If you find the video useful and would like to tip you can buy me some electricity for all these image generations. It is greatly appreciated! ko-fi.com/kleebztech
Nice exercise! Abandoned rusted shell old vehicle shell worked for me...most of the time. But I struggled before reaching that conclusion for many, maaaany generations. Had to turn off styles, as you said, and add "no humans" to it, otherwise a nice lady kept appearing with default Juggernaut V8
That is a fun exercise - the car with no tires. The attempts I've been trying... sometimes I get a car up on a pallet load of cement blocks, or a car with a bunch of cement bricks around the tires. Or instead of the tires. You can almost see the engine fighting it as it generates. I was a bit surprised when even my quick attempt with vary(subtle) using a real photograph failed as well. Only upscale worked, and I was starting to doubt that it would. I could get it to inpaint bricks into an empty wheel well. It didn't want to, but it did.
HI, very interresting video ! Thank you ! FDor newbies, Prompt is a really hard thing to understand... I always meet difficulties with eyes and hands, they are so often weird - no matter I ask in Prompt or negative prompt I wand realistic eyes or hands, Fooocus always made some Quasimodo eyes and hands with 9 fingers :D (more or less)
Hello Kleebz. Thank you for all the tips and information. I have a question for you. In the civitai website, there are these poses, which are skeletons made of colored sticks making a pose on a black background. Is there a way to use those with fooocus? Thanks again and great video!
Sounds like Openpose. Fooocus does not support that yet but I think it may in the future. I do know there is a fork of Fooocus that supports it but that fork last I checked was way out of date. I have used with other tools and have mixed feelings on how well it works. Works better with SD 1.5 and not so good with SDXL. But would be nice to see it added.
Introduction and Overview - 00:00:00 Basics of Prompting - 00:00:54 Starting Simple and Building Up - 00:01:48 Using AI Tools for Prompts - 00:02:55 Elements of a Good Prompt - 00:03:22 Experimenting with Prompts - 00:04:57 Fooocus V2 Prompt Processing Engine - 00:05:29 Negative Prompts - 00:07:07 Prompt Weight - 00:08:17 Example of Prompt Weighting - 00:09:28 Multi-line Prompts and Blending - 00:10:54 The Association Effect - 00:12:47 Bias in Image Generation - 00:13:35 Common Mistakes in Prompting - 00:14:46 Prompt Challenge - 00:15:24 Conclusion and Additional Resources - 00:15:56
useful turtorial thank you for that, with the multi-lines can you also organized your prompts. as example i used like that A Dog runs into a dark forest (describe the scene) 1dog, white fur, bulldog (describe your character) dark lightning, full moon, a wolf runs behind the dog (lightning and more details) i dont know that you can merge with multi-lines characters or objects that is pretty awesome
I did a little experimenting with multi line prompts and don't think you would get the expected results separating sections of prompt on each line. You will get some of what you might expect but not all. At least what I messed around with. For example I just tried using the ones you just listed and never got a full moon or a wolf. But once I combined on one line it did give me those more often.
@@KLEEBZTECH ah okay, i havent this issue and i use this Multi-line method only too organized my prompts because you know sometimes if you want something good you make a mess with many prompts and i have often this problem that i dont understand what prompts mess up my image and with this method i can play around which word make a clown out of me 😄
8K just refers to 8k resolution like 4k. Just terms used to try to get higher detail usually. Using different camera terms can have an impact on your prompts. I am not sure I if I tried tireless yet but will have to give it a shot tomorrow. 👍
Hello, I have learned a lot from your videos dedicated to foocus, I am from Chile, I would like to know if I use foocus and change to stable diffusion with the same models, would there be a difference? Although I still prefer foocus. Thank you very much for your videos 👍🙌
If you mean use other Stable Diffusion tools like A1111 or ComfyUI you will get different results. Fooocus has some backend tweaks. Fooocus is much easier to use but the others do have some benefits in some cases. I use several myself.
@@KLEEBZTECH The fact is that I made an Ai influencer created in foocus, but I want to use loras 1.5 but they don't work in foocus. If I use the same model in stable diffusion, the realisticstock, would it have different results for the influencer?
I might not be the same but probably close. Hard to say without trying. Just to mention you can use 1.5 LoRAs if you use a 1.5 model as a refiner in Fooocus but not sure how much that will effect your influencer. But I find that any LoRA is going to have an impact on the results as well.
@@KLEEBZTECH Thank you very much. What you give us is priceless, I`m serious. Fooocus is a great but without knowledge it is just a golden tool. Thank you for this.
Thank you for the feedback. Currently limited time to create more videos right now but should be back to more regular uploads soon. Actually have a couple in the works.
So it does not check off the box when you click on it? Weird. Have you tried a different browser? Is it actually applying the styles if you do click on them? Have you checked the log to see?
@@earlsargent105 Do you have issues with any of the other checkboxes in the interface? If not then might have nothing to do with the browser. But if you have a different browser installed you would just need to enter the same address in the address bar and it will open in that browser.
@@KLEEBZTECH I have the same issues with all the checkboxes in edge but when I oped opera they all work. The styles do not show up in opera but I checked the symbol and it is rotating so I am waiting to see if they show up. They showed up. Now I am checking to see if I can modify the run programs to open opera instead of edge. Thank You for your help.
I wonder if there is something blocking certain things. I just tested in Edge and it all worked for me. I normally use Brave without issue and I also know Chrome should have no issue.
Can you please give an example for a realistic soldier holding realistic weapons? Whenever I try to give similar prompts, the subject is not as close as I’d like, the eyes are crossed, and the weapons don’t even remotely make sense. Don’t even look like weapons most of the time. I’m brand new to this
@@KLEEBZTECHOkay, and do you have any videos that explain what all of these things are and do? I am brand new at this and I don’t know what loras are/do, as well as a lot of other things. I downloaded and added some models in and they show in the dropdown lists but then nothing generates when I use them. I’ll hit Generate and then it’ll think for a second and then stop
Oh, I have many videos on all aspects of Fooocus. Will mention that many of my videos may seem to be for something you might not use but will show how things work so can still be useful. For example my text videos are geared towards text but will also teach many aspects of inpainting that can be used for other things. ua-cam.com/play/PLSofK8pvSk5oHH9iNAAemQREADEY7CPp_.html
Bro the problem I’m having is the image of a person or animal is always looking at the camera. I prompt by say man looking up into the sky and the guy will be looking into my eyes lol. Please help me with this
Are you describing details of the face? If you describe things like eye color and such that will happen. Also use things like casual for example can help. But really the big thing is usually describing facial details will cause that to happen.
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.
You will need to follow the instructions for AMD devices. You need to add more to your run.bat file. Will warn that AMD will be pretty slow. See here: github.com/lllyasviel/Fooocus?tab=readme-ov-file#windows-amd-gpus
As for Colab is it after some time or when you first try? Because what will happen with Colab is when you hit the usage limits it will not allow you to use with a GPU until the limit gets lifted the next day. I will say I don't use often on Colab so not super knowledgeable about using on it.
@@KLEEBZTECH I played with this some more today and just had fun with it "automotive manual exploded view of (entire car) brakes, suspension, engine 1950's"
I appreciate that. The situation is when I am trying different variations of input images. I'll drop an image of a portrait into the Upscale/Variation window, checkmark Vary (Subtle), add some text prompting; usually a sentence followed by some descriptors: "a bi-racial man with blue eyes and a buzz cut dressed in golden full armor, white background, solo, looking at viewer, smile, blue eyes, simple background, black hair, 1boy, white background, upper body, male focus, teeth, dark skin, armor, grin, dark-skinned male, shoulder armor, portrait, pauldrons, realistic, gold armor, golden armor, solid gold breastplate, mixed ethnicity," Presets are on: Realistic, Speed, 1:1, PNG, and the Negative Prompt will have "unrealistic, saturated, high contrast, big nose, painting, drawing, sketch, cartoon, anime, manga, render, CG, 3d, watermark, signature, label" Selected Styles: Fooocus V2, Fooocus Photograph, Fooocus Negative. Base Model, usually one of these checkpoints; juggernautXL_version6Rundiffusion socarealismXL_vae30 sdxlTripleHeadedMonkeys_v10 realisticStockPhoto_v10 devlishphotorealism_sdxl15 Sometimes with or without a Refiner (from the same list of checkpoints) Only LoRA would be SDXL_FILM_PHOTOGRAPHY_STYLE_BetaV0 (weight 0.25) No settings on the advanced tab are changed. I will get ear rings 90% of the time. I will add to the Negative Prompt line of text: "no ear rings, no earrings, no ear-ring," etc Still around 85% of the time I'll get ear rings. I'll try adding to the text prompt: "empty ears, bare ears," etc I'll get ear rings 95% of the time then. I blame the checkpoints, but I do like the other results I get from using them. I think the real solution will be inpainting, but I haven't tried that yet. I'm sure that is something you have covered in your videos, so I'll poke around and look. If you ever do a video on using Oobabooga's text-generation-webui to implement the use of Fooocus I'll be very interested in seeing it!!
@@marshallodom1388 interesting. My first thought was you had the Masterpiece style enabled and that includes the word earring. I'm not seeing anything that stands out that would explain it but I'll think about it. Does it do it when just generating as well? Or just under the vary/upscale section? As for negative prompt, just put earrings, no need to add the word no. Negative prompts only have minimal effect but also you can add extra weight (earrings:1.5) for example.
@@marshallodom1388 I wonder if using the word gold is part of the issue. That gets into the association effect. Often that's the sort of thing that causes these things that I find.
If you find the video useful and would like to tip you can buy me some electricity for all these image generations. It is greatly appreciated! ko-fi.com/kleebztech
A couple of more useful tips to tuck under my hat. Understanding how AI interprets really helps too. Thanks again!!
Happy to help! So many little things and I am always finding new things the more I experiment. The association effect is actually a big factor.
I fed your old car on blocks prompt into ideogram and 2 of the 4 images nailed it!
Some of these are starting to get better at understanding prompts. Good to know.
All your videos explaining how Fooocus works are really awesome. Thanks a lot, you're the best. Greetings from Argentina. 😄
Glad you like them! Fooocus is a really good tool and keeps getting better.
Nice exercise! Abandoned rusted shell old vehicle shell worked for me...most of the time. But I struggled before reaching that conclusion for many, maaaany generations. Had to turn off styles, as you said, and add "no humans" to it, otherwise a nice lady kept appearing with default Juggernaut V8
Excellent. I'm still trying to find a way of getting a newer car without tires as well. That one is pretty tough.
That is a fun exercise - the car with no tires. The attempts I've been trying... sometimes I get a car up on a pallet load of cement blocks, or a car with a bunch of cement bricks around the tires. Or instead of the tires. You can almost see the engine fighting it as it generates. I was a bit surprised when even my quick attempt with vary(subtle) using a real photograph failed as well. Only upscale worked, and I was starting to doubt that it would. I could get it to inpaint bricks into an empty wheel well. It didn't want to, but it did.
Love it! I like doing these because it gets you to think about how the AI handles things.
I think that if you see the engine fighting the results it means that you should turn something off
@@marcelobaus Indeed; the generation of the tires is what I was working to stop.
Thanks for the useful video!
A possible way to not use a negative prompt is to use an antonym as a positive prompt))
Absolutely!
HI, very interresting video ! Thank you ! FDor newbies, Prompt is a really hard thing to understand... I always meet difficulties with eyes and hands, they are so often weird - no matter I ask in Prompt or negative prompt I wand realistic eyes or hands, Fooocus always made some Quasimodo eyes and hands with 9 fingers :D (more or less)
Eyes and hands you will want to fix with things like improve detail function of inpainting.
Hello Kleebz. Thank you for all the tips and information. I have a question for you. In the civitai website, there are these poses, which are skeletons made of colored sticks making a pose on a black background. Is there a way to use those with fooocus? Thanks again and great video!
Sounds like Openpose. Fooocus does not support that yet but I think it may in the future. I do know there is a fork of Fooocus that supports it but that fork last I checked was way out of date. I have used with other tools and have mixed feelings on how well it works. Works better with SD 1.5 and not so good with SDXL. But would be nice to see it added.
Introduction and Overview - 00:00:00
Basics of Prompting - 00:00:54
Starting Simple and Building Up - 00:01:48
Using AI Tools for Prompts - 00:02:55
Elements of a Good Prompt - 00:03:22
Experimenting with Prompts - 00:04:57
Fooocus V2 Prompt Processing Engine - 00:05:29
Negative Prompts - 00:07:07
Prompt Weight - 00:08:17
Example of Prompt Weighting - 00:09:28
Multi-line Prompts and Blending - 00:10:54
The Association Effect - 00:12:47
Bias in Image Generation - 00:13:35
Common Mistakes in Prompting - 00:14:46
Prompt Challenge - 00:15:24
Conclusion and Additional Resources - 00:15:56
You're videos are so awesome ! No wonder Mashb1t recommended your channel to me !
useful turtorial thank you for that, with the multi-lines can you also organized your prompts. as example i used like that
A Dog runs into a dark forest (describe the scene)
1dog, white fur, bulldog (describe your character)
dark lightning, full moon, a wolf runs behind the dog (lightning and more details)
i dont know that you can merge with multi-lines characters or objects that is pretty awesome
I did a little experimenting with multi line prompts and don't think you would get the expected results separating sections of prompt on each line. You will get some of what you might expect but not all. At least what I messed around with. For example I just tried using the ones you just listed and never got a full moon or a wolf. But once I combined on one line it did give me those more often.
@@KLEEBZTECH ah okay, i havent this issue and i use this Multi-line method only too organized my prompts because you know sometimes if you want something good you make a mess with many prompts and i have often this problem that i dont understand what prompts mess up my image and with this method i can play around which word make a clown out of me 😄
I wonder if "tireless" would work for the car...
By the way, what does "8K" do in prompts?
Thanks for all your helpful videos!
8K just refers to 8k resolution like 4k. Just terms used to try to get higher detail usually. Using different camera terms can have an impact on your prompts. I am not sure I if I tried tireless yet but will have to give it a shot tomorrow. 👍
Super Job 👍👍👍👍
Thank you 👍
Hello, I have learned a lot from your videos dedicated to foocus, I am from Chile, I would like to know if I use foocus and change to stable diffusion with the same models, would there be a difference? Although I still prefer foocus. Thank you very much for your videos 👍🙌
If you mean use other Stable Diffusion tools like A1111 or ComfyUI you will get different results. Fooocus has some backend tweaks. Fooocus is much easier to use but the others do have some benefits in some cases. I use several myself.
@@KLEEBZTECH The fact is that I made an Ai influencer created in foocus, but I want to use loras 1.5 but they don't work in foocus. If I use the same model in stable diffusion, the realisticstock, would it have different results for the influencer?
I might not be the same but probably close. Hard to say without trying. Just to mention you can use 1.5 LoRAs if you use a 1.5 model as a refiner in Fooocus but not sure how much that will effect your influencer. But I find that any LoRA is going to have an impact on the results as well.
Thank you, it is priceless. Just one question: where are wild cards? :) It doesn`t seen on the video.
I do have a video on wildcards if that is what you are looking for. ua-cam.com/video/HnxkE281oUM/v-deo.html
@@KLEEBZTECH Thank you very much. What you give us is priceless, I`m serious. Fooocus is a great but without knowledge it is just a golden tool. Thank you for this.
Thank you for the feedback. Currently limited time to create more videos right now but should be back to more regular uploads soon. Actually have a couple in the works.
@@KLEEBZTECH This was not a feedback, this was a recognition :)
Hey buddies, i am getting typed storage is deprecated error...any idea how to resolve?!
thanks
Welcome
Could you help me understand why when i click on styles I can't tell when something is selected? I enjoy your videos and have learned a lot. TIA
So it does not check off the box when you click on it? Weird. Have you tried a different browser? Is it actually applying the styles if you do click on them? Have you checked the log to see?
@@KLEEBZTECH I don't know how to open in a different browser. It does apply the styles. I checked the log and it showes the styles selected.TIA
@@earlsargent105 Do you have issues with any of the other checkboxes in the interface? If not then might have nothing to do with the browser. But if you have a different browser installed you would just need to enter the same address in the address bar and it will open in that browser.
@@KLEEBZTECH I have the same issues with all the checkboxes in edge but when I oped opera they all work. The styles do not show up in opera but I checked the symbol and it is rotating so I am waiting to see if they show up. They showed up. Now I am checking to see if I can modify the run programs to open opera instead of edge. Thank You for your help.
I wonder if there is something blocking certain things. I just tested in Edge and it all worked for me. I normally use Brave without issue and I also know Chrome should have no issue.
Can you please give an example for a realistic soldier holding realistic weapons? Whenever I try to give similar prompts, the subject is not as close as I’d like, the eyes are crossed, and the weapons don’t even remotely make sense. Don’t even look like weapons most of the time. I’m brand new to this
I would suggest using inpainting to fix things like that. Or looking for models that might work better for that including Loras.
@@KLEEBZTECHOkay, and do you have any videos that explain what all of these things are and do? I am brand new at this and I don’t know what loras are/do, as well as a lot of other things. I downloaded and added some models in and they show in the dropdown lists but then nothing generates when I use them. I’ll hit Generate and then it’ll think for a second and then stop
Oh, I have many videos on all aspects of Fooocus. Will mention that many of my videos may seem to be for something you might not use but will show how things work so can still be useful. For example my text videos are geared towards text but will also teach many aspects of inpainting that can be used for other things. ua-cam.com/play/PLSofK8pvSk5oHH9iNAAemQREADEY7CPp_.html
How do you make the wildcard?
This should help. Wildcards have changed a little with more functionality but creating them is still the same. ua-cam.com/video/HnxkE281oUM/v-deo.html
Without tires or without wheels? How about "wheels off"?
No luck, but by including the word wheels it is also more likely to include wheels.
Bro the problem I’m having is the image of a person or animal is always looking at the camera. I prompt by say man looking up into the sky and the guy will be looking into my eyes lol. Please help me with this
Are you describing details of the face? If you describe things like eye color and such that will happen. Also use things like casual for example can help. But really the big thing is usually describing facial details will cause that to happen.
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.
You will need to follow the instructions for AMD devices. You need to add more to your run.bat file. Will warn that AMD will be pretty slow. See here: github.com/lllyasviel/Fooocus?tab=readme-ov-file#windows-amd-gpus
@@KLEEBZTECH Thank you very much! Its working!
Also i have the same issue with google colab fooocus and its confusing since it is running on their server
As for Colab is it after some time or when you first try? Because what will happen with Colab is when you hit the usage limits it will not allow you to use with a GPU until the limit gets lifted the next day. I will say I don't use often on Colab so not super knowledgeable about using on it.
@@KLEEBZTECH Yeah, its seems that situation is what you desribed. Thank you again!
I go the wheels off doing this "car manual showing how brakes are assembled"
And that is the type of thinking you need when creating good prompts. Think of circumstances that would have the tires off and prompt for that.
@@KLEEBZTECH I played with this some more today and just had fun with it "automotive manual exploded view of (entire car) brakes, suspension, engine 1950's"
And now we have parts all over the place. lol. Have you tried adding the "Knolling Photography" style to it?
@@KLEEBZTECHalso when I enable the face swap i get 1006 in the prompt, and the focus get stuck
Don't we have a discord
🤔
should we?
I only hope I can someday learn to generate images of men without earrings.
Are you using any styles when you generate and get them? If you can give me more info I might be able to give you some suggestions.
I appreciate that. The situation is when I am trying different variations of input images. I'll drop an image of a portrait into the Upscale/Variation window, checkmark Vary (Subtle), add some text prompting; usually a sentence followed by some descriptors:
"a bi-racial man with blue eyes and a buzz cut dressed in golden full armor, white background,
solo, looking at viewer, smile, blue eyes, simple background, black hair, 1boy, white background, upper body, male focus, teeth, dark skin, armor, grin, dark-skinned male, shoulder armor, portrait, pauldrons, realistic, gold armor, golden armor, solid gold breastplate, mixed ethnicity,"
Presets are on: Realistic, Speed, 1:1, PNG, and the Negative Prompt will have
"unrealistic, saturated, high contrast, big nose, painting, drawing, sketch, cartoon, anime, manga, render, CG, 3d, watermark, signature, label"
Selected Styles: Fooocus V2, Fooocus Photograph, Fooocus Negative.
Base Model, usually one of these checkpoints;
juggernautXL_version6Rundiffusion
socarealismXL_vae30
sdxlTripleHeadedMonkeys_v10
realisticStockPhoto_v10
devlishphotorealism_sdxl15
Sometimes with or without a Refiner (from the same list of checkpoints)
Only LoRA would be SDXL_FILM_PHOTOGRAPHY_STYLE_BetaV0 (weight 0.25)
No settings on the advanced tab are changed.
I will get ear rings 90% of the time.
I will add to the Negative Prompt line of text: "no ear rings, no earrings, no ear-ring," etc
Still around 85% of the time I'll get ear rings.
I'll try adding to the text prompt: "empty ears, bare ears," etc
I'll get ear rings 95% of the time then.
I blame the checkpoints, but I do like the other results I get from using them.
I think the real solution will be inpainting, but I haven't tried that yet.
I'm sure that is something you have covered in your videos, so I'll poke around and look.
If you ever do a video on using Oobabooga's text-generation-webui to implement the use of Fooocus I'll be very interested in seeing it!!
@@marshallodom1388 interesting. My first thought was you had the Masterpiece style enabled and that includes the word earring. I'm not seeing anything that stands out that would explain it but I'll think about it. Does it do it when just generating as well? Or just under the vary/upscale section? As for negative prompt, just put earrings, no need to add the word no. Negative prompts only have minimal effect but also you can add extra weight (earrings:1.5) for example.
@@marshallodom1388 I wonder if using the word gold is part of the issue. That gets into the association effect. Often that's the sort of thing that causes these things that I find.
This is a great channel I'll tip you with a Subscribe Like and Comment! I have no money sorry 😄