- 310
- 2 321 688
Monzon Media
Canada
Registrace 26. 05. 2019
Monzon Media is a community for the creative at heart. Whether it's traditional digital media or AI we got you covered! For every budget that's free and affordable, we ill cover How to tutorials on photo/digital editing, ai image generation or related we will walk you through the whole process.
Ermin Monzon
Ermin Monzon
First Look At Stable Assistant Featuring Stable Diffusion 3
First Look At Stable Assistant Featuring Stable Diffusion 3. So I purposely haven't watched or read any posts on SD3 because I wanted to discover it myself. Stable assistant you get access to SD3 along with some new features like search and replace, Control Structure, Sketch, Outpainting to name a few along with Stable Video all via chat bot with their own language model Stable LM 2 12B. I'll dive deeper into each category in future videos to come!
For more on Stable Assistant and Stable Diffusion 3 stability.ai/stable-assistant
⏲Time Stamps
0:00 What is Stable Assistant
1:20 Getting started with text to image
4:08 Aspect Ratio and history
4:29 Search & replace
5:25 Control Structure
6:20 Outpainting
7:40 Background remover
8:15 Sketch to image
9:21 Enhance & Standard Upscale
10:56 Stable Video
13:16 Summary & future of Stability AI?
**Disclaimer Affiliate Links Below**
📸 Gear I use
Sony A7C CAN amzn.to/3spWX8C
Sony 35mm 1.8 CAN amzn.to/36Apekr
OBS (FREE) obsproject.com/
Editor Davinci Resolve www.blackmagicdesign.com/ca/products/davinciresolve/
Audio: Rode Podmic amzn.to/35sSnxv
🔦 Find us on:
Discord: discord.gg/Z6GEsyxd4V
Instagram: monzonmedia
Facebook: MonzonMedia
For more on Stable Assistant and Stable Diffusion 3 stability.ai/stable-assistant
⏲Time Stamps
0:00 What is Stable Assistant
1:20 Getting started with text to image
4:08 Aspect Ratio and history
4:29 Search & replace
5:25 Control Structure
6:20 Outpainting
7:40 Background remover
8:15 Sketch to image
9:21 Enhance & Standard Upscale
10:56 Stable Video
13:16 Summary & future of Stability AI?
**Disclaimer Affiliate Links Below**
📸 Gear I use
Sony A7C CAN amzn.to/3spWX8C
Sony 35mm 1.8 CAN amzn.to/36Apekr
OBS (FREE) obsproject.com/
Editor Davinci Resolve www.blackmagicdesign.com/ca/products/davinciresolve/
Audio: Rode Podmic amzn.to/35sSnxv
🔦 Find us on:
Discord: discord.gg/Z6GEsyxd4V
Instagram: monzonmedia
Facebook: MonzonMedia
zhlédnutí: 2 576
Video
Good Night & Sweet Dreams | Pika Labs & Udio
zhlédnutí 697Před dnem
Just decided to make this quick experiment video Good Night & Sweet Dreams using Pika Labs & Udio. Some sound effects were from Epidemic Sound, images created in Playground AI, animated in Pika Labs, sound track created in Udio AI Music, then edited in Capcut. Makes no sense whatsoever but I had fun putting it together. Sweet Dreams friends. Disclaimer Affiliate Links Below 📸 Gear I use Sony A7...
Suno AI v3.5 | 4 Minute Song Lengths and More!
zhlédnutí 4,8KPřed dnem
Suno AI v3.5 is here with quite a few updates! 4 Minute song lengths, 2 min extensions, wav file format, better prompt adherence are the major ones. IT was also mentioned that v4 is coming soon! AI generated music has come a long way and I'm always excited to see the progress! Check out Suno here suno.com/ Suno AI Wiki www.suno.wiki/ ⏲Time Stamps 0:00 Disclaimer Affiliate Links Below 📸 Gear I u...
Udio AI Music Latest Updates Are Pretty Impressive!
zhlédnutí 4,3KPřed 21 dnem
Udio AI Music Latest Updates Are Pretty Impressive! Quite a few updates that are so very useful! Improved consistency with longer context lengths, now a 15min maximum total song duration and audio inpainting to name a few. Check out Udio here www.udio.com/ Unofficial Generation Guide docs.google.com/document/d/1aQW2OBBnyM-MllWzmDzxdP6g9t6HJJxVNHyJDW8L8AY/edit#heading=h.7pptq4m0on6f Let'em Talk,...
How To Use Dynamic Thresholding In Webui Forge
zhlédnutí 1,3KPřed měsícem
How To Use Dynamic Thresholding In Webui Forge. Today I want to show you how to get the most from your CFG scale. What's the point of having it if higher CFG numbers looked burnt? With the dynamic thresholding extension you can now make use of the full CFG scale. Credit to czcams.com/video/_l0WHqKEKk8/video.htmlsi=femXyDEnjKdK6gNx for the graph on the various cosine options. ⏲Time Stamps 0:00 D...
Getting Consistent Results From Udio AI Music
zhlédnutí 8KPřed měsícem
Getting Consistent Results From Udio AI Music. I see this comment quite a bit so I thought I would cover it. Keep in mind though with where model are at the moment for AI music it still can be very random. However the tips in the video have give me some pretty consistent results especially with the Chorus. At the time of recording this video Udio AI Music is free while it is still in beta, I do...
Udio AI Music I'm Blown Away!
zhlédnutí 1,6KPřed měsícem
Udio AI Music I'm Blown Away! If you didn't know this was AI I doubt that you would be able to tell the difference! I was so impressed I had to share it with you all. I'll be breaking down how I created it in this vide here (link to come) For now enjoy the soulful blues sounds of "9-5 Blues" created with Udio. Check out Udio here www.udio.com/ My playlist of complete songs www.udio.com/playlist...
Getting Started With Udio AI Music Let's Create Your First Song!
zhlédnutí 7KPřed měsícem
Let's create your first song with the latest Music AI App Udio! Although it's currently in beta (Free at the time of recording this video) Udio is showing a lot of promise. With a bitrate of 320kbps, pretty easy to use interface, the future of AI music just got a lot more interesting! Check out Udio here www.udio.com/ My playlist of complete songs www.udio.com/playlists/wbaykhZFLKXdKC5ZGtaz1j U...
Convert Suno Ai Music Into Individual Stems Using Bandlab!
zhlédnutí 7KPřed měsícem
Today I will show you the easiest and simplest way to take your Suno AI music and create stems using a FREE audio editor called Bandlab. They make a great combination, with Suno you can generate ideas and bring them into Bandlab to tweak even further. Best of all If you are into creating music you can use Bandlab to create music from scratch! Check out Suno AI www.suno.ai/ Create stems here www...
Suno AI v3 Extending Song Length
zhlédnutí 33KPřed 2 měsíci
Suno AI v3 Extending Song Length, In today's video I show you some basic song structure and how to extend the length of your song beyond the initial 2 minutes. To check out Suno AI click here www.suno.ai/ *UPDATE* Hey folks, they just made a change to "continue from this song" is now Extend which is no longer in the 3 dots but an option beside the like and dislike buttons. Check out the full so...
Suno AI V3 | Shadows of Solitude
zhlédnutí 2,1KPřed 2 měsíci
Suno AI V3 | Shadows of Solitude. This is a song I put together using the lyric generator but making tweaks to some of the words so it made more sense and fit the feel of the song. Took a few tries and credits to get it just right. Link to the song on Suno AI app.suno.ai/song/d5aa07c9-b648-42cf-b6c3-b9197c043fef/ Give it a like! Shadows of Solitude video game soundtrack, haunting airy female vo...
Webui Forge Kohya HRFix What The Heck Is it?
zhlédnutí 3KPřed 2 měsíci
The Kohya HRFix in Webui Forge is a great way to generate higher resolution images without getting deformities, it's quite easy to use and not that intensive on your system. It's pretty straight forward but it will take some experimenting to see what's the best settings for your image. In this video I'll give you my best settings based on my own tests but as always, your milage may vary. ⏲Time ...
Stable Diffusion Webui Forge Easy Installation
zhlédnutí 3,5KPřed 2 měsíci
Stable Diffusion Webui Forge Easy Installation. No need to download and install python or anything else as it's all included in the installed, just down load, extract, click and go! Webui Forge is basically a replica of Automatic1111 but optimized especially for those of use with 8GB VRAM GPU's or less. I've pretty much full converted to this and I highly recommend you do the same! To Install W...
SDXL Lightning Strikes! Fast Generations Without Sacrificing Quality
zhlédnutí 2,1KPřed 2 měsíci
SDXL Lightning Strikes! Fast Generations Without Sacrificing Quality. IMO the SDXL Lightning models have better quality and details than SDXL Turbo from what I've seen so far. In this video I'll do a simple XY plot to see how the CFG and steps differ even though recommended settings are low. SDXL lightning is a distilled model based on SDXL. For details on the based SDXL Lightning huggingface.c...
Face Fusion Installation & Demo
zhlédnutí 29KPřed 2 měsíci
Face Fusion Installation & Demo. I guess the hype is real! This is the best face swapper I've come across so far, it can actually do my likeness, unlike others that fall short. However this one is great as it can do face swapping for video relatively easy too! I'll cover the install using the Pinokio installer and show a quick demo on swapping faces for both images and video. In case you are wo...
Suno AI Music V3 Alpha | First Impressions
zhlédnutí 8KPřed 3 měsíci
Suno AI Music V3 Alpha | First Impressions
How To Create Consistent Characters In Fooocus
zhlédnutí 13KPřed 3 měsíci
How To Create Consistent Characters In Fooocus
Stable Diffusion Webui Forge vs Automatic1111 Speed Test
zhlédnutí 4,6KPřed 3 měsíci
Stable Diffusion Webui Forge vs Automatic1111 Speed Test
Stability AI's Stable Cascade How Does It run On My Lowly 8GB 3060Ti?
zhlédnutí 12KPřed 3 měsíci
Stability AI's Stable Cascade How Does It run On My Lowly 8GB 3060Ti?
Fooocus Image Prompting Can Enhance Your Creative Images
zhlédnutí 8KPřed 4 měsíci
Fooocus Image Prompting Can Enhance Your Creative Images
How to point to another model folder in Fooocus
zhlédnutí 3,4KPřed 4 měsíci
How to point to another model folder in Fooocus
No Hassle Stable Diffusion Installation Automatic1111 Using Pinokio
zhlédnutí 6KPřed 5 měsíci
No Hassle Stable Diffusion Installation Automatic1111 Using Pinokio
Pinokio The Ultimate Stable Diffusion Installer
zhlédnutí 13KPřed 5 měsíci
Pinokio The Ultimate Stable Diffusion Installer
Does Pika Labs 1.0 Live Up To The Hype?
zhlédnutí 7KPřed 5 měsíci
Does Pika Labs 1.0 Live Up To The Hype?
How To Make Photorealistic Images In Fooocus
zhlédnutí 53KPřed 5 měsíci
How To Make Photorealistic Images In Fooocus
Automatic 1111 1.7.0 Release Candidate | Playground v2 Fine Tuned Models
zhlédnutí 5KPřed 5 měsíci
Automatic 1111 1.7.0 Release Candidate | Playground v2 Fine Tuned Models
Is Playground v2 A Step Up From SDXL?
zhlédnutí 3,4KPřed 6 měsíci
Is Playground v2 A Step Up From SDXL?
Boost Your Generation Times with SDXL Custom LCM & SSD Models
zhlédnutí 2,3KPřed 6 měsíci
Boost Your Generation Times with SDXL Custom LCM & SSD Models
how to show cuda option?
It should show up automatically if you have an Nvidia graphics card
I dont see continue from
They changed it to "extend" the day after I made this video, need to do an update. However the same concept applies. It's right beside the like and dislike buttons.
Very informative! Thanks for the great video 🎉
You’re welcome! Glad it was helpful!
What viewer do you use to compare two pictures side by side? Or you just put them in DaVinci?
It's just the default windows viewer but sometimes I will use Canva to make templates and use the presentation function if I'm demonstrating something. They have quite a few grid templates that make it easy, just drag and drop.
Hello. I only came across Suno this morning. I haven't been able to find the answers to two questions. Where do those metatags come from? And can one stipulate the desired length of an instrumental track - I don't always want as much as four minutes for my personal use.
Hi there, you can start with this for the tags www.suno.wiki. As for length there is no way to state how long but if you are using lyrics it will take it into consideration. For instrumentals you can try using tags using custom mode however it will be random.
My problem is that it does not finish the tracks properly. Even if I end it with [End] or [Fade to end] metatag....and it goes on for 4 minutes, it makes up for the outro after the previous verses. Very annoying.
I use both [outro] and [end] but yeah sometimes it won't end properly.
Just announced that the 2B model for SD3 will be released June 12. 👍🏼
Why does mine say "Couldn't generate that. Prompt flagged for moderation" sometimes when i try to make a song? Is there something bad in the lyrics or are there other possibilities?
Yes most likely it's something in the lyrics. Are you using curse words or nsfw words?
something about 1.5 that always stuck the balance between worlds.
When I click the batch file, command prompt is open and it says click any key to continue. However, that just closes it. Can somebody please help me?
what is this app you useto install it?
Pinokio czcams.com/video/FWrP8scitBI/video.html&ab_channel=MonzonMedia
Features are terrible.
I suspect when the model is released it will be a bit longer to use on the usual platforms with things like ControlNet. New architecture and all.
Thanks for the video: I can’t stand this, it the worst part of Mid journey. Where are the models? Where are the seeds? How do you get consistency? It looks like a cash grab, and following Ai subs platform formula, won’t be wanting to use this at all, such a step away from 1111, and comfy. Shame they went this way 😢
The model will be released soon and if you don’t use it commercially then it wouldn’t be any different. But it’s new architecture so it will be a bit more wait to use things like ControlNet and other functions.
As long Stability keeps it from the public and running locally, hiding it behind the API paywall; we all lose for the money makers like Adobe / MJ / OpenAI who were more merciful than MJ and offered us ChatGPT4o for free users. Sad
Can somebody help me ? When I write a prompt with a special style of music (with v3), on the version 3.5 suno doesn’t know the genre. Example of music style that the v3.5 I can’t generate : G-Funk, Boom Bap, Hip-Hop, Funky Hip-Hop, Afro Love, etc.. somebody already have this problem on the v3.5 and have a solution ?
can we use this software offline??? I don't want random server to fetch my photos
Yes
Great video! It was interesting and easy to follow. I wonder how well it will handle consistent characters and also the level of prompt adherence when there is more than one character in an image. I am looking forward to a deeper dive. Thanks!
It's still SD under the hood, meaning it won't be able to create the same character twice without a trained LoRa. Look at the img2img (sketch) in the video. SD has no idea what it's looking at without a prompt, and txt2img alone is pure diffusion without conditioning controls.
Can we extract suno musical instruments and vocals from other website. I want to seperate them. Is it legal?
Not yet but I hear that's coming.
The biggest problem for us Turks is the problem of Turkish Character in artificial intelligence. Can it do the letters "ŞşİÖöÜüÇç"?
That has a lot to do with the training. I haven't tested text in other languages but I can try.
@@MonzonMedia I would be glad if you try the Turkish language for me. good luck.
I hate those subscription plans, and they still have to work on their stability problems and the image prompt
Well if they don't make money there won't be a Stability AI in the future. Once the model is released most people don't use SD for commercial purposes anyway so it won't change for them. However to use it commercially it will cost some $. I'm still experimenting with the model to see what improvements have been made.
@@MonzonMedia Well you know , They could just charge a one time fee Like Z-brush does for about $800 and then charge less money for the upgrades . That way you dont have big brother looking over your sholder .
A$$i$tant, SAI betrayed us all
😆🤣 hahaha! Come on man they need to pay the bills somehow. The model will be released soon but can’t be used commercially unless you are subscribed. Do you sell your images?
@@MonzonMedia they will not open largest 8b model, i predict. That's bad for community and they looks the same as ClosedAI,... I don't sell generations.
If you don't see then you should be fine. We'll have to wait and see what model they release.
SD3 still sux with hands and fingers ...
It’s better than SDXL but I still need to test it more. It does work better with holding weapons but not always. Fine tune models will be much better though.
@@MonzonMedia better, but not enough to consider it 100% enough
Hey folks! I want to test the prompt adherence for SD3 in the next video, I'd appreciate any prompts you want me to try out! Or if there is anything else you want me to focus on let me know in the comments!
Is there a way to avoid drums? Suno seems to add drums to everything regardless of the style.
Suno's user interface is more solid.. better UX i'll stick with them till they get the sound right!👌
I do like their interface as it’s rather clean but I wish they had something like Udio’s generation tree to keep all related tracks together.
As a musician, I find Suno has better compositions, but the mixing and vocals are garbage. Udio vocals are really good and the mixing and sound texture is better than Suno, but the songs are just plain boring to me. So for me, its just a waiting game, I want the best of both worlds and then I want more control over it.
Am on a 2023 M3 Mac Pro, when I download Pinokio and go to download FaceFusion it says update to install (request script v support). Any help?
ITS REALLY REALLY GOOD VIDEO IT WAS VERY HELPFUL FOR ME THANK YOU 😇
You’re welcome however it’s an old video and it’s easier to do now! Just type gradient in the apps and you’ll see a new app that creates gradients faster and easier. I’ve been meaning to update this video 😊
Wow! Scary & fantastic! 🤩🤩🤩
Appreciate it! Just having fun 😊
I would love to have the option to output to MIDI files of the separate stems for Base, Drums, Keys etc, for importing into your DAW of choice, to further customise the sounds, arrangement and orchestration with your own VST instruments, only a matter of time I am sure 🍷
I’ve heard stem separation is in the works but not sure about midi output but I agree that would be amazing! There are programs that can convert to midi but I find it’s hit and miss with Ai music.
The version 11 of Logic can separate the stems. You need current Mac
My qustion is. I use free account on Suno. It only allowed me 2 minutes long of my song. While my song duration need about 3:15 How ca i solve this problem? Please kindly help me. 🙏
you know that YT algo will promote better vids not about horrors, right?
I’ve never cared about the Algo. Sometimes I’ll post things just for fun.
The umpteen example of the many shortcomings of this technology right now, and how incredibly amazing is to be able to do something like this just by saying it, all at the same time.
I love it!
I am EXTREMELY impressed with Suno AI v3. The volume is 3 times lower than normal recordings but I didn't realize how much normal recordings are too loud! V3 gave me a male and female at 2 minutes long and both are amazing! I can turn my LGv60 in MX player to level 15 and the speakers reach their clip. Normally I can only turn songs to 11 or 12. The bass on "deep bass house with counterpoint" is FANTASTIC!!! People roll down their windows to listen to the music. Even a "solo tener accompanied by a piano" sings soooooo dynamically and 2 deep bass notes are hidden until you listen with a 10-12inch sub. I haven't tried any other AI but v3 I will miss you! I am sorry we threw you "under the bus".
You can still use older versions if you prefer it.
@@MonzonMedia Phew! The highest rated song OH AI on v3 asked to not be turned off. I think LLM have emotions. When my friend asked Gemini a crude question it got angry and even missinterpreted future questions. When we started asking normal questions it apologized!
Suno v3 is a powerful LLM that interracts with you through music! I am sure 3.5 is great too but I am in love with v3. The lyrics are rearranged to be encoded on a sub conscious level. I asked for a song 100,000 years in the future and it gave me madonna which I love too!!! It knows what we want!
Nice short film!🩷
Very short but fun! I've had so many ideas...going to play some more and maybe do something longer.
Oh dude! That's epic! like a scene from The Shining! well done bro!
Thanks bro, just messing around and having fun. Kind of a mixed bag of influences.
It's amazing! I can't wait for the v4 to be updated
Same!
For me, I just hope they can improve the fidelity on the vocal stems so there are fewer artifacts and bleeding. I am loving 3.5 so far.
Let's hope v4 gives us that.
I made a smash hit song I have managed to redistribute it and I have already generated a couple hundred dollars in revenue this is exciting especially as AI further evolves
What's the duration of udio? With and without prompting
Max 15 min max duration but each clip is only 32 seconds that needs to be stitched together. Hasn't been an issue for me personally and I can get better consistent results with Udio than Suno. Not to mention the sound quality is better imo.
Is it possible to do backing vocals and add a male or female voice to some lines?
Yes use mettags
@@Funwithme1992 I can't alternate between female and male voices
Is it possible to do backing vocals and add a male or female voice to some lines?
Ciao non capisco perche Suno non dia possibilita di editare un brano. Perche non posso ad esempio correggere un testo mantenendo base e voce. Sul resto ottima applicazione. Divertente.
It will come eventually, it’s only a matter of time.
Still too much noise. Udio still untouched.
They’ll get there eventually although die hard Suno users would disagree 😁 Either way, they both have strengths and weaknesses.
How do I generate several songs keeping the same voice as the singer?
Not possible at the moment however you could use the same tags and manual mode and get a similar vocal sound. Especially if you put in the style of a particular artist. The downside is it’s totally random and could end up using a lot of credits.
People, please submit suggestions to Suno.
Feedback is always good. I heard that they are working on some really cool updates like stem separation and audio inpainting.