FOoOcus - The Best Tool to Get Started with Stable Diffusion and AI Art! 🎨✨🍆
Vložit
- čas přidán 2. 05. 2024
- Let's take a look at the easiest way to get started with AI art and Stable Diffusion. Not only does this tool have a one click installer but you don't need to install prereq's like python and it uses a lot less VRAM than Automatic 1111. Fooocus also has preset settings that keep your art looking beautiful even if your new to Ai art. This is the best way to use stable diffusion for the average AI artist. Check it out today and Simplify your life with this tool.
This is the closest thing to a Free Midjourney!
Download Fooocus Here - github.com/lllyasviel/Fooocus
Download Fooocus MRE here - github.com/MoonRide303/Fooocu...
#stablediffusion #fooocus #illyasvile #freemidjourney
Chapters
---------------------------------------
00:00 The Problem with SDXL...
01:37 Let's Take a look at Fooocus!
02:51 Why Choose Fooocus Over A1111 and Comfy UI?
04:11 Let's Install this AKA download it =)
06:32 Using Existing Models with Fooocus (If your new to Ai art just Skip this section)
07:32 Alright Let's Start Fooocus Up
08:55 Advanced Settings, Speed and Resolution
09:51 Styles - What Makes Fooocus Better than the rest
11:01 Input - Control Net Canny, Face Swap, CPD
13:45 Variation, 2x Upscale, Blending
14:10 Inpainting and Outpainting
15:12 Check out More Videos on Ai Art! - Věda a technologie
Fooocus is hands down the easiest way to get started with Stable diffusion and SDXL. The sleek interface and Style selectors make it easy for new users to make beautiful art without dealing with all the complicated Stable Diffusion requirements that were introduced with SDXL. Try it out today, It's a 1.8GB Download, then unzip some documents and click on run file. No python, GIT, or other prereqs necessary. Here is the Fooocus link to get your started - github.com/lllyasviel/Fooocus
How to solve SSL Exception while running the bat file? 6:35
always connection error
Thanks for the detailed instructions! I'd love to try out Fooocus but minimum requirements show 16GB VRAM for AMD systems and I have an RX 7700 XT GPU (12GB). Does that mean it would not even run/generate images on my system at all, or just very slowly?
Thanks for sharing, i can't believe how easy it's to install and use and the quality is amazing.
how can i install in macbook pro M1 ?
Thank you for this thorough introductory fooocus walkthrough. Shared with a friend, and now subscribed. 🤠👍
this program is amazing. when i first loaded it i thought it was just overly simplified. but did not realize it has a LOT of nice uniqjue features built in as well as one of the BEST face swappers ive used def worth a try DONT be turned off by its simple looking interface at first!
Wow, by far the easiest and best quality one I have tried.
Thank you for this! Helps me get started! Most useful!
I love fooocus so much, I’ve been using it for a couple months on my 16vram gpu. Amazing tool! This is the most user friendly sdxl version out there.
Thanks for your video, really useful! I have a question: is there a way to make an AI generate subject holding another object taken from a picture? For example, I've generated a character, now I want him to hold a particular videogame controller. Is there a way to make this happen using a controller photo as input?
Thanks
"Foo is commonly used slang term in computer programming as a term to express different variables, functions and other specific concepts"
Awesome, I learned something new! Seriously appreciate that I was trying to find the answer everywhere.
How about privacy? Are input or output images reuploaded to the image data pool for the AI to learn?
Thanks very much. This will suit me for what I have in mind.
For me, generating stays at "Moving model to GPU ..." phase, and nothing happens anymore, even after couple of minutes. Someone knows how to fix that?
Hey man, thank you so much for this!!!! Appreciate the help. Let me ask you, I downloaded the MRE version, and it's not appearing those Styles for me, do I have to download them from somewhere?? I'm still new to this, getting to read the Wiki now. I appreciate any help you can give me!
the face swapper in foocus is amazing way better then other options out there. but it does NOT JUST seem to copy the face but hair, skin and apparently maybe even body type. awesome!
Nah the face swap is decent for sure though reactor or roop are straight up better, if Fooocus get's dreambooth and reactor I'd purely use it and holy crap does it make things easier plus the results are waaaaaaaaaaaaaaay more consistent in my time using it while also looking a damn sight better
I never bothered to try Fooocus cos I thought it wouldnt be as good as A1111 but your video convinced me to give it a try simply cos of how convenient it looks. Thanks for the video.
Ya it's much more convenient and faster. I also just link to my existing A1111 files so I can jump back into A1111 if i need the full control net suite. I'm not sure if all control net models are back up and working with SDXL though. Funny thing is Illyasville (the guy that made fooocus) is the control net guy so it's weird his tool doesn't have all of the control net pre processors.
@@ArtificallyIntelligentAi haha. That is indeed funny. Please do a followup video on fooocus mre as well, if possible.
@@SionMusica Already planning to do it. I need to learn a bit more about it first.
i've been playing around with fOoOcus for a few month now, and i still have an issue i can't fix.
i have 100s of food photos from back when i was a chef and want to use them in combination with my new table xD
it sounds odd but basically, i want to use fOoOcus to add those foods to my table, as if i snap a photo of them ON MY TABLE.
any idea on how i can make that haappen?
How can you update fooocus? Do you need to redownload it?
Thanks. Do you have a video how to install all this and SD on a Mac ?
Is there a way to get consistent workflow in the form of body position and what they wear ?
Right to the point and easy to understand, thanks.
Work like a charme and easy to use with my specs configuration on pc 👍😁
am using amd radeon graphics, which doesnt seem compatible with foocus installation, any advice?,,, also tried using it on google colab but no luck either, any advice? nb my pc cant support NVIDIA graphic drivers
I am very new to the AI image generation journey so it might sound silly. Can you let me know how can I use the image prompt to generate consistent characters or environment within fooocus. Can someone guide me to a step by step guide to get this, it will be a great help.
Joined and like put. Could someone tell me why every time I launch the run batch file it downloads 6.62 Gb (of what?) instead of opening the program for me? Any help would be greatly appreciated. I've a Laptop with a Nvidia RTX 2060 installed on it. Thanks!
is it possible using AMD graphic card??
Can I upload some of photo and change them to animation in one time ? Like stable diffusion 😢
I have 7zip but the fooocus win64 is still white for me after I downloaded it. What can I do?
Invoke AI is the solution for people who wants functionality without sacrificing any new features combine with easy interface. Much more advanced that Fooocus yet easy to learn. In addition, as you progress, you can use more and more advanced functions such as nodes, just like in Comfy UI, all in one common environment.
Do i need A good cpu to instal it and use smooth? Or do i need something like paid gpu online to run this and use it more comfy?
How do you do a negative prompt with Fooocus... am I missing something?
How can I make the page dark mode, everyone seems to have dark mode as default but my fooocus page is white
thanks for the help
hello is it possible to input a photo of a medallion for them to wear ?
this doesn’t run on my computer right is it my graphics card? It’s an hp pavilion windows. Any advice on getting it to work greatly appreciated
Its pretty bad that, when you create a low quality image to see if the prompt works, but you like the image that much and click the "quality" check mark, that it just creates a whole new image instead of the image you first saw and liked in better quality... am i missing osmething?
Can it run on my Radeon Graphics card? at least slowly generate images?
Does it takes 6GB whenver i run it???
Do you know how to enable low VRAM mode? the Command prompt tells me i may need to enable it - hence why it doesn't even start to generate images, I have 4gb vram but it should work, at least slowly right?
Same problem here. Up
Is it possible to create animations with fooocus?
broo i need all the characters like shinchan doraemon ben10 nad such cartoons which model or lora should i install
mate, why is it so slow on mac? it takes forever to generate images
Its been a few months, is this still the best free local option, or have people moved to something different?
We need video to how make multiple angle for character on fooocus plzzzzzzz
How to solve SSL Exception while running the bat file? 6:35
Can you tell us, how to use the same modell face over and over again? thank you
What’s weird is I download this and it’s just giving me an error but the run version works perfectly
i run a1111 on a gtx1070 SDXL1 is up to about 2min to render, newer sdxl1.5 up is faster, its a old 8gig card not issues at 1024 render size, i then do the upscale with gigapixle as its better than SD upscale where the vram can be a issue in that aspect. Easy diffusion is one click. I'll test Fooocus though.
Easy Diffusion is definitely more user friendly than fooocus for people that are new..
Yup 8Gig is the key for A1111 and the min req. but if you start playing with the resolution sizes you might get an out of vram error. My 1660TI with 6GB of Vram can't even do the 512 render that gets upscaled to 1024. I could do it with Fooocus though. I'm starting to prefer Fooocus > Comfy UI then > A1111. Still love A1111 but it can use some optimization and simplification.
@@ArtificallyIntelligentAi made a video to help the issue you are having in a1111 will fix your memory errors, plus figure after you do it you can pass the information to others also. this works for 2gig and 4gig NVIDIA laptops too I have read. i deep dived forums to learn about, lot of gtx960 users told me about it.
czcams.com/video/TbFRXDdWssI/video.htmlsi=wYxXYcth-RBkthhn
bro please tell me how to delete those files if download on cmd
but this work with intel arc???
Does this work on Mac?
Do any of these perform video-to-video face swaps with the same quality?
No but I'm making a video on that with insight. It's pretty easy to do but it doesn't run in Foocus.
No Linux version available?
Why does it take so long to generate an image on my pc?
can u tell me bruh how to delete those files it download on cmd
Hi, thanks for the tutorial. Could you tell why it doesn’t work for me and tell me: Connect error out . Can you help me?
that happens with me aswell
Great video but I want to know how to use the same person (the same face) with different poses?
I tried setting the seed but it doesn't work for some reason :(
Same, let me know what you find.
really useful . my laptop have only 1 gb vram. 16 gb ram
iris xe integrated card.
will this work on my laptop
doubtful
No
I dont wont to creat photo i need. Give fooocus some photo and convert them to ani photo. Can i make that worh foocus?
does it support AMD cards ?
I just tried to run it, and as soon as I hit generate, it says error in the picture creation window
Same have u figured out how to fix it
I think this doesn't tested on Apple iMac intel cpu. Anyone know?
The Config file didn't come with my download for the vanilla version. No mention of anything changing on the github page.
EDIT: Didn't realize it gets installed when first launching it.
Thank you
i have a standard Intel UHD graphics card and upon running fooocus it generates NVIDIA graphics card not found error. any way around it ?
You cant run it. This needs a dedicated gpu.
Im sure its great, ive seen it do amazing stuff. Unfortunately is just doesnt work on my RX 6700XT and i cant for the life of me get it to work.
This is indeed a cry for help, anyone got any tips lol?
so. i tried to make "someone" with robotic body. fooocus can't do it. whatever prompts you try - fcs doesn't understand what "cybernetic, robotic, cyberpunk, metall" means
A custom model from civitai can fix that
@@ArtificallyIntelligentAi do you have some guide on how to add and use custom models to fooocus?
What is your graphics model and vram memory to generate the images so quickly?
its a 4070 some of it was cut but with very fast it was a 5-10 second render and an average of 10-30 for normal quality images. Depends on the type of image.
@@ArtificallyIntelligentAi Not gonna hold you to it, but do you think that a 3060 with 12gb would do pretty well? I'm not too worried about the time it takes, moreso running out of ram
@@mastabas yes, better than my more expensive 3070 which only has 8gb of vram and the 3060 should still be pretty quick. The biggest concern is not having enough. 12 is pretty good and it gets super expensive for the 24gb models 3090 and 4090
its great
When prompting it shows connection errored out
same
I found the solution. I needed to update my Nvidia video card drivers
@@ViralEssentialsClips I found the solution. I needed to update my Nvidia video card drivers
@@pamoja1696 Thank you!
Cool :)
😃
I'm giving it a go but from the looks of my current rig, I'm still screwed. Thanks for this info, though.
You can switch to the v1.5 model that uses a lot less vram if your not trying to use sdxl specifically. I think it downloads it automatically but let me know if you need help trying that I can walk u through it. The base model isn’t great for 1.5 but on the site civitai they have really nice custom models comparable to sdxl
@@ArtificallyIntelligentAi Thanks a lot.
everything works fine untill I try to generate an image, it just shows a blank white image icon with nothing after a generation
Hi, have you tried changing the source image ? I had something similar happen where the face of the output what just white and blurred. Also what the console say? If it says something about a failed wheel for insight face you the newest windows visual c++ . In the official install guide if you click on windows there is a Microsoft visual studios tools python command. You can just copy and paste that into python and press enter and choose desktop dev pkg c++ when prompted or asked
hey man same problem here hit me up if u figure it out
I've installed it but when i prompt anything it gives me an error instead of an image
same thing
me too
I found the solution. I needed to update my Nvidia video card drivers
How do you turn on dark mode?
same question
@@v2iketiit165 you have to right click open the run.bat file and add this text to the path in the text editor: --theme dark
so it will be like this: .\python_embeded\python.exe -s Fooocus\entry_with_update.py --theme dark
Is there a way to upload my own image and generate images based on that image?
I installed it using python v environment and when I started prompting it shows connection errored out
Same, have you found any solution?
same
yeah same ,how to resolve
@@probanana8541 no I thimk it's because of less vram
same
How do I add models or checkpoints from CivitAI to Fooocus?
Look for SDXL models,. you can use SD1.5 models to refine but you have to use an XL Model for your base.
Hi, did you find out? Because i'm looking for that information right now
@@daniilhavrylov7046 No, sorry. The answer i got tells me what resources I need, but not how to implement them in Fooocus.
"oh man his nipples are torn off" the best quote in the history of quotes 😂😅😂
mine just says error after generating how can i fix this?
same
@@ViralEssentialsClips same
there is not Linear in ControlNet, this is bad
How to create a model with this? Just can use 4 videos as insert examples
Take 4 screenshots and set them as faceswap.
This is not the only one click installer, there is others on the market
I've seen a couple in the past that were discontinued or not updated. Which one click installer were you thinking of and is it better than this one? I'll check it out.
Pinokio Computer can install this with 1 click. 😍
i have error help please
did you fix it?
i have the same problem
👋
Is there any copyright by using it? Can I just share the generated pictures on instagram?
great question, what about real world publicity?
how to uninstall? thanks
same question
i thought u were going to cover fooocus mre??
I just left the link because the video was already too long and MRE deserves its own video with all the settings it has. TBH I need more time with MRE b4 I make a video on it.
By the way do you have a GitHub account count that starts with Moon something? 😉
Anyone know how to uninstall this? It's... Alright. I mean I get why people would use it, but it's not for me. I vastly prefer MJ. However, I can't figure out how the hell to uninstall fooocus. Deleting the folder isn't enough, there's still 8gb+ of shit SOMEWHERE that I can't find.
Music in the background is disturbing
I can never really tell on my end. I guess it's something I need to work on. Thanks for the feedback! Definitely going to keep it in mind for my next video.
Is there face swap?
Yes with a little combination of parameters and it's work like a charm 👍
does this allow nsfw prompts? I create fantasy / dragon pieces and sometimes there's nudity. I don't want to waste my time downloading something that's going to have a filter. Thank you.
Yes NSFW is fully unlocked.
I prefer Easy Diffusion
Wasting time if someone have lover then GTX 1050 TI, 15 min for one pic :)
TIC tok vídeo ? 🙄🤕Se puede o no ?
How come people say this is good. Every image generation costs around at least 5 to 10 minutes and puts my GPU to 100% like a fighter jet. I got way enough vram and a decent AMD GPU with correct settings. Quickly dropped it, waste of time.
It takes 20 seconds at 60 passes (quality mode) on a 16gb vram Nvidia gpu. It’s blazing fast!!
The background noise is so annoying that I could not follow this tutorial.
If you're going to provide an instructional video, you should be prepared to answer questions as well. What kind of teacher teaches, but doesn't answer questions?
I followed ur instructions but it says " "error, connection timed out" when attamepting to create an image.
Hy I'm having the same problem did u figure it out
@@EmmanuelNcube-pu8xh no i didnt. I use seaart now instead
same problem
same