Видео

PSA Update: The Regions seem to work MUCH better in 1.5 if you DON'T include anything in the "common text prompt" field or in the background field.

Thanks! I was still using 1.5 almost exclusively up until a couple of months ago. Pony Diffusion models are my go to now, so I haven't tested the 1.5 models with Krita's newer features.

nvm it's ComfyUI

Yes, ComfyUI is shown in the video. I mainly use the plugin for the Krita paint program which connects to ComfyUI for my generations. You can see it in my other videos.

Thanks!😁

You can DM me on x/twitter. There is also an email link in my channel bio. x.com/intellimageai?t=Z8azcVj42vbhaM4m9zz5PA&s=09

I feel like I underutilize control nets. I haven't actually tried them with regions. I would expect it to work. I would try and make sure the control net doesn't overlap different regions.

Are you dumb?

lets see if ur still saying this kind of stuff once ai is taking over and hunting every last human on this planet.

@@JuhoSprite We cant build a phone to last a day what makes you think ai will have enough juice to hunt us ? :D

@@RichardKincses what? we obviously have the technology to build a phone that lasts for days 💀 look at most nokia phones. also we could have phones last for weeks, its just that its not practical and would increase size of the design, aswell as the cost. Ther are already cars operating by themselves using ai to detect humans. Its clearly already a thing of reality that robots can specifically target humans. so a bunch of robots getting hacked to attack us all isn't a far stretch.

Thanks!

I would try composing images with non Pony models and then doing image to image with a Pony model to get the Pony style to get around most of these problems.

Glad you like them!

I haven't tried flux yet. I wouldn't be surprised if it didn't respond to regions in the same way.

Interesting. I suspected it may be a general problem of sizes getting misaligned somewhere in the workflow.

More on that next time!

You would have to download them and use them locally. It should run on your PC, but I'm not sure about the speeds you will get.

Do they show up where you can apply them in the settings? If there is only one Lora missing and it is one you just installed, you may need to restart Krita to get it to show up.

@@IntelligentImage-sl7uf yes they showup in settings but not when i type <lora:

Where are you trying to type it? It only works in the prompt box of the docker itself, not in the style prompts in the settings.

@@IntelligentImage-sl7uf ya in the docker itself just as in video

I'm really not sure then. It should work the same way in the text prompt node in ComfyUI. You could see if it works there and at least determine if it's a Krita issue.

Thanks! It takes a lot of tries to get things to turn out right though 😅

@@IntelligentImage-sl7uf I learned that when removing object from pictures. You have to try and change the prompt and change the amount until it finally gets rid of the object and creates a nice new blend.

You could try using a pixel art style checkpoint such as this one: civitai.com/models/277680/pixel-art-diffusion-xl

You want to share models between two Comfy UI installations right? You should be able to do it in the way described here: github.com/Acly/krita-ai-diffusion/wiki/common-issues#how-to-share-models-from-another-folder-with-krita-ai-diffusion-plugin

Thanks! I think I'll start posting stuff on X (Twitter) for now. I made an account and haven't done much with it. x.com/intellimageai?t=5XAAddlTYLPWefAm4ef3WA&s=09 I need to look into what Discord actually is. I've looked at it a few times and couldn't figure it out. Maybe I'm too old.

​@@IntelligentImage-sl7uf😂😂😂

​@@IntelligentImage-sl7uf , please let me know which model you are using on this example. I'm using Pony Diffusion V6 XL and I don't get fullbody characters as you do, I only get a very close-up of faces.

​@@Lunarsong.Don't use the base pony. It's busted in many ways. Use autismMix instead. It's pony based model and lora compatible while being more predictable. Also pony based model have issues with inpaint and controlnet. For a beter experience try to use some other proper SDXL model that actually don't broke controls when you don't make anatomy or nsfw work. (wildcardXL, Juggernaut,AAMXL to name a few)

I'm using Pony Pencil XL with a lot of LoRAs. My next video I'm going to go more in depth into setting up Pony Diffusion in Krita. civitai.com/models/432249/ponypencil-xl

Some models have some character baked in. For example AnimagineXL have the hololive Vtuber but not PonyXL. When a character is absent, Lora can be used on the mentionned checkpoint. For background it's good to have that as separate layer. For consistent style, a LORA. For likeness overall, either reference/style/composition controlnet.

You can also try the composition and face control nets to reference a specific image.

@@IntelligentImage-sl7uf I till investigate, thank you, will let you know about my results <3

Thanks 😅

Thanks! Great to hear! I have been using the 1.22 version of the plugin. It looks like there is already an update I haven't installed yet. I'm pretty sure I have the latest version of Krita installed. The only issues I have had are that the newer versions of the plugin require additional models and custom nodes for Comfy UI. If you are not using the managed server, you will have to set those up manually.

I've looked at the settings again and I didn't think there is a way to increase the text size unfortunately. You could try downloading a screen magnifying application. I've been meaning to look for one so I don't have to do so much manual zooming during video editing.

Is there any way to link it to certain say sticky notes in windows And i would want you to interact in a discord link where people talk about Ai Stuff more of comfy and forge ui Its of pixorama

You can create your own discord too

@@BUILDS-ge8kz I'm not sure what you mean by connecting it to Sticky Notes, but there is no way to have it interface with any other program as far as I know. So many people have asked me to start a Discord I will definitely look into it. I have looked at Discord before and don't really understand what it's supposed to be. Maybe I ca get Chat GPT to explain it to me like I'm five 😅

@@IntelligentImage-sl7uf its a very group community of people thing, who are very very near to you, like you all are in a virtual room together

I agree. I wish there was a more straightforward way to get it set up at least.

1) DONT USE NEGATIVES 2) DONT USE NEGATIVES 3) do not (((big breasts))) or (huge breasts:1.6) ONLY up to :1.2 4) just ask simply in natural language and don't repeat the same words 5) use 1024*1024 resolution NEVER use below 832*832 pixels

The checkpoint you choose makes a big difference. I used Pony Pencil to make the "good" images for the video. civitai.com/models/432249/ponypencil-xl

@@IntelligentImage-sl7uf Unfortunately, it doesn't matter which I use, any Pony checkpoint does it to me (with the exception of EtherRealMix). It defaults to some amateurish style that it can't escape. Even the distorted signatures that sometimes appears in a corner is always the same. I tried adding a couple of style loras at 100% to push the output in a vastly different direction, but the ugly default style still just mixes in like poison. The only thing I can think to do is jack the loras up past 100%, but it's been my experience that it can harshly effect an image, and I've never seen anyone else say they had to do it.

Make sure there is nothing in your prompt that is locking you into a certain image style. You said you're using Krita, so don't forget about any style prompts that might be in the appended prompts in the settings. Sometimes a certain style or subject can confine the model to a small region of the data set.

There is a section on the wiki that might help: github.com/Acly/krita-ai-diffusion/wiki/common-issues#image-generation-is-really-slow

Sorry, I don't know why this error might be. Maybe someone else who reads this can help 🤞

Sorry, I don't know anything about Mimic PC.

For some reason, Civit marked it as R rated. It is probably hidden because of your content settings. I thought it was gone once too 😅 civitai.com/images/21471122

I'll try and incorporate it in a video soon!

@@IntelligentImage-sl7uf Thanks! I found that even if i draw the hands and use the Btw, theres any way to generate the same face? I tryed to use the Face controller but i get "onnx_cpp2py_export DLL load error"

The Face controlnet uses Face ID for the IP Adapter. I don't know what would be causing that error though.

@@IntelligentImage-sl7uf I got it working… well, more or less. The results are blurred faces with artifacts.

Glad it was helpful!

The same thing happened to me, so I knew it was probably a common experience 😆

Thanks! Glad it was helpful!

Glad it helped!

Thanks! I really appreciate that!

Thanks for coming to my defense! I have actually learned to enjoy the haters 😆 They just sound silly to me. I have a lot more videos in the works including more process videos!

@@IntelligentImage-sl7uf <3 Im sorry, what you mean in the works :D I've checked the links - no videos :DD

Sorry, I mean I am working on them and will post them soon :)

​@@IntelligentImage-sl7uf cool, Im waiting for them. Dunno if rtx 3060 will good for AI Krita I had amd card, but its hard to configure, so ordered budget one <3 I was trying to learn cg drawing long, but it's hard may be this will help me :DD

Thanks! I'm not sure about the answer to your question. Each Pony based model will be different. Some might work better than others. I haven't done much with Animatediff, but thinking about your question has made me want to try it again. I have a few ideas on how to make it work. I'll see if I can work in making a tutorial about it if I can figure it out.

I confirm, Some models like idéalpony or cinematicpony gives correct results but other like autism for example are bas. I'll try with other models an add loras thanks again

Thanks! I really appreciate it!

nevermind, I got it done.. haha