Hi, I installed everything but the "depth library" tab doesn't appear. How should I proceed about this?
@masoomehtanghatari8750Ай бұрын
I love you girl
@LevendeStregАй бұрын
Thank you kindly @masoomehtanghatari8750 - glad I could help.🙏
@crashdummygloryАй бұрын
the video should start from the 9:18 mark tbh.
@modusvivendi1442Ай бұрын
Very curious how i can keep the design i stole from a real illustrator to myself.
@wingstrongwingstrongАй бұрын
RunDiffusion doesn't have free options - I don't have the physical ability to transfer money from my country. It's a nonsense, not an option
@LouisGedo2 ай бұрын
Been missing you a lot I do hope you're well. 🫂 💜
@LevendeStreg2 ай бұрын
You're are very kind, @LouisGedo. Hope you're doing well too? I've chosen to focus on my primary business (illustration and animation). It has been a struggle time and energy-wise to create youtube videos. So I'm taking a time out from that.
@LouisGedo2 ай бұрын
@@LevendeStreg 💯% understandable. 🫂 Don't feel pressure to make regular or any content but if you do, I'll be here to support your efforts.
@LevendeStreg2 ай бұрын
Thank you so much@@LouisGedo . 🫶
@melissalutterman44522 ай бұрын
@LevendeStreg how do I get to this part of Dall E where I can select certain parts of the image? Even with the modifying section of Modjourney, it still messes up eyes and hands/limbs for me, so I subscribed to OpenAI thinking I would get this same option you show in Dall E, but it only let's me type out what I want changed to images created in Dall E, rather than images I upload (and doesn't let me hand select areas like you show in your video here). It also doesn't allow me to upscale the image to use predictive AI to add to the background. Was this only in the older versions of Dall E? Am I missing something?
@EvolvedComics2 ай бұрын
In posemyart, are we able to manipulate the pose by red/blue dots to move the joints so it changes the pose?
@LevendeStreg2 ай бұрын
Yes, that is exactly what you are able to in Posemyart. Hope it works well for you.🙌
@dustinpoissant3 ай бұрын
This does litterally nothing. I generate an image, save the seed and all settings, same prompt. I turn on the lora (with they keyword) and regenerate, exact same image is generated. This does nothing at all
@LevendeStreg3 ай бұрын
Sorry it doesn't work. It's been some time since I tested LoRAs. Please note this is an old video from many month back. Hope you get it to work.🙌
@dorkfactory3 ай бұрын
SUBSCRIBED. thank you so much, this is some really great information!:)
@edsonjr-dev3 ай бұрын
💜💜💜
@BabylonBaller3 ай бұрын
Waiting for Midjourney to allow inpainting of external images.
@anthillmob1003 ай бұрын
since wonder dynamics came out it hasnt really improved..
@LevendeStreg3 ай бұрын
I agree. A bit disappointing if you ask me.🙌
@loquiman3 ай бұрын
95% of this short is waste of time
@LevendeStreg3 ай бұрын
Please note that this is an old video made just when Midjourney 4 came out. Have a great day. Cheers!
@energeiai993 ай бұрын
cool - thanks
@LevendeStreg3 ай бұрын
You're welcome. Thanks for watching.
@ChrisVirgilio4 ай бұрын
Over 3 and a half minutes in before you finally introduce yourself and tell us why we should even bother listening to you? Gosh.
@pritamsarkar23854 ай бұрын
how can i get consistent results? i.e same character wearing same outfit but different poses of my choice without any crazy/ugly deformation?...every time different results is frustrating me
@LevendeStreg4 ай бұрын
Yeah, that's that though part. The technology is not quite there yet. It's difficult to get consistent outfits - without the deformation. Try doing long negative promtps. That sometimes works. Good luck.🙌
@dippydooo4414 ай бұрын
Will you be coming back?
@mayurpathak76064 ай бұрын
Is this still best solution you found for comic book characters? anything changed over past 6 months? Please let us know if you are using something else now or any new flow. Thanks.
@bluetreacle4 ай бұрын
none of the links work
@LevendeStreg4 ай бұрын
Sorry to hear it. It's a rather old video, so I'm guessing that some of the solutions are updated now. 🙌
@lilillllii2464 ай бұрын
If I try to make a cloth lora, should I do the same as in the video? Is there any difference?
@LevendeStreg4 ай бұрын
You mean if you want to make a LoRA with clothing? Yeah, then you would dress the person in specific clothing and have pictures from different angles. If you only want ONE piece of garment (like a hat) on different people - then you need lots of images with different people wearing that very hat - from all angles. Hope it helps.
@tudu66045 ай бұрын
you say I don't understand anything
@LevendeStreg5 ай бұрын
Sorry to hear it. Thanks for watching, though.🙌
@SaberBE5 ай бұрын
i quit watching after the 3rd reminder to hit the subscribe button
@LevendeStreg5 ай бұрын
Thank you for your comment and for watching. Have a great Christmas!
@ConquestusWorks5 ай бұрын
Eeeeeh and where is now the part with the "consistent characters"? Kinda misleading title.
@LevendeStreg5 ай бұрын
The consistent character part is this process - using ControlNet with an image input and img2img tab to have the face input. This way you can tweak you character. You might want to check out Nerdy Rodents video on "reposer" and comfy UI. It's really difficult to set up. But it looks really cool.🙌
@lilillllii2465 ай бұрын
Is it possible to apply clothes and have them look exactly the same when they are slightly different?
@LevendeStreg5 ай бұрын
Everything is possible if you spent enough time on it. For me it's much easier to correct and redraw with Photoshop. But yes, you can do it with outpaiting. It just takes a lot of time. Hope it helps. Also you might want to look into Nerdy Rodent and his video about "reposer" and comfy UI.
@user-gq2bq3zf1f5 ай бұрын
If you already have other photos as jpgs, how do you change the skirts in one photo, and then apply those skirts to the models in the other jpgs?
@LevendeStreg5 ай бұрын
This is an old video. I don't know how the solution works at the moment. I've seen something similar on Prome.ai - in that solution you add it per image. That means you do the same process over and over with new images. Hope it helps.🙌
@AndresAlvarez-zc4xo5 ай бұрын
Hi ! You made my day! Since the dreambooths colabs were broken I wasnt able to train ckpt models until now, thank you so much, I thought that I wouldnt be able to train custom models anymore
@LevendeStreg5 ай бұрын
I'm so glad I could help. And thanks for the comment and for watching. 🙌
@Phil_Langone_FilmArt5 ай бұрын
As an artist AI is one of the more depressing developments in art history. Obviously it's a wave that can't be held back. I'm sure the goal for most artists is to figure out how to control this for their own work, but even that, the time it takes to learn, the time it takes to write prompts, it's just a depressing, boring process.
@LevendeStreg5 ай бұрын
I tend to agree with you. But there are also a lot of potential in using AI. I still prefer to illustrate, draw and visualize🙌
@Phil_Langone_FilmArt5 ай бұрын
@@LevendeStreg there is a lot of potential. What that is while not wrecking people’s careers I’m not sure yet. In LA, within the concept art community and larger film art community there’s a lot of worry and meetings happening. People that have built overhead, with homes, families, bills are seeing all the horrible things that can go wrong for them. It’s already happening with producers cutting out concept artists and paying low paid PAs to generate images.
@LevendeStreg5 ай бұрын
I agree with you, @Philhockey22. It's concerning that currently, only major studios like Disney, Pixar, and Dreamworks are utilizing AI to create 2D characters in 3D spaces, as it requires significant computing power and advanced graphics cards. This technology is out of reach for individual animators and illustrators due to the immense resources needed. However, I believe that as AI becomes more affordable and user-friendly, many creatives will integrate it into their workflow. For now, AI doesn't seem practical for smaller projects, as it doesn't yet offer time or cost savings in those contexts.
@flameinfiren55655 ай бұрын
Nuh uh
@jessecool5615 ай бұрын
Would you by happen to know how to train free locally in dreambooth on SDXL in windows 10?...... if so a tut would be appreciated.
@LevendeStreg5 ай бұрын
NO sorry, I don't know about Windows and so far my experience with the SDXL models is limited. They're slower and a bit inaccurate, I think. Good luck with it.🙌
@PADATWO5 ай бұрын
I have just discovered your channel which seems very helpful. But ineed to improve a few my english ! Thanks for sharing 😊
@LevendeStreg5 ай бұрын
Thank you so much for watching and commenting. Cheers🙌
@User-pq2yn5 ай бұрын
After installation I don't see the "instruct pix2pix" tab (Automatic1111 v 1.6.1)
@LevendeStreg5 ай бұрын
Thank you for your comment. Please note that this is an 8 month old video. So Pix2Pix might not be in there anymore due to lack of usability or updates to the model. Most people don't use the model as Inpainting works so much better now. Hope this helps. 🙌
@User-pq2yn5 ай бұрын
@@LevendeStreg Thank You!
@erikmaki86426 ай бұрын
Ok, that video was 16:49 long. During the first 5 min I didnt lear a thing.
@LevendeStreg6 ай бұрын
THank you for watching and commenting. It is an older video. And the service has improved greatly since I made this video.
@randomprocess78766 ай бұрын
Hi! could you please help? I am not able to figure out how to download the outputs on my pc locally.
@LevendeStreg6 ай бұрын
Hi there. Sorry, but I don't use a PC - I use a cloud service for my Stable Diffusion. So I can't help there. Hope you can figure it out, though. I know learning SD is really difficult.
@_B3ater6 ай бұрын
Well she doesnt talk about the watermark on the whole screen.Unless you pay 200 dollars a month.Was very helpful really thank you for wasting my another hour.
@LevendeStreg6 ай бұрын
Please note that this is an old video. The watermark was not as prevailing on the videos back then.
@_B3ater6 ай бұрын
Ah ok. Sorry for being too aggressive then 🙇@@LevendeStreg
@themightyflog6 ай бұрын
What is that ARIA 2c you are talking about?
@LevendeStreg6 ай бұрын
It's the old line (that you at the time had to use, to import Models into RunDiffusion). Now they've built in a button to just import models.
@petermolvaier6 ай бұрын
the pro tips sound like were written by chatgpt
@LevendeStreg6 ай бұрын
Hahaha, good point. Please note that this is an older video (dating back a couple of month). I do use ChatGPT to check the grammar and proofread my manuscripts though.
@yannmassard39706 ай бұрын
You are way too old to pretend not being old. Just accept yourself you will sound less cringe and you won’t have to find yourself a personality by asking gpt for a haircut
@vi84036 ай бұрын
DELETE FROM KZbin YOU FEMINIST
@vi84036 ай бұрын
you horrible
@ekot04196 ай бұрын
Took me a good few weeks to find you!! An expert who shows how to combine Ai with the real design world(Like, the one that pays the bills!!). Still watching your videos. Hope that this will help me get out of my learning phrase and add this new skill to my business. Only thing is is, I need to stop your video and move it frame by frame to find clues. Thank you very much for sharing.
@LevendeStreg6 ай бұрын
Hi there. Glad it helps a little. And thank you for your comment and for watching. It takes forever to do the videos for me (so I'm not very productive with creating videos as I have a business to run🤗). Hope you get the hang of AI. It can be a great tool. Cheers🙌
@kurwa_bmw6 ай бұрын
11 minutes ouf of 12 are just about promos and the rest is full crap
@LevendeStreg6 ай бұрын
Thank you for leaving a comment and thanks for watching.
@Hardts6 ай бұрын
Rarely do I come across a fellow Dane who speak English so proficiently, almost no accent at all! Also, thanks for the stellar video, I really want to train a character LORA. I used SD Dreambooth about 10 months ago, in a rented google server. Took 1 hour, and results were not good.. I run SD locally, but last time I tried, dreambooth was too heavy for my GTX 1080
@LevendeStreg6 ай бұрын
Thank you kindly🕺- Yeah dreambooth is heavy now. You can try out RunDiffusion (it's a cloud service). I have a promo code to their service for 15% off on the first month of Creator's Club. It really works well. Promo Code: levendestreg15. Hope it works out. 🙌
@Hardts6 ай бұрын
@@LevendeStreg Heh okay, thanks :)
@INGLES.Gratis6 ай бұрын
Hey, how did you move your head up and to the sides... it was WAY BETTER than D-ID. D-ID doesn't move freely your head like a real video of your own. You showed too fast the demo in the beginning of the video! Please, could you make an updated version of this video with the free method of having that realistic look and movments WAY BETTER than D-ID?
@LevendeStreg6 ай бұрын
Hey there. I just did a video of myself and then used one of the free versions of "Wave2lip" in Stable diffusion. It's an extension. But just find one of the free versions on Huggingface. Hope it works for you. Cheers - Maria!
@INGLES.Gratis6 ай бұрын
@@LevendeStreg many thanks for returning back! i looked for a video explaining this, and really there's a gap. It would be extremely interesting if you could make a provokative video like "FORGET ABOUT TALKING PHOTOS WEBSITES - this is the next level!" and then, you show a real application with a demo to blow our minds. The video would get easy views and would help us visualize that in real applications for serious; not just 3 seconds of a quick demo :)
@INGLES.Gratis6 ай бұрын
P.s: this is the future of monetizing talking avatars. KZbin will crush on it soon in the future. A video of yourself with a mask on it and a new cloned voice is way more authoral (and original) than simple talking photos from D-ID and similars.
@INGLES.Gratis6 ай бұрын
P.s. 2: it would help people who got banned from KZbin and want a second chance playing fair; and people who doesn't want to show their faces but don't want to make ordinary faceless videos like everyone, having artistic appeal and humanity to make a strong connection to the audience like a real person. Talking photos are cool but c'mon: humans won't "buy it" after a time and won't create a real bond to the creator.
@LevendeStreg6 ай бұрын
Yes@@INGLES.Gratis I agree. KZbin is already crushing on it. Nerdy Rodent (KZbinr) has been doing it for months now.🙌
@haljordan15756 ай бұрын
i wish she wouldn't go all over the place. i end up getting confused and not learninganything except the existence of these new tools.
@LevendeStreg6 ай бұрын
I'm sorry you feel confused. This video is kinda old, and a lot of new tools have come up since then. So I'd recommend not using Google Colab for it. Way too complicated to work with. Cheers - Maria!
@capricegeorge54817 ай бұрын
So what's the order?? Juesh. Pointless video
@itslilsalami7 ай бұрын
You are a badass human being
@LevendeStreg7 ай бұрын
Haha. Thank you kindly for your comment. 🙌
@thewebstylist7 ай бұрын
Luv your tips and vids. It seems you should’ve mentioned the 4 ingredients in this one though.
@LevendeStreg7 ай бұрын
Thank you kindly. And yes, I probably should have. Thanks for commenting🙌
@ESan-lh6dq7 ай бұрын
I stopped watching within 3 seconds if you cant even have a great normal camera I cant trust you to provide anything of quality.
@mariaprohazka27307 ай бұрын
Thank you for your comment and sorry to hear that. 🙌