Пікірлер

• 
  @deagzzzshorts4 күн бұрын

  Where did you go dude? Hope you doing good

• 
  @cmdr_talikarni12 күн бұрын

  I think usage and budget have a big affect on what you should use/have. 1. Even in 2024, there is currently no direct equivalent Stable Diffusion system that works great on AMD GPUs. This is why with SDXL, a 8GB RTX3060 is on par with a 16GB RX7900XT. 2. Not everyone has $500-1200 for a single GPU, and they may be just playing around with it, not using it professionally. This is where a 8GB RTX3050 ($220-260) can be used, taking ~30 sec per image, or a refurbished 12GB 2060 a little faster than the 3050 for less money (under $200).

• 
  @sessizinsan111116 күн бұрын

  Hi mate where is xformers install part? i have this ''no module 'xformers'. proceeding without it.''

• 
  @mrrevengaa16 күн бұрын

  Amazing stuff, great explanation way better than many tutorials. Thank you for your work and time.

• 
  @eyoo36921 күн бұрын

  Hope you’re ok man ❤ Always enjoyed watching your videos

• 
  @Prasath-vm1snАй бұрын

  Idk maybe it made the model schizophrenic maybe this is how schizophrenia works in humans too maybe learning stable diffusion more and more with the context of human pshyce and thinking process will make literall sense but yeah let's see how it goes but a really great work buddy loving it thank you

• 
  @Channel_2020_Ай бұрын

  you are a god send sir

• 
  @codebycandleАй бұрын

  found your call to "make something" (and not simply "comment or subscribe") - refreshing. thus, you've earned both, sir.

• 
  @user-wx9ms5zc4jАй бұрын

  thanks man

• 
  @Sarah-dj1esАй бұрын

  Wow! This is the best Explanation I have read/heard and I have been looking through alot of papers on Aesthetic personalization. I am a postgraduate researcher writing a paper on this. Is there a way to get in touch soon-ish? my use case is very specific and I could really use some input.

• 
  @JunaidAzizChannelАй бұрын

  Man casually delivers a masters degree course with a research thesis in 20 minutes

• 
  @DataScienceGuy2 ай бұрын

  Sooo usefull video, thx!

• 
  @derekghh2 ай бұрын

  I've been programming for 30 years. This AI brings me back to the early days of computer, when hacking was so much fun.

• 
  @PawFromTheBroons2 ай бұрын

  Having the beach be *Sandy* instead of Aandy, would most certainly make it more beachy.

• 
  @Clabear2 ай бұрын

  Love your video! great explanation!

• 
  @sergetheijspartner20052 ай бұрын

  I would say it is the difference between Straciatella icecream and vanilla ice with chocolate sprinkles, both are vanilla icecream but one type straciatella you trained the whole icecream to be different and whatever you do you will allways get straciatella and it would be a hell of a job to only get vanilla out of that box, where as regular vanilla, you can add the chocolate sprinkles and add it to where it is satisfactory to you or just omit them according to your taste, but it's a lot faster, because you just add a bit to the big model without losing the big model, whereas in straicatella you change the model to something completely different and you can't finetune it anymore

• 
  @haohaocreates2 ай бұрын

  this is such a great video, would you be able to make a video on IPAdapters?

• 
  @user-yq8uh8gw2y3 ай бұрын

  не работает! после марта и обновления на 1.9.0++ много чего пропало в sd.

• 
  @ahmadzaka98853 ай бұрын

  Man this video is so helpful. Ty

• 
  @JarppaGuru3 ай бұрын

  0:48 yeah current world. let bloat internet and get likes. its youtube that make more and you get worthless wall piece

• 
  @jonm68343 ай бұрын

  I appreciate the technical explanation but, in all honesty, I boiled it down after a single picture: ControlNet prioritizes image-to-image for denoising the subject, and text-to-image fills in the details.

• 
  @baseddoggie3 ай бұрын

  I'm not sure the numbers about Dreambooth downloads are accurate. It seems he got that number from the number of "checkpoints" (aka full size models) downloaded from civit ai, but I'm not so sure most of those are made with Dreambooth, a lot (if not the majority) are model merges which is not the same thing. Just thought I'd mention that.

• 
  @mat58443 ай бұрын

  Fkn love this

• 
  @ivizlab6224 ай бұрын

  on training, I got this error: Exception training model: 'type object 'LoraLoaderMixin' has no attribute '_modify_text_encoder''. any thoughts?

• 
  @Mika433444 ай бұрын

  outdated?

• 
  @suryaprasathramalingam24214 ай бұрын

  thanks for the short explanation. Loved it!

• 
  @JordanPetersonTech4 ай бұрын

  There's a few different ways to remove backgrounds in the stock AUTOMATIC1111 interface. Is there a reason you downloaded an additional script? Are the stock functions not working? Just curious, because while I was previously able to change backgrounds now it seems I get a mixed bag of results, which by no means compare to your time of 11 minutes.. Would be interesting video or just a comment as to why this is the background method you're choosing. Thanks for the howto bro. Peace

• 
  @yahyajapan4 ай бұрын

  Excellent !!!!

• 
  @Nerf_Jeez4 ай бұрын

  Niiiiiceee!! Very comprehensive

• 
  @aarondavidlewis4 ай бұрын

  I couldn't follow these instructions because the launch.py file calls a separate modules\launch_utils.py and the setup of that file is different than here...BUT... if I just added the argument --xformers to the webui(.bat) command line, it did the same thing... so just launching SD by typing 'webui --xformers' without the quotes

• 
  @MrBottleNeck3 ай бұрын

  This worked for me thanks! I added 'webui --xformers' in to the file 'webui-user.bat' so it is automatically run when SD is started. As a sidenote, the reason why I needed xformers: My 24GB RTX 3090 was running out of memory in images even with dimension under 500x500, but now I can upscale no problem even 100x size images

• 
  @workplaydie4 ай бұрын

  I really like your videos btw

• 
  @workplaydie4 ай бұрын

  What about the argument that the art is stolen? Stable Diffusion, etc, were trained on images without artists consent.

• 
  @tag_of_frank4 ай бұрын

  my intuition says hypernetwork is better than lora. Hypernetwork would have more layers than Lora.

• 
  @tag_of_frank4 ай бұрын

  Are they training for a specific sampler if so how?

• 
  @edkins15 ай бұрын

  it is a fat dislike for this kind a tutorial. Looks you are smart enough. But why did you place your talking head in upper left corner ? That is a big fail.

• 
  @charliebaby70655 ай бұрын

  huh. im creating a js app that lets me do the same thing and be able to edit the entire process with drag and drop within the enviroment, but im not using ai or an image, but opencv and live camera streams instead

• 
  @megative44445 ай бұрын

  Do you understand that you are a legend?

• 
  @phantomhydra5 ай бұрын

  What exactly does learning rate do?

• 
  @jeronimogauna75085 ай бұрын

  Taking the course! Ofcourseeeeeeeeeeeee

• 
  @jeronimogauna75085 ай бұрын

  Best video I ever seen. Best vibes! Thanks so much

• 
  @pipinstallyp5 ай бұрын

  man it's been a wild west out there an year later.

• 
  @eMgotcha775 ай бұрын

  However can textual inversion create something that the model has never learned before and has no similar shape than anything it learned before? Well a corgi is a dog and SD learned many different dogs. What if SD was never trained on images with bicycles and motorbikes. Could it create an image of a bicycle with 'just' textual inversion?

• 
  @aschelocke52876 ай бұрын

  why would you use zoom < 0 anyway...?

• 
  @chrisharden70336 ай бұрын

  So entertaining and insightful, thank you koiboi. Really enjoyed it!

• 
  @ozanyaman69316 ай бұрын

  abi hasan kim :D

• 
  @jarroddeskins91616 ай бұрын

  All I had to do was edit a line in webui.bat... this video is such nonsense.

• 
  @jarroddeskins91616 ай бұрын

  Why does this say "one click" but its 13 mins long? Stupid