MORE Consistent Characters & Emotions In Fooocus (Stable Diffusion)
Вставка
- Опубліковано 2 чер 2024
- We Have More Tips for Character Consistency With Faces, Expressions, and Emotions in SDXL Stable Diffusions Easiest UI, Fooocus.
In this I’ve shown you more ways to get different angles and different facial expressions. While Fooocus can be limiting in the advanced creation of images, there are still several ways to get what you want out of Face Swap and Consistent Character Creation.
Want to get a quick start? Here is the 4x4 Face Grid!: www.mediafire.com/file/uyvyzi...
If you wish, you can help support the channel:
www.buymeacoffee.com/jumpintoai
-----
00:00 Intro
00:40 Grid Creation
02:30 Character Creation
04:10 Expressions & Emotions
08:08 First Way To Use
10:32 Nighttime Tip
12:45 Second Way
14:35 Third Way
15:41 Bonus Advanced Tips
----- - Наука та технологія
Want to get a quick start? Here is the 4x4 Face Grid!: www.mediafire.com/file/uyvyzi4yfk2fgiv/4-face.zip/file
**EDIT** If getting a single image and not a grid of faces, make sure to put the 4x4 Grid to PYRACANNY setting.
Since I've previously explained this part a bunch, I went past it and some people are confused. Sorry!
ComfyUI Please Please 🙏🙏
That link isnt working.. neither one (in the description or above)
@DesignerVIsuals hmm still works for me, and it's still getting downloads according to the stats. ❓🤔
Just dropping in to share something exciting with my fellow content creators! As a newcomer to UA-cam, I've been all about storytelling and creative video-making. Recently stumbled upon VideoGPT, and it's been a game-changer, giving my videos that polished, professional touch.
Can’t find the initial tutorial you talked about.. :/
That's great! Thank you so much for a perfect and needed lesson!
Your video is the best I've ever seen on generating consistent characters. I hope you will continue to share more technologies in this area in the future, and I also hope you will share more advanced usage of Fooocus. 🎉🎉🎉
By far the most in depth explanation I've seen
Amazing work dude!
Hands down one of the best videos I’ve found on the topic
Subscribed! the only 1 channel that explained to details what and what does what, simply amazing. been wanting to change the face expression and this video teach just that. Thank you a lot for this video alone make huge dfferent for me, thanks bro 👍
You really get in depth but keep it easy. Really good at what you do.
Thanks! I appreciate the support 😉. 👍
Nice to hear and watch you again! Each time I get a notification of a new film on this channel I drop everything and run to UA-cam! :)
Thanks! I'm glad the videos are something to look forward to. Much appreciated. 😊
Good stuff
Cheers from Poland!
It's great! Thank you!👍
Thank you! Great technique, thanks for sharing
No Problem!
finally someone who knows how to do it. No bs!
Wow, this is an excellent tutorial that shows your perfect mastery of fooocus and image generation. Thank you so much
No problem! Glad to help show people other ways to get results.
Oooo I was looking for such videos a lot thank you 💕💕❤
You're welcome 😊
That's a lot for me to process now, but you did an excellent job here.
marvelousssssss!!!!
Great Video my friend...
awesome
👏👏👏👏👏
Wow! Amazing video Thank You very Much!
Welcome! Glad you liked it!
Ah this is great. thanks so much
Thank you so much 😘👍🤝
Awesome video and awesome channel man!
Is there a good way to keep landscapes and environments consistent too?
Good JoB, Nice ; )
Bien!!! gracias... quisiera ya que una vez venga los videos ai de Sora
Wow really great video didn’t know that fooocus had so many features. Did you try training a lora with the faces you generated or do you have any experiences?
I have done LoRAs from generations with mixed results. I haven't put enough work into training since it can be frustrating, lol.
I wonder if you could use similar techniques to change the weather and lighting of a scene.
Hi, Your teaching is very excellent. REQUESTING YOU PLEASE MAKE VIDEO IMAGE FULL POTRAIT (MEANS HEAD TO TOE) IN ANY POSE AND ANY EXPRESSION. THANKS
First of all I want to congratulate you for the extraordinary way you explain the procedure. Your explanation is very precise and, at the same time, didactic. What was a great addition is the "Disable Seed Increment" option to create multiple images with the same SEED and PROMPT.
In the procedure you start with a detailed PROMPT (t 3 min 32 sec). The question is: How to start the process with a reference image (instead of a PROMPT) from which you want to create different emotions?
When doing it this way, having the prompt, the pyracanny grid, and the same seed. We can get emotion without compromising the original image because we are only adding in one or two words to all of that information.
When putting in an image and trying to get emotion without anything to holding the face to its original form, you will get what you want but not without the character details changing too much.
What you can try is putting an image into the "Upscale or Variation" and using the "Vary(subtle)" and simply put in the emotion in the text prompt. It's better if the face is majority of the image as then it wont change as much as if the face was far away.
You can also try going into the debug menu on the debug tools tab and go down to (Forced Overwrite of Denoising Strength of "Vary" ) and change the denoise level of that. Vary (subtle) starts at 0.5 so try going down to 0.4 or lower if the image is changing too much.
@@JumpIntoAI Hi, also thanks from my side for your excellent tutorial! It helps a lot.
I was first creating multiple models to then later choose the one that I'd like the most. When going back to create the emotion grids, would you approach it in the same way as pointed out above, or does the seed + details from the log help me in any form to start from the selecting your model point?
Thank you in advance!
Edit: Nevermind - the log file usually helps to get back into the editing
@@JumpIntoAI Hi, I have the same problem, I generated the model I wanted, but when I tried your process, it changed the model even if I lowered the Forced Overwrite of Denoising Strength of ‘Vary’.
I get stuck on this step
Awesome video! how you would advice to change the hair style and color?
you can prompt for it in the generation, if that doesnt work well enough you can change it in inpaint after.
If wanting to change the grid of 4 you can mask all 4 subjects hair and try to change at once with inpainting.
I watched the videos and created my virtual model, thank you very much. What if I have rings, necklaces and earrings, and I want to create photos in which the virtual model is wearing these pieces?
How hard is it to get a model and train it to learn a new persona. Eg: you can use meganfox in the promp to generate stuff with her face.
Maybe you can train the model to learn a new entity and if you use that in the prompt, generate everything with the entity face/hair/body ?
Could you do a training on that?
You are really awesome btw
with the grid that I uploaded created by you I can't understand why on the first pass the 2 images below are merged into a single one the two above are done correctly, on the second pass all 4 images are corrected, but why on the first pass does it give me that error?
best
i have already created ai character through tensor art, how can i achieve consistent face angles?
Great video! But how'd you get the images at 8:20 to have no background?
Used a background removal tool after I split them. If you are on windows even MS paint has one, not as great as others but a pure white background like that is easy to remove with it.
thanks for clarifying @@JumpIntoAI
Awesome videos, I'm binge watching your channel! Is there a reason why you chose only 4 head positions? And How does the Weight and Stop At parameters actually work?
And I really liked the "[[happy, laughing, angry, crying]]" prompt, I didn't know it was possible to do that. Is it possible to do something like that, but to generate sequential images, like a person standing up? Do you know a reliable way for making this kind of sequential images?
I used 9 head positions before which worked but since the heads were smaller the quality of each was lower. So i switched to 4.
stop at and weight can be difficult to understand at first.
ua-cam.com/video/0vzunoCYiMI/v-deo.html
that explains it some but might still be confusing.
As far as the array function and adding actions I haven't tried. All depends on the image really, asking a closeup face to smile is different than asking a character to do an action. But always worth a shot!
@@JumpIntoAI Ah ok, I'll check that video.
Do you know situations other than facial expressions, where this type of array function can be used? Or other possible array functions?
For example, I was wondering if it's possible to vary other parameters like adding a awway for the function to generate 4 images, each one with values equal to 0.5, 0.6, 0.7 and 0.8, in the same prompt, like the facial expression array, in order to generate each image with a different set of variables.
And another question, if I'm not already being an annoyance... Kkkkk Is there a good way to alter specific characteristics of a character while prompting. For example, if I just want the right arm to be up, or the left leg to be sideways... I was struggling with that a lot yesterday. @@JumpIntoAI
IT seems that this array function works for clothes colors, interesting.... But I couldn't find online a reference for the term "array function" used in this context @@JumpIntoAI
@@BiancaMatsuo The array function was only added in 2.2 a few weeks ago so haven't tested it myself extensively. But right now generating different weights with a lora automatically isn't possible, actually the lora text prompt command like that doesnt work in fooocus (but i think they are looking to add it) so possibly in the future.
If I already have the character beforehand, how do I swap the faces into the 4x4 face grid instead of creating a new character from scratch like you did?
Can you make a video on how to change the weather in photos or how to make photos at night of the same scene?
Hello, how are you? I wanted to ask you, I was testing with focus, and I can't get it to generate full body images. Do you have any idea if there is a specific checkpoint/models to create those images? Or do I just have to generate the prompt in another way?. Thank you very much, i'm learning a lot from your videos.
Yes there are a few ways to achieve this, the best is to describe the subject from top to bottom. Like, "A woman wearing a t-shirt, jeans and cowboy boots." adding in their shoes helps as it will want to include what you are describing so it will be more zoomed out.
Also describing their surroundings. especially items that are bigger than them like. "A woman wearing a t-shirt, jeans and cowboy boots. Standing next to a lamppost. "
If still having trouble, you might try removing the 3 default fooocus styles in the "Styles" tab. they tend to lean more towards portraits.
@@JumpIntoAI Ok, i'll try that. And this works with any models? Or some models are trained to create portraits only?
Thx for the tutorial buddy😀 when I'm swapping face in collab with mixing img and inpaint I always get error... So is there any way to fix it
google collab has limited gpu credits in the free tier which fooocus quickly maxes out. Only solution to this is to either switch to a paid tier or run it on your own system.
@@dhruvarora2995 so is there anyway to generate high quality background or blend things perfectly with face swap and then typing prompt manually?
I already have a face that I've been using but i want to use this tutorial to have the possibility of having better images, how could I do it? I have the image of my face
I'm not sure how you got your character to do emotions, starting at 4:30. Is it because you generated everything from the seed that gave you the original 4 faces and then kept that seed and prompt?
I personally built my 4 faces quadrille some other way (using stable diffusion) because I didn't want to rely on luck to get a face I like. But now that I have a face I like and want to give it emotions, I can't seem to be able to do it using your technique. I have followed every step of your video multiple times but end up very short on the expected results. I have tried different models like juggernault and stockphoto, but the results are way, way off. Help please?
This method really only works with generating an image first, all the factors like the prompt/seed/grid faces/ stop at & weight settings, all hold the image close to the original and changing just a word or 2 for emotion is why it works.
Nothing changes the pose for me. My model always has the same pose on the park bench. Can someone please help me?
Where can I get the model you use in this video RealismEngineSDXL ? Thanks!
all models from CivitAI
civitai.com/models/152525/realism-engine-sdxl
cool tutorial, thx. where can i download these models 3:08?
CivitAI, just set the filter on there to SDXL 1.0>Checkpoints. Those are all the base models that can be used in Fooocus.
What if i already have a face that i created but i want to use this method? Would i need to do faceswaps with the grid and then move on from there with the emotion arrays???
With this specific method no. It will be a different face. The reason I can create different emotions is because I am using the exact settings/weights/prompts/seed/model that created the original and tweaking just one or two words. So it wont change much.
@@JumpIntoAI ok. Thanks. Makes sense
How to force it to generate 4 faces in one picture? I've added that sheet to image prompt but it keeps generating just one face at a picture. Increased weight to 1.0 but it still ignoring it. Using juggernautxl9 model, turned all filters and negative prompts off.
is the 4x4 grid set to pyracanny?
@@JumpIntoAI Thanks a lot! I've missed that part in the video..
I'm actually struggling to get even or 'flat' lighting in my images. Every image fooocus generates feels like it has studio lighting or a rendered quality to it. Any way to fix that?
First is to uncheck the 3 default "styles". They lean towards that studio look.
Hello! Could you help me please? I have an issue with running Fooocus. Its says RuntimeError: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver. I have amd gpu.
AMD gpu aren't officially supported (its a stable diffusion problem not a fooocus problem) but there are ways to get it to work as long as it is a beefy card.
Fooocus install page has a few things you can try to get it to work. github.com/lllyasviel/Fooocus?tab=readme-ov-file#linux-amd-gpus
Or this person created a little tutorial to get his amd gpu to work
github.com/lllyasviel/Fooocus/discussions/2552
@@JumpIntoAI Thank you!)
hi, I did all the steps you did but when comes the time to generate the faces on the 4 different 3d heads, it only gives me a weird colored square. Anyone would know why?
Just to check. you have used fooocus fine before trying this yes? Are you on google colab or using this on your own computer?
What model/checkpoint are you using?
What is your GPU if using on your computer?
How do I reach out to you privately?
@JumpIntoAI bro, pls make video about how to fix fingers, because it's the most hardest thing to fix with inpaint, is there any good setting to guaranteed or at least make it better to fix the fingers and hand deformed?
Yes, I also need it
Fingers and hands are still a pain. Especially if they are closer to the camera, and holding hands or ones with the fingers interlocking are nightmares. I usually end up hiding them if i can. But I have fixed them in the past with some basic photoshop (just separating the fingers) and then running again in Fooocus inpaint.
If I can come up with something that isn't too complicated that works I will make a vid.
@@JumpIntoAI thanks a lot bro, nice idea, cut them off and run it again, should be easier for the AI to regenerate whole new thing.
@@AxelWXChannel Yep, I have even found a 3d hand that i spent hours getting the right angle and then low denoising in inpaint over and over to blend in naturally. But it was way too much work than it was worth.
Would you please upload a video to train dreambooth in cloud services like colab or kaggle,,,,,(Not lora,,,,, dreambooth ckpt) .......
tell me abit about your spec computer . and render time per image ..thank you.
AMD Ryzen 7 3800X
32gb Ram
4070 Ti 12gb Vram
Images take around 12 seconds to generate each
It only generates one front facing image for me not the grid.
any ideas to kepp consistent clothes and faces on faceswap?
If you describe the clothing in detail you can get similar clothes in generations. But its hard to get exactly the same. there will always be slight variations in shape and color, especially if the clothes you want are specific looking.
You can also go back and try to inpaint clothing to change it, especially if its close to what you want and just needs a color change or a missing button, etc.
Thans a lot for your videos! I'be been following your videos about consistency and more or less you can get a good face consistency, but whay about the body? Famous AI influencers have a perfect consistency, and would be great to know how to do it. Thank you!!
One thing to remember is those people probably have some resources in post processing and perhaps some well trained LoRAs. And I bet they still generate hundreds of images for every one good photo.
But to do this yourself isn't impossible if the clothing you want is not isn't very specific, doesn't have lots of minor details, and no words or logos.
With a lot patience and skill with inpainting it could work.
If I come up with a workflow that makes sense I will make a video about it.
@@JumpIntoAI I've thought that using a body created in 3D (created with daz3D, Blender or similar) , you can render it and after that, use AI to make a faceswap on the render. So, you'll always have the same body (sizes of chest, hips, etc..) Even you can change clothes, make physics on clothes, etc..) I don't know if it'd be possible ,I'm only thinking in loud voice :)
Hi, I need advice. Why am I only seeing one Base model?
You need to download additional models. CivitAI is the main site for this. Just use the filter in the model tab and look for SDXL 1.0 Checkpoints.
How to get 6th Lora
Someone help me I have I7 12700kf Ram 32G
GPU 1660S but when I generate image on fooocus need to spend Around 1-2min per image any help ?
Have you tried using a Lightning Model?
@@JumpIntoAI I get this from Civit Ai that’s name Realities edge XL lightning+ turbo that one brother ?
I’m installing fooocus on hdd if I change to install on SSD that’s have some change for me or not brother ?
And if this 1660S 6GB too slow for this Fooocus ?
@@zeezee4760 Yes an SSD will help. and Yes any of the lightning and or turbo models will help since they use less steps (3-8). They do need specific settings and changes made in the advanced/Debug mode to get them to work correctly.
ua-cam.com/video/DRcxsqnhjws/v-deo.html
That will show you what settings need to be changed.
that gpu is on the low end but I would try out the lightning models and see how much it improves.
@@JumpIntoAI I’m followed ur step brother but still too slow to generate a image with only 4-6 steps but quality is quite good love it maybe I need to upgrade my GPU
Can the same be achieved in Forge?
This method isn't tied to Fooocus. I can't say for sure the results without testing it but I have used something similar in A1111 in the past with no problem. So I don't see why not.
How to install Model Realism engineSDXL ? thanks
you can download it from CivitAI and place it into your fooocus\models\checkpoints folders
civitai.com/models/152525/realism-engine-sdxl
what is your gup and system ?
AMD Ryzen 7 3800X
32gb ram
4070 Ti 12gb
(I do speed up the video during generations)
Unfortunately, it doesn't work for me. I don't get a grid. Only 2 images are generated on my end :(
in the 4x4 grid select PyraCanny
@@ljimenez29oh thx
ComfyUI Please
Why u stop uploading .... can u make videos how u can change weather in forest like that or the light or darkness
how did you install your stable diffusion?
github.com/lllyasviel/Fooocus?tab=readme-ov-file#download
Easy install if you have Windows.
thanks, i watched some other videos while i was waiting and found comfydo you know if its also possible to generate multiple angles of a face from a single reference photo like you did in the original video?@@JumpIntoAI specifically "Create Consistent Character Face/Body/Clothes From Multiple Angles" at 0:33
@@infectioussneeze9099 Yes you can face swap with a single photo and get different angles. It can be hard to do and keep the consistency since you will need to turn down the steps and weights, otherwise the face will always be the same angle or close to the original photo.
One way to help is using a photo of a similar face in the position you want set to pyracanny slot, and then your reference photo set to face swap onto that.
can't i take 60 pics and create a lora instead?
Yes! A well created LoRA is much more efficient in the long run for a single subject. But it can be too confusing for most people to do themselves and not free to do online. Other alternatives are always nice.
its not generating 4 images only one img how do I fix it
Using the 3d face grid in the input image section? Pyracanny selected? 1024x1024 resolution? if its blending into a single face by the end, the stop at needs to be higher. If its generating a single face from the beginning than there is a step your missing in this process.
@@JumpIntoAI thanks I fixed , was not on PyraCanny , good videos
Lots of effort to get one good image.
I don't understand why but the grid doesn't work for me, it generates just one face
Is the grid set to pyracanny?
i could not get 4 different photo as like you
Make sure the 4 face grid is set to pyracanny
Thanks, also had this problem.
@@JumpIntoAI yes but still not working
ReActor in controlnet is far, far better, in any way possible
I agree that it is overall a better tool out of the box, but it still suffers its own issues with blurry or too smooth skin. And really, this is for people stretching the limits of Fooocus.
就问网红照片是不是你做的？
Okay, time to switch to Windows 11.
Midjourney released amazing consistent character feature! But sadly its Paid! 😢
Indeed! I Kind of wish I got this done a few days earlier, lol. But thats ok. Like you said, paid vs free!
dood use roop, this is overkill
I agree! I prefer Reactor in auto1111/forge. But lots of people don't want to move beyond the easy interface of fooocus so i like finding ways to stretch the limits. I might be beating a dead horse by now, but, oh well.
@@JumpIntoAI Your def not overdoing everything. This is great and cool to learn. Gives people who are willing a bit more insight to how all this is working.
@@JumpIntoAI roop just takes less time, its exactly for something like this, imoi you should mention it at the beginning that theres easier faster way but needs auto11
I wish people would stop making tutorials only for specific types of Stable Diffusion... how about A1111?
Well, you can't please everybody. This method works fine in A1111 also.
Omg, just be thankful
It’s not a type of SD! It’s just an interface. You can make it even without any interface using script.
Thank you for making this amazing video❤🔥 I'm having some problems learning it though🥺 When I follow your steps, the generate image is not 100% guaranteed to be a 4x4 face grid image… Most of the time it only generates a single image that resembles a portrait😣 Everything I have is consistent with what you show in the video, except for the prompt words. I'm a fooocus newbie and I'm not sure what the problem is😭😭😭 Maybe you know the reason why this is happening🥺 Looking forward to your answer😭🙏🏻 Infinitely grateful
You do get some images that are 4 faces yes? If it only morphs to one image some times then you might need to turn the "stop at" up some on the image grid. The grid is set to pyracanny correct?
@@JumpIntoAI So it is! It's because I didn't set the grid to pyracanny!!! a million thanks to you!!!!❤🔥❤🔥❤🔥❤🔥❤🔥
@@QianruLiu No problem. I have done a few videos on the basics of this so I went a bit fast. I realize I didn't mention that setting this time. My fault.