Olivio Sarikas, an AI Expert and passionate Artist, invites you to explore the exciting world of AI art. Join live streams to turn your creative visions into reality. Let's create together! 🎨🤖🚀
Olivio Sarikas is a professional Designer from Vienna Austria, a passionate Artist for over 26 years. He studied at the University for Fine Arts in Vienna and Munich and holds a Masters Degree in Fine Arts.
Community Guidelines:
Inspire, Engage & Help: Use comments to share passion, inspire, and support AI art.
Respect and Kindness: Treat all with respect, regardless of opinions or backgrounds.
Constructive Criticism: Offer constructive feedback; avoid overly negative comments.
No Harassment: Report and avoid harassment or bullying.
No AI Haters: Spread love and passion; keep comments positive and inspiring.
*Note: Do not use the email below for questions.
Пікірлер
Happy birthday!
I know this is probably the most basic of questions but, What does the () do in a prompt, assign detail to the prior word?
How is it smoothly looping? is it just the video that dose it? or whats going on? mine all animate great, but at the end jump
I don't have that "Manager" option. Please help.
you need to install comfyui manager. please google it. the install is very simple
this is going in the playlist, thanks a bunch :D
Recently, there are several new models, such as Playground V2.5, SD Cascade, and PixArt Sigma, which I think provide huge improvements in terms of prompts adherence and image quality as compared to SDXL. Since SD 3 is not accessible by public any time soon, it would be great to hear your opinions on these new models (a head-to-head comparison would be awesome).
Can we use control net ? doesn't spell properly or bring any text
This workflow needs to feature a huge DC Shoes trainer heading straight for the viewer. Because it literally kicked me in the face
The only concern which we should have, and I'm surprised nobody seems to be discussing this at large, is in the defence of those who's jobs have become "redundant" due to large companies training models off former employee's work, such as web design, concept design, anything to do with design. None of these industries are cheap to get into, and take up several years of study, and large amounts of money. Soon as capitalists discovered "AI" use for generation? What was mainly a community of nerds creating open source tools for personal use, and sharing with others, has become a business venture. Those employees should have rights to the work they've spent hours, weeks, months on, not the corporations to train models. Besides, since when do we defend corpos?
these apps dont install for me. something about a "conda value error"
Does this Upscaler work with Forge
Instructions unclear, grandma became a top level hacker and now she laughs at my coding attempts
Another great video. I am looking for a way to combine two images, I have an image of a cheerleader of a football team, and I have a logo, I want to have the cheerleader holding a sign with that logo. do you have a video that explains combining images? cheers
thanks
KZreadrs are so greedy they sell workflow in patreon.. but you give away for free .. you deserved more followers
Hi Olivio, I'm an avid viewer of your content, and keep learning soooo much from you.. I normally work on A1111 due to the extensive community support A1111 already has.......However......... In recent weeks I have been drawn to ComfyUI especially after watching your videos/tutorials and realizing the powerful additional features it offers. But.... Since I have used A1111 for a long time, I have built-up a large collection of Extensions, LoRAs checkpoints, embeddings etc. I am slightly reluctant to install ComfyUI and lose the stuff that already works flawlessly on A1111. So.....With that in mind, I thought the best thing may be to have an existing installation of A1111 that remained relatively unchanged, and in parallel have an installation/webui that allowed me the benefit of ComfyIU without copying/reinstalling/downloading all the Loras/Checkpoints that I already use as I would run out of disk space on my PC. I searched your youtube channel, to see if you had any content on running them together, but I was not able to find anything... yet.. Also doing a google search, and youtube search, bring-up very little and one video I saw installing ComfyUI as an extension did not have sufficient details, and did not go into specifics, i.e. is a ComfyUI manager installation possible. I'm sure there are lots of people that may have the same problem. Kind Request: Is it possible for you to do a Video Tutorial on the best method of running ComfyUI in parallel with A1111
What is the best Ai Generator to make a music video with myself in it?
Love you Olivio wish you all best from my hearth! Thank you for all of your work youve done...Stay awesome!
Great video, thanks:) I have one question. Can I call the LoRa just through the prompt so it's not activated when the prompt is not asking for it?
I had same thoughts, be prepare for law suit, how dare you copy my thoughts.
Did you invest or what? Why 43 minutes for that? It has nothing to do with recession. Those products are just bad design. Thx for wasting 4 minutes of my time. (I've skipped a lot of this).
its telling me in commend that No Python at that location i copy as path
I create artwork for my shooting game with stable diffusion. Being a paid user of chatgpt, I decided last week to utilize my access to dall-e 3. I wanted to make targets resembling criminals with weapons, much like the police training scenarios. After 3 hours of trying to coax the AI into creating these images, I gave up after being intermittently reminded by chatgpt that I should not try to portray negative or violent behaviour, and instead should concentrate on neutral images. It often suggested just drawing a circular bullseye instead. Needless to say.. I went back to SD and produced the content I required within an hour... Censorship will be openAI's downfall, only then will they alter their approach and give the public what they want.
a lot of great tipps and hints, thank you!!
You are the MAN! whoah! It works so well!! Im using it to get ideas on how to improve my 3D models!
what's happened to SD3??
Ja Danke, bin gerade sehr mit Resolume-Plugins zu erstellen beschäftigt und daran Tool3 in den Griff zu bekommen. Aber irgendwan dan werde ich wohl nicht mehr um dieses AI-Zeugs herumkommen, wie gesagt, es giebt ja schon gute Dinge da. Mit nur den besten Wünschen & Grüssen bennoH.🐼🙋
This is why I learned to use blender ^^
So schön... ich wünschte ich könnte mal nach Wien,.... meine Familie, Esterhàzy und Pàlffy Daun , haben ja viele Paläste und Statuen in Wien über die Jahrhunderte gehabt, die ich noch nie gesehen habe.... shame on me...ich weiss.... dein video inspiriert einfach mal in den Flieger zu steigen, und Wien zu besuchen....
does it occupies any space in computer's local SSD?
Auto1111 is best. Comfy ui is made by 16 yr old who had nightmare 😂 it confuse everyone
5:05 i lost it here, where can i find my path of /A1111/webui? I cant find it in my desktop
Hello, is it possible to use this method to add jewelry?
Vsauce ?
great tuto but the sdxl models don't work : server execution error : Error while deserializing header : MetadataIncompletebuffer
Thank you very much sir.
"Freep!k" clever name for a paid service... lol
I use AI in post work to enhance my original works. I call it AI Bumping to give it just a tweak. From my understanding of AI laws so far this is protected.
I've tried other workflows, this is the best, and it's free.
I think if you really want to have a productive conversation about this, you need to talk about the motivation behind using these tools for ourselves. If we're using these tools simply to make spam art and fake ads, then nobody will want to preserve them. If people really want public support, then they need to show the public that these tools can actually be used for real creative expression, and the transformative nature of the technology.
Maybe make a "perfect human"-workflow, I have seen separate workflows for face-detailing, skin, hands, eyes, feet.....maybe I just want to click qeue prompt once and I want my humanoid figure to be perfect in the end without building a workflow for every part of the human body
After installing Pinokio and Cascade, I just get "Error", if I try to render something. What can I do? Thanks in advance!
I'm using image from outside using load image, while using Image Alpha composite I'm getting error - image size must be same. I used image resize to make sure I pass same size of both image but getting same error again. Any solutions please?
Hey, I like direction of your thoughts in the way and such genre of the video. Seems like you are nice guy in you tutorial and overview videos, it's nice too see you doing smth on the street. I.m doing smth like that myself - going for photo trip. I like to do some photoshoots for photogrammetry, even if I just use my smartphone. No reason to sit staring at the screen all you time. Highly appreciate you to explore the world and share your thoughts.
so nice....although not there yet with skin,... as MJ in most cases gets there. would love to challenge you on the face skin one day, if you are up to it? Thanks for lettings us see all your tricks and magic.
i cant install kohya bc my python version is 3.12 :(
too bad it works only with "portrait" images