled already. With new test Comfy install I'll give more feedback. Anyway, after installing this built in Comfy simple 'Load Audio' or 'Preview Audio' nodes didn't work, afair something with PIL not recognizing files. Now after uninstall those nodes work again (play sound) without any errors in console. And I didn't want to install even more nodes to break Comfy install. Also even with those errors text-to-speech files were generated with correct words, so it's not like it isn't working at all.
nice
Thanks man❤
Is it a big software? Can i run it on my local laptop?
Hi, If you have a GPU in your laptop, I think you should be able to run it.
Thanks a lot for this 👍 How about another tutorial on how to create such awesome avatars as seen in this video? Was it made using LivePortrait?
Hey, I'm using Hedra Labs and enhancing the quality with CapCut Enhancer. Here, I made a video about it: th-cam.com/video/TqzDCuYlNRE/w-d-xo.htmlsi=yfNFMOWtR_Pgf0Lb
Which talking head ai did you use? can you do a video on it?
I have already made a video about it. Here is link: th-cam.com/video/TqzDCuYlNRE/w-d-xo.html
Hello, great video but although I follow all your steps, somehow when generating the voice I get a "Error occurred when executing CosyVoiceNode etc", it's a long text in red. I uninstalled pinokio and reinstalled it, did the same with ComfyUI. Although I google everywhere I still can't find a fix for it. I am new to this, if you can possibly help, I would greatly appreciate it
Hi. Make sure that after entering the custom nodes manager, and type "CosyVoice" it doesn't say "restart required." If it does, restart ComfyUI by pressing the restart button. Then restart Pinokio, and everything should work. If this doesn't help, I have created a simple Discord server to help beginners solve problems more easily. Please send a screenshot of the error you mentioned and specify when exactly it happens. We'll fix it quickly 😊 discord.com/invite/aAUVDFpD
I got an error when I used a large file. When I used a smaller audio file it worked fine. Hopefully this helps.
@@authorkevin Hey, do you mean a large audio file? Maybe so, because I haven't tested it. This model only requires a few seconds of your voice for cloning. I used 10-20 seconds of audio. Thanks, someone will definitely find this helpful. ❤
@@Grandeai yes. I tried it with a 2:30 wav file and got the error. I cut it down to 20 seconds and it worked fine. I also converted the two minute and 30 second wav file into an MP3 file and it worked.
@@authorkevin Yes, that's great! This model also supports MP3 files.
Thanks Can you share workflow file
Hi, There is link in the description 😉
Is the language available for Indonesia?
Yes, Applio supports the Indonesian language.
@@Grandeai ok thanks for share..🙏😊
And what is Pinocchio for? (what its role in this process?)
Hi, Pinokio is a very quick way to install most applications without needing to mess with the code, and is user-friendly for beginners (GUI). There's also no need to install Python or other tools on your system.
I wrote on 20 words after converting it only give 2 second of audio why ? Sorry for my English
Hi, try reinstalling or checking your model. Maybe try a different one. If you follow the steps, everything should work fine.
Will I have to repeat all the processes every time? Let's say I cloned Ronaldo's voice and then tomorrow I want Ronaldo's voice again so will I have to repeat the process all over again or from somewhere in between. Please clarify this query!
Hi, after restarting program, the pretrained models will be available in the model list. Just select them by name, and you can continue creating TTS.
Part 2 please. 🙂
Next time, try to include links to the tools you use in your tutorial.
Thanks for the tip! I'll include links to the tools in my next tutorials.
Thanks, can I run on CPU because i don't have GPU
Hi, Unfortunately, you can't.
Can we add emotions like anger,happy in the voices?
Unfortunately no, but soon something will appear on the channel that might interest you.
Hello, the VAE File is missing!!!
Hi, I just updated link in the description: huggingface.co/stabilityai/sdxl-vae/tree/main
Thank you for the Tutorial, the file for the sdxl-VAE is not in the 3rd link but a web search you may find it sdxl_vae.safetensors
Hi . I just updated link in the description.
right now if you search "kolors" it gives 2 results. The one you installed and a newer one called "ComfyUI-Kolors-MZ". Is that one better or is that one something new that still needs the other one to be downloaded first?
Hi, you can use both but the MZ workflow is in Chinese. I suggest starting by installing this english one first, and then testing only workflow from the second one.
@@Grandeai thanks!
How is this comfyUI better than SD webui?
Hi, ComfyUI offers a more intuitive and user-friendly interface compared to SD web UI.
@@Grandeai Okay, gonna try it, thanks
simply awesome
Part 2
Thanks for the video!
Hello sir Are you looking for a professional youtube thumbnail designer and youtube video SEO expert.?
Thanks, but not interested right now.
How can they pretend to have a license agreement when they trained it on SD lol
Good Question.
Great tutorial How can we upscale with Kolors
Thanks for your comment I'm currently working on another video where we'll create images in Kolors and then animate them using a new workflow. 😊 We'll also connect the image upscaler to the workflow in Kolors. Stay tuned for that! 😊
at 1:35 "Web Ui" I get an error: ENOENT: no such file or directory, stat '/home/xxx/pinokio/api/comfyui.pinokio.git/{{input.event[0]}}' Solution : Turn off windows firewall, press the "Reset" button and "Reinstall" button, an error will be fixed.
Thank you for your comment. It might be helpful to someone. However, I have installed it many times on Windows 11 and never had this issue.
Fooocus