WOW! Krea AI LIVE PAINTING + Webcam
HTML-код
- Опубликовано: 15 ноя 2023
- We're checking out Krea AI and their new live ai painting tool.
Get early access to videos and help me, support me on Patreon / sebastiankamph
Chat with me in our community discord: / discord
Prompt styles for Stable diffusion a1111 & Vlad/SD.Next: / sebs-hilis-79649068
ComfyUI workflow for 1.5 models: / comfyui-1-5-86145057
ComfyUI Workflow for SDXL: / comfyui-workflow-86104919
My Weekly AI Art Challenges • Let's AI Paint - Weekl...
My Stable diffusion workflow to Perfect Images • Revealing my Workflow ...
ControlNet tutorial and install guide • NEW ControlNet for Sta...
Famous Scenes Remade by ControlNet AI • Famous Scenes Remade b... 
Хобби
Invite codes here for Patreon Rainbow Superstar Subscribers www.patreon.com/posts/krea-ai-codes-93154234
Join up to be first on any future exclusive content
Still have codes? im trying to suscribe
This will be super useful when you can "freeze" the portions you like or freeze the entire gen, then inpaint -> freeze -> inpaint -> freeze... until you have a composition, then iterate the whole thing again at low denoise factors.
Screw low denois ip adapter and control net go brrrrrrrrrrrrr
I can see this being very useful for getting an initial base image for use in img-to-img type of workflow/process
Right! I think a lot of creative people will love this.
@@sebastiankamph or does it make sd obsolete? 😢
@@CoconutPete this is just SD in a interface package :)
Great overview with clarity. Cheers
this is amazing! you mastered the tool so quickly!!
Is a really intuitive tool and very funny to use. I can see Seb is really having fun using it.
Looks great , very creative possibilities
I have to try it - thank you
Will definitely give it a shot. Love your videos
Thank you kindly! Good to see you, Ashish! Welcome aboard the AI hype train 🌟😊
I was a genuinne joy watching you have fun with this.
This would be great to have in a local GUI maybe Invoke AI that is already more catered towards using a canvas?
Holy moly this is insanely cool! With generation timeframes ever decreasing, I wonder what other inventive ways will be developed in the coming weeks and months!
just awesome....
Neat. Stoked to see a live paint Control Net for Auto1111 soon
A1111 is out date and is going to be left in the dust trail that comfyui is creating
"An AI painter never gets old, it just becomes more pixelated."
Ah AI dad jokes!
@@pedroserapio8075 What do you get when you ask an AI to bake a cake? A pie chart.
very cool
I just installed the Krita plugin for SD (uses ComfyUI) and I hate to say it, but it may be an A1111 killer. But maybe not... might be a valuable part of the workflow though. I definitely don't want to abandon my beloved A1111
Fantastic cat! ❤ Cool tool anyways, I tested the first hacky version locally and it was pretty dope 😄
Yeah, I remember you showing the webcam thing in the chat!
amazing 👍
Thank you! Cheers!
awesome. looking forward to your guide to install it local :D:D btw can you export images or set to export all images while cam ° moving around? or you need to be really quick to have a good catch? is it free?
Look at nerdy rodents local install video
Dude, the 'Home Alone' thumbnail with the open mouth expression. Don't go down that well-trodden road. It's cringy. :)
Enjoying your content and Dad jokes though. This tool is amazing. It took Nvidia Canvas to a whole new level !!
This is a nice and powerful tool for speedpainting a base image or concepts, I approve 💪
The only problem is that it regenerates the entire image, but it doesn't really matter. This is one of those tools that allow *you* to take the lead and unleash your creativity ✔
Yes, sometimes you want to just change little parts and keep the rest. But like you said, for this tool it probably doesn't matter. It's a creative thing.
Wow
Good stuff, can you feed inputs from your desktop. i.e working in photoshop, procreate, video clips ..?
Yes!
It seems almost silly to try to get image generators to be faster, considering how much time they save already, but quick iteration is such a useful thing when creating.
Can you use it to inpaint existing pictures?
combine this with some form of really efficient interpolater that works in real time and this might be truly spectacular (it already is too).
Sebastian, I really like your videos and your simple way of explaining things. Could you create a tutorial or recommend a video for Stable Diffusion or CmofyUI on how to insert an object that has been generated into other scenes? Generate the same element in different scenes? For example, I generated the design of a new bottle and then, the prompt gave me a perfect result, after which I want to create an image of this same bottle in a scene with different angles or different poses (like a new photo of someone holding the bottle of juice, for example) It would be very interesting to have this type of video.
you're better off designing a scene with or without a bottle (or someone holding one) and then swapping it out with your perfect bottle in your photo editor of choice. In Photoshop its a 30-second job. Then bring your comp into Img2Img tab with Controlnet and a low denoise to "fuse" the composition. Be warned, it may take a few tries with Img2Img, because it's a diffuser and will change things.
Ip adapter + comfyui will take you there
hi, im new to ai art.. is there a comfyui way to do similar to this? (not the live aspect) i just want to put my childs painting into comfyui and have it changed into a scene
Yes, this is done with something called ControlNet. Got guides on that
I went to their website. Apparently you need an invite code, unless I did something wrong. I registered, so we will see if I get one.
Still have no idea how to enter the interface start using.
I woud like to finally see someone with actual skill using it - how would that work, not just folks doodling random crap
thats so cool. i was so impressed, when nvidia presented the predecessor of this for landscapes. only bummer its not local
It's most likely built upon Stable diffusion and LCM, so I'm sure it will be available locally soon.
@@sebastiankamphkrita has it as a plugin
Ohh I thought this was going to be video about how to install and setup Real-Time Latent Consistency Model
That was the video he released 3 days ago (if you are looking for that info).
Thanks to TensorRT and LCM Lora some 3090/4090 users state they can do 5-10 images in 1024x1024 resolution a SEC :O
Crazy stuff
how to start using this? Do I need to download it or use it on the internet?
You can local install the krita plug in that does this with stable diffusion
@@hipjoeroflmto4764 where to get it
Would be this locally possible soon?
....now! 🤣
It is possible with krita
this'll be cool 120fps, 4K...in VR
Millennials develop Sketch from A1111 on LCM sampler in paid service. Big think. (Nope).
What are you even saying lol
this could possibly be using the LCM lora
Probably so, yes
Yes: WOW!
Indeed! I don't like clickbaiting but man, this was so cool!
👋
Art challenge: try to imitate the output in the input without directly copying it. Keep going until they are identical.
Impossible difficulty: a denois strength of 1 + random seeds
Poll a drawing interactively is really really old tech. This is not the new crazy novel thing you make it out to be. I've seen AI image generation demos do this stuff from years ago.
I looked at the website, this must be a paid service since it says 'try krea for free' but there's no mention of price anywhere
30 dollars a month, unlimited imagen and video creation. I might cancel midjourney if I get the hang of this.
Too bad its not local and free. There are at least 2 more with the same concept: fictiverse redream for auto111 and other in demo mode
You are wrong, krita has this plug in with comfy ui or there version of SD install
Damn im starting to feel all the $10, $20, $30, $40 a month tabs adding up. Im having to go thru and say, nope d-id gotta go, splice, elevens lab maybe? chatgtp, midjourney...
What a shuffling match its turning out to be
Just learn about local install for things it's pretty fucking funny people are paying for any Ai service with all the shit open sourced for free downloads
😂🤣👍👍👍
🎯 Key Takeaways for quick navigation:
00:00 🚀 *To train your own AI model with KREA, start by going to the AI training section on the KREA dashboard.*
01:08 📷 *A good AI training dataset should have a common style or concept among the images you upload.*
02:16 🧹 *You can remove low-quality, repeated, or irrelevant images from your training dataset.*
03:30 🖼️ *Ensure that the images in your dataset are high resolution, preferably at least 512x512 pixels.*
04:11 ⏳ *The AI training process typically takes 1-2 hours, and you can monitor its progress on the KREA dashboard.*
05:07 🤖 *After training your AI model, you can use it to generate content by selecting the trained model in the KREA AI engine.*
06:05 🎨 *The generated content will reflect the stylistic properties of your training dataset and respond to the prompts you provide.*
Made with HARPA AI
Another paint cat ai
ALL my images on Krea AI were deleted without my permission. I am a paying customer and I have a lot of time invested in creating these images and I am pissed. Why would my images be deleted?! Infuriating!!!!
Can you comment on this $20 for 3 to 5? I am really not happy.
The what now?
† I believe we are meant to be like Jesus in our hearts and not in our flesh. But be careful of AI, for it is just our flesh and that is it. It knows only things of the flesh (our fleshly desires) and cannot comprehend things of the spirit such as peace of heart (which comes from obeying God's Word). Whereas we are a spirit and we have a soul but live in the body (in the flesh). When you go to bed it is your flesh that sleeps but your spirit never sleeps (otherwise you have died physically) that is why you have dreams. More so, true love that endures and last is a thing of the heart (when I say 'heart', I mean 'spirit'). But fake love, pretentious love, love with expectations, love for classic reasons, love for material reasons and love for selfish reasons that is a thing of our flesh. In the beginning God said let us make man in our own image, according to our likeness. Take note, God is Spirit and God is Love. As Love He is the source of it. We also know that God is Omnipotent, for He creates out of nothing and He has no beginning and has no end. That means, our love is but a shadow of God's Love. True love looks around to see who is in need of your help, your smile, your possessions, your money, your strength, your quality time. Love forgives and forgets. Love wants for others what it wants for itself. Take note, true love works in conjunction with other spiritual forces such as patience and faith (in the finished work of our Lord and Savior, Jesus Christ, rather than in what man has done such as science, technology and organizations which won't last forever). To avoid sin and error which leads to the death of our body and also our spirit in hell fire, we should let the Word of God be the standard of our lives not AI. If not, God will let us face AI on our own and it will cast the truth down to the ground, it will be the cause of so much destruction like never seen before, it will deceive many and take many captive in order to enslave them into worshipping it and abiding in lawlessness. We can only destroy ourselves but with God all things are possible. God knows us better because He is our Creater and He knows our beginning and our end. Our prove text is taken from the book of John 5:31-44, 2 Thessalonians 2:1-12, Daniel 7-9, Revelation 13-15, Matthew 24-25 and Luke 21. Let us watch and pray... God bless you as you share this message to others.
Notice how it’s biased towards women.