Inject Yourself into the AI and Make Any Image With Your Face! (100% FREE Method)

[@r34ct4]

Hey man kind of a meta comment: I remember when you uploaded the video about running StabelDiffusion locally, and thinking I want to contribute by commenting with some instructions on how to troubleshoot some potential errors, hoping I could contribute in some way, instead of always being a lurker. I remember hoping that your channel would become what it is today. Ultimately, you've helped me finally realize that I always give up following my passions not because I afraid of failure, but because I am afraid of success. Thank you

[@MarianaTraxel]

A-MA-ZING!!!! I do have to admit, that for a non-programmer this is A LOT of information and room for doing mistakes ... it took me two hours to get same-is results. But I CAN DO IT now, thanks to you.

[@buchneski]

Great content. Well done explanation and everything works locally (which is amazing) as described.

[@iwantit539]

Npc spotted😊

[@TannerHeke]

frr🤣@@iwantit539

[@matix676]

@@iwantit539 NPC that pays? Sign me up

[@stevejordan7275]

1:00 The "aspect ratio" of a 512x512 image is not 512 to 512, it's 1:1. If the pixel dimensions were - for example - 300x400, the aspect would be 3:4. We look for the smallest whole numbers that (when multiplied by the same subsequent number) create the pixel dimensions. (If the required dimensions were 512x511, that would also be the "aspect ratio." If it was 500x512, the aspect ratio would be 125:128, etc. 1920x1080 is 16:9.) Still, good stuff. An informative tour. Thank you!

[@deadpooh]

So 512 IS indeed the ideal length and height of the image in PIXELS, and not aspect ratio? Perhaps you might be able to lend more clarity.

[@deadpooh]

Also, are you, or anyone else, aware of a way to "batch resize" these images quickly, and ideally for free? I feel like this supplementary knowledge could be a good candidate for being a pinned comment.

[@stevejordan7275]

@@deadpooh PhotoShop has automation that could likely do this. Or at least it used to; I haven't needed to batch process images for some time. The process involves starting the script recorder function, perform one resizing, and then turn the recorder off. Then you select the directory where the files are that you want to process, and a directory for the processed images to be saved. Adobe's forums can probably give you the specifics for the CC version.

[@stevejordan7275]

@@deadpooh That's correct. Start with the pixel dimensions, solve for the lowest common denominator (LCD); the rest is just maths.

[@DeletedComment]

There's no box to press at 2:28. I have the same screen as Matt despite not having checked the button. Reading comments below it seems like this is a common problem and no-one seems to have fixed it. Any ideas?

[@marazu043]

I have the same problem have u found a solution?

[@cryptomillie]

I haven't found the box yet either?

[@mooniproductions9782]

have you found any solution yet? MATT HELP PLZ🥲

[@DeletedComment]

Ok update, it turns out it works now without the box tick. It used to be essential. Now I suppose it's just removed and ticked as default

[@justjewellent8129]

You my friend, has gained a friend. If ever tutorial could be taught by you, this world would be a better place!

[@ImperialRoads]

for those wondering why seed isn't showing you have to go to filter beside the search bar and change it to Stable Diffusion 1.5

[@dannygreeves6676]

can you help with the above issue please - no idea how to sort it! Any advice much appreciated

[@yogaadi3034]

Thank you!

[@dadungrpj8314]

Great tutorial Wolfe, after several attempts I have some observations, 1. I'm using Mac BookPro and it couldn't exceed the point of uploading the image, error message kept saying "instance file not found" so I ran it successfully on a windows system. 2. The terms and agreement check box is no longer there 3. Install xformers from precompiled wheel is no longer available despite the fact that 2 and 3 were no longer available i successfully injected my pics and generated fun AI images. Thanks Wolfe

[@dadungrpj8314]

@Viral Spook I did not, I guess it just does that automatically

[@HSR]

@@dadungrpj8314 I am on the Mac too. Got this error when I tried to upload the images MessageError: RangeError: Maximum call stack size exceeded.

[@dadungrpj8314]

@@HSR If you can lay your hands on a windows OS system you'll be done in an hour or so. But for some reason some of these AI tools and apps don't do well on Mac OS and I don't know why but going forward I'm getting a virtual box on my Mac then installing Windows OS, let's see if that would do the trick.

[@GoomusicLtd]

I'm using a Mac Mini M1, and it can't even get pass the install requirements, it says "ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts. lida 0.0.10 requires kaleido, which is not installed. llmx 0.0.15a0 requires cohere, which is not installed. llmx 0.0.15a0 requires openai, which is not installed. llmx 0.0.15a0 requires tiktoken, which is not installed. tensorflow-probability 0.22.0 requires typing-extensions

[@thisjuno]

@@GoomusicLtd and then press the play button, this should fix it.

[@krizh289]

If you try this, use this as a negative prompt to get a lot better outputs (credit SECourses): Negative prompt: (blue eyes, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), fat, text, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck

[@melissakampers]

I recently discovered ChatGPT and I've been diving into the world of A.I. ever since. Your channel has been a valuable source of information and inspiration, a true treasure trove. Keep up the great work!

[@smokedes2]

Same here. I've been saving all of these videos

[@xixtixspace2660]

For all those having trouble with the license issue, just get your token continue on with the process, and ignore the message saying you need to click and accept. I just followed the process Matt laid out and it worked. You can ignore the missing parts on training as well.

[@heypett6619]

Update: October 2023, it works really well. For those having a pip error, just execute that step again, that way worked for me. Thanks for this video, Matt!

[@anasdroby2802]

HOW dude ?? i've been trying for the past 3 days it didn't work

[@heypett6619]

@@anasdroby2802 I'mma try again rn and will let you know.

[@sheeesh404]

@@heypett6619 Did it work?

[@JonathanKingFC]

Doing the lord's work mate

[@techwhisper]

😂

[@J3R3MI6]

🤫

[@PaRj0053]

Matt, I have got to 2:30. I am supposed to see a button to Accept Terms and Conditions. Is that just for a new Hugging Face user - as I can't find that button?

[@daveulrich]

same. definitely no button.

[@kk47shooter91]

ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts. torchaudio 2.0.2+cu118 requires torch==2.0.1, but you have torch 2.0.0 which is incompatible. torchdata 0.6.1 requires torch==2.0.1, but you have torch 2.0.0 which is incompatible. torchtext 0.15.2 requires torch==2.0.1, but you have torch 2.0.0 which is incompatible. torchvision 0.15.2+cu118 requires torch==2.0.1, but you have torch 2.0.0 which is incompatible.

[@FinalFlameProductions]

Did you find a fix for this ?

[@kk47shooter91]

@@FinalFlameProductions not yet :(

[@KK47..]

help

[@carolynholland1962]

Same issue, I tried to just keep going but training stopped with runtime error PyTorch and torchvision compiled with different CUDA versions. 😕

[@kk47shooter91]

@@carolynholland1962 its fixed now, i guess it was and update

[@jmanjuice710]

In the link that was in the description, I’m following the steps and at around 3:33. The segment that is “Install xformers from precompiled wheel” That section doesn’t pop up for me. 😢. What do I do?

[@dineshkannaa]

Same here

[@NathanJayMusic]

Turns out you don't need it

[@dineshkannaa]

Thanks bro

[@DubsCP]

THIS IS ABSOLUTELY AMAZING....Thank you so much for your guided lesson. Extremely easy to understand, and QUICK to the point! Working on mine RIGHT NOW!

[@PrinceWesterburg]

The install X-Formers step is missing now and it warns the code is no longer compatible with Google whatever - video update time already?

[@dannysosa9983]

I cannot find the button that you are talking about at 2:30. I am sure I never clicked anything and have followed all the steps up until now. Any Advice? Thanks, Danny

[@inteligenciamilgrau]

At num_class_images you can put the amount of "classes" you are trainning, in your case, just one!! In your case "mreflow person"!! If you wanna train a model and add you wife and son, in that case 3 classes, each folder with images separated!! So you can generate a image with 3 all together!! And You can also choose train interval to 1000 and put max_train_steps to 3000! In that case it will save the model at 1000, 2000 and 3000 and you can compare the 3 of them at the end!! (But think also this will save 3 saved models, almost 15gb of your drive! lol !!! Thank you so much for sharing this knowledge!!

[@SUDO-gm2if]

At 2:52 if the new token is greyed out means that the email has not yet been confirmed. It can be seen at the upper left to do it.

[@PaRj0053]

Then at 3:31 I do NOt see the Install xformers from precomplied wheel. What have I done wrong?

[@lualgomo3920]

Awesome video. Sadly not working anymore due to dependencies issues.Any updates in the method would be very much appreciated.

[@shambhavitiwari508]

How do I accept the terms and conditions. Cannot find any box.

[@PremiumWebsites]

I do not see it either

[@aimarketingmoney]

10:20 mine are messed up. I got around 60 photos that were trained on 4000 instead of 2000 and they got ugly what did i do wrong?

[@kaizenacos8183]

excellent matt, but dont appear the button to accept the terms and conditions, would you someone please tell me what could I do?

[@einar_stray]

You said I can use the trained model again in the future. How? Where? Thank you!

[@SHAMONDAEREACTS2]

2:24 ok you mentioned a terms and conditions button, where is it?

[@2ndEarth]

same issue, there is no button for me too, effectively locked out from their services

[@leapintobookkeeping]

Model card link no longer exists.

[@jamiecurran8163]

Have you made an updated version of this Matt? it doesn't seem to work anymore due to install requirements error

[@Soumya-Faria72677]

This is SO cool! Cant wait to see myself in all kinds of crazy pictures.

[@danvorosmarty9854]

Question: I want to "sequentially" train a model, in other words, I want to train it on pictures of myself and then repeat the process on the same model and train it on pictures of say, my daughter, with a new instance prompt word for her as well. This would enable things like being able to prompt for images with both instance peompts for myself and my daughter at the same time. And/or being able to switch between images of her or myself without having to load a new model each time (just use lne unique instance prompt word or the other). Currently I have a handful of custom trained models for various friends and family but my goal would be to have a single custom model where i could prompt for anyone/anything I've trained it on, and in whatever combinations I want (including all at once like say for a group photo). My question is, you mentioned being able to "use the model later" which i think you meant narrowly as in downloading the ckpt file and importing it to a local application (and/or running it from gdrive?)... This is what I do with my custom models currently... But I'm wondering what exactly it is pulling for files when you designate a model in the: "Name/path of the initial model" field... I understand it pulls the model from huggingface, but is there a way to modify this collab notebook to have it use a cpkt file that you upload? Or somehow point it to the saved file(s) in Gdrive? My novice thinking was to perhaps upload the file to my huggingface account so that it would have the same pathway, but all I'd have to upload is the ckpt file... Is that enough? Or are there additional files I would need to upload? And if so, where/what are they? Thanks!

[@CupcakeUnicorn]

@inteligenciamilgrau seem to have figured it out further down in the comments.

[@SmudgeOfficialUK]

Hey mate, thanks for the great video! Just wondering, why did you pick the number 12 for num_class_images?

[@MrAgoof]

Hi Matt, I did everything you showed in the video. It works just fine. Thanks! But when I reopen the page where can I paste the location so I can use it further?

[@lokeshchadha7715]

Pls let me also know if you find a solution to this.

[@pressrender_]

Could anyone do this?

[@TRAVELZILLA]

Hello there, how are you today? Thanks for this video, it is an amazing! I can´t find this tick box to agree with the terms and conditions mentioned on 2:25 (model card) can´t find it anywhere, so I'm stuck there....there is no button sadly.

[@mooniproductions9782]

same man. if i find it ima let u know. digging so hard rn.

[@TRAVELZILLA]

@@mooniproductions9782 I got to the project's completion, ut it didn´t come out very nicely, maybe i need to posto better pictures or different pictures, but in the end the generated images looked nothing like me. SOme look as if a were disfigure, but it is an excellent video, I just need to try a few times and try different pictures. When I got to the model, i simply read the license, made sure all pictures were 512x512 and that all of them had the same name followed by a number...example.... star(10) star(11) etc....then it finally worked

[@meevidz]

No need now follow other steps just

[@googlehomemini9823]

Matt, can you tell me what the minimum GPU you would suggest? My machine is clearly not up to snuff… Is the GPU the only part that’s important? Or does the CPU and Ram play much of a part in this?

[@FixitantwerpBe2100]

This tutorial is outdated, I get errors when installing the requirements already: ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts. lida 0.0.10 requires kaleido, which is not installed. llmx 0.0.15a0 requires cohere, which is not installed. llmx 0.0.15a0 requires openai, which is not installed. llmx 0.0.15a0 requires tiktoken, which is not installed. tensorflow-probability 0.22.0 requires typing-extensions

[@phoneflasher]

How to you reuse the CKPT when you go back another day? How do you use it in you own SD?

[@TheGadgetGuru]

Do you have to use Google Drive or can you save to a local hard drive. And...love your Midjourney videos...keep 'em coming!

[@CultureDrift]

Wow! this is a year ago now ? Wadda ya think, could you do an updated version of this?

[@CultureDrift]

haha you actually did it

[@anointed444]

@@CultureDrifthe made a updated version? I can’t find it

[@davidedasilva2207]

Great! But I have some question in minute 5:42: let's suppose that my dataset contains images of a person, dog, cat... Is it just to add more objects inside the "concepts_list" array in the same order that the images are sorted in the dataset?

[@vivalsdne3239]

Hi , How to use a custom model in this stable diffusion google colab ? i want to use other model like protogen or dreamlike diffusion

[@skwjisin]

what do you do when you finish generating the photos? do you just close the web page? do you need to delete the photos of your face uploaded?

[@Tim_Black]

When trying to reconnect I get to the "Inference" point and it will not connect to my GDrive. Any thoughts?

[@alfchurch733]

The terms and agreement check box not available!?

[@winther5]

not there - this video is a waste of time

[@crazy_uni_stud6184]

Having issues here, when running the code after uploading the images, i'm told that python3: can't open file '/content/train_dreambooth.py': [Errno 2] No such file or directory Any help?

[@freakyninjaman3]

This is great! I'm having a bunch of fun. Do you know if I can upload some art of mine into a folder (all a similar style) and make illustrations with the same colors/style? Would I change "person" to "style," or how would that work?

[@mreflow]

Honestly, I haven't tried that yet. I'm not 100% sure if the process is the same or not. It's something I'm looking into though.

[@Raylative]

@@mreflow the corridor crew released a new video on how to push consistently a specific kind of art style without changing the characters profile. it might interest you. they use reverse stable diffusion with a fixed seed. im still in the process gf understanding this but YO the outcome is great. they made a whole anime from picture to picture generation. amazing.

[@hustler6069]

@@mreflow Hi Matt, may I know which tool do you use to remove your background and add a virtual background to your video

[@mnrvaprjct]

@@mreflow hello, I tried to find the check box you mentioned but can't seem to find it, where would it be @mreflow

[@krizh289]

Yes you can train it on artistic styles as well, just replace "person" with design or art or something like that

[@EliteConfiDance]

Where do we find the seed numbers for Lexica art? Also, how do I save this page?

[@callummcclelland875]

what button? I can't find it 2:33

[@zeneditingdesign9686]

That was amazing. But all of the sudden it stopped working. Any other having errors once reached - accelerate launch train….? I have tried with different google account and it doesn’t work anymore

[@maxinewairimu6478]

Thank for sharing this gem Matt, I had no idea that this was/is even possible. At first all the numbers intimidated me but not at all anymore. I have heard quite a number of people talk about a new AI tool called BlueWillow, I am curious to learn more. Please please share in your next video

[@vf3d]

After I close the long link where I did all this, what do I do when I get back to access the model again? Seems like everything is reset when I repoen it.

[@vf3d]

What I ended up doing was just dowload the model and put it into stable diffusion like he mentions in the video.

[@marksutherland774]

Great video, thank you, have you got a video on how to load a model e.g I do the training and save the ckpt file. I leave colab and start a new session, how do I load the existing model , thank you.

[@joreybernsteinAI]

Thanks!

[@Ryhha]

Great tutorial :) Please is there a way to save my training after it is done and continue on generating the images next day? Or do I have to start over and over again? Thank you

[@programasinmer]

Save the notebook into your Google Drive, top left in File "Save a copy to my Google Drive". I highly recommend you to do it before all, and start the google colab from the copy, that way anything you did will be save. Another stuff, you still need to run again the installation and all of that everytime you close Google Colab (Or stopped for any reason), in order to create all he Stable Difussion files.

[@FinalFlameProductions]

@@programasinmer Thanks for your help. So we need to add the pics and do the 30 min bit everytime ?

[@lokeshchadha7715]

@@FinalFlameProductions Did u get an answer to this? Even I am finding this weird running 30 mins photo upload everytime i restart my pc..Pls let me know if u find a solution to this..Thanks

[@FinalFlameProductions]

@@lokeshchadha7715 Yeah I just redo everything again, whether it's right or not. 🤣 The 30 min part is sometimes 16 mins, it's actually learning the face I think.

[@pressrender_]

Could anyone do this?

[@holo388]

2023-06-07 22:06:36.807570: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT

[@terrinhaverde2873]

Thank for your video but for the train part there is an error: python3: can't open file '/content/train_dreambooth.py': [Errno 2] No such file or directory.

[@Sarita-Kriti63805]

Subscribed! Love learning new tech tricks like this.

[@TravelingThruLife]

I'm getting this error during Install Requirements: ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts. torch 2.0.1+cu118 requires triton==2.0.0; platform_system == "Linux" and platform_machine == "x86_64", but you have triton 2.1.0 which is incompatible. do you know anything about this?

[@xixtixspace2660]

Same error

[@TravelingThruLife]

@@xixtixspace2660 i can't for the life of me figure it out. my terminal keeps telling me i don't have pip installed when i do

[@fletcherstudios]

same error

[@santicodaro]

Amazing! Is it possible to do the process with multiple persons? I want to do it with all my friends faces (with their permission of course)

[@KailasAH-n5i]

Hi, an OutOfMemoryError: is being shown when doing the training what needs to be done? i dont have that much storage in google drive. please suggest an alternative. Thanks

[@Brian-Cherry]

I can't find the button to accept the terms and conditions, can anyone help?

[@2ndEarth]

I am having exact same issue. I am surprised more people are not talking about this, because there seems to be a discussion already on the general internet about this problem. I STILL HAVE NOT FOUND A SOLUTION :(

[@Brian-Cherry]

@@2ndEarth I even got my wife to look. she couldn't find it either.

[@509Bren]

I can’t find it either!

[@BetterEveryDay947]

how to resize picture's? i have resized every picture with online resizer. When i put to train it comes horizontal.

[@steampoweredtv]

I got this to work! Thank you for the no-nonscence tutorial!

[@Orsvideo]

Great tutorial, thanks! Is there a way to add a second person to the trained model?

[@itsmarkallan]

I don't see the "Accept Terms & Conditions" button anywhere...

[@Sum5thefirst]

Like others have said, this video no longer works. Save your time and look elsewhere if you see this.

[@prisonisinourminds8070]

Did u find any other app that works?

[@WhatNRdidnext]

Colab won't work for me at all. I keep getting errors. Plus, the layout is completely different to the one that I'm seeing in the video. 😓

[@jameshong351]

Hi, I get an error with the CUDA version on the training step. CUDA SETUP: CUDA detection failed. Either CUDA driver not installed, CUDA not installed, or you have multiple conflicting CUDA libraries! Any help?

[@gautamsharma8386]

Amazing I just loved the info provided. But is it possible to load the trained created model for the second time when we run this program. :)

[@rezkyheryadimalik8561]

Hey sir, I can't find the install of xformers button, what should I do?

[@Darocosan]

I have the same problem :/

[@jmanjuice710]

I have the same problem too :/

[@meevidz]

Same problem

[@MyDivingSuit]

is there a newer version of this? i'm getting errors during the training step.

[@BEASTmqMANIA]

Hey matt, the tutorial is amazing, but one thing, i could'nt find the seed number in the lexica images, instead its says :Lexica Aperture v2" any help

[@edsonmatheus7976]

Use random seed

[@BEASTmqMANIA]

@@edsonmatheus7976 they came out worse

[@edsonmatheus7976]

@@BEASTmqMANIA How many steps have used to train? Also, how many images? It also can be your prompts or the num_inference_steps to generate

[@KK47..]

are you going to show us how to use the models in stable diffusion?

[@bazey]

Have you encountered a bug on the training section when you play it and it will finish quickly like 10 seconds. then when you go and play the weight directory, you will have an error stack overflow on line 7. I'm just encountering it now but this morning it works perfectly fine.

[@RansomnoteWill]

same issue!

[@bazey]

@@RansomnoteWill fixed it by commiting on the default settings of dreambooth. apparently i messed something on my settings that's why I encountered it. hope this helps

[@gonewild6596]

How cani use my old training data on this site itself?, where should I put that ckpt file?

[@earthingchargeurterre]

😀😀😀😀Amazing Can you explain to me how can i use this model on my stable diffusion offline in my computer ? because your metid is only available online... and i have stable duffusion already installed on my computer... 🙏🙏🙏

[@kafadek825]

Can this be done locally. Not on the Internet?

[@gabrieldelamanche9291]

great video, it did work with me, but where can i found the images on my computer?

[@mreflow]

You need to right-click and save the images to your computer.

[@gabrieldelamanche9291]

@@mreflow ah ok, ty

[@César.Tejada]

Thanks! the tutorial was very helpful. How you can reuse the model again on google colab?

[@RM-yr1yy]

Great walk through Matt! Got it to work, but can you make a walk through on how to re use the trained model from my Google drive? I'm struggling on that part, I don't want to keep re training everytime. Cheers!~

[@edsonmatheus7976]

Very simple. On the "Inference" section there's a variable: model_path = WEIGHTS_DIR. Change the value of this variable for the path where your model is saved in your google drive. Something like this: model_path = '/content/drive/MyDrive/stable_diffusion_weights/my_model/2000'

[@kk47shooter91]

did you find any other use for the trained model

[@VaibhavShewale]

so this model can only work on set of new images it cant generate image without image input?

[@tannerdowns8612]

anyone know how if there is a way to recover it if you close the page? or do you just have to retrain every time?

[@greenghostuk]

Hi Matt great content as ever really helped us starting out in MidJourney. Can you help me please, I keep getting lots of image generated that are canvases stood up agaisnt a wall or a person holding up the canvas so can’t actually use the picture. On all my prompts I’m requesting (white background) or some I have tried (No background) but it still keeps happening so you know what negative prompting is needed to remove and make the graphic flat and usable

[@mreflow]

You can take the resulting image over to a site like remove.bg and remove the background that way. Canva can also do this. Sometimes the AI struggles to remove backgrounds though.

[@ainsley2115]

im having this error on 2nd step ?ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts. torchaudio 2.0.2+cu118 requires torch==2.0.1, but you have torch 2.0.0 which is incompatible. torchdata 0.6.1 requires torch==2.0.1, but you have torch 2.0.0 which is incompatible. torchtext 0.15.2 requires torch==2.0.1, but you have torch 2.0.0 which is incompatible. torchvision 0.15.2+cu118 requires torch==2.0.1, but you have torch 2.0.0 which is incompatible.

[@tiggersaldy6237]

@ainsley2115 - did you resolve this issue - I am encountering the same (maybe its a windows issue ??)

[@jeralraspati16]

can somebody help? i cant generate anymore after i closed the tab? how to restore it? thanks a lot

[@thedemigodstudios]

Hey Matt i love your channel! i have a question, would you still say this is the best way to train an AI model for yourself?

[@joanmemoz-he9ec]

Does this take a long time to generate ? I am looking into BlueWillow, It would be wonderful if you could share a tutorial on it ! 😄 Reading through your comments, I am glad I am not the only one to request for it. I feel like I can learn a lot from your breakdowns of the tools.

[@ewwkl7279]

Thank you for your great tutorial. I've tried to use Lexica to get a seed number from the image I want to regenerate but it only showed the model name instead of the seed number. Where can I find the seed number of the image I want to generate, just like the example of Tom Cruise you showed me in this tutorial.

[@jeralraspati16]

i have the same problem, what to do?

[@Vossie_Vorster]

Hey Matt, great video as always. Very informative. Say, how do I go about reusing previously trained models? You mentioned something about the ckpt. file, but I'm clueless about implementing it.

[@jp1551]

Just import the trained model from `StableDiffusionPipeline.from_pretrained` and run as usual

[@Vossie_Vorster]

@@jp1551 You absolute legend. I appreciate the assistance, I'm quite shit with this code stuff, so thanks for the info.

[@11ui55]

@@Vossie_Vorster what did he say, the comments gone

[@dushyantsinghshekhawat793]

ckpt file will be saved in gdrive when you first train a model. I am not getting how can I use it. He mentioned in code comments that we can add ckpt file path and use the pretrained model, but it's throwing following error. Any clue how to resolve this? HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': '../content/drive/MyDrive/stable_diffusion_weights/mrblack408/2000/model.ckpt'. Use `repo_type` argument if needed.

[@SteveFrame_devonuto]

This is cool, but do you have a tutorial for using these trained models in a AUTOMATIC1111 webui? I'm running a 3070, and didn't have the VRAM to be able to train, but should be able to generate images locally using thse ckpts?

[@siunaldosenior8605]

great video! I'm just amazed by the results it generated But I cannot upscale my photos. How do I increase the resolution of a picture that I just generated?

[@brazatolz213]

Cool tutorial. So much work to get it going. Easier to just take a picture. Thanks for breaking it down though.

[@IvarDaigon]

does the trainng continue to process if you refresh the page? if so you can use a page refresh browser extension to keep it active.

[@TechMIs]

Hey i am having an issue with it after using can i save my data in there ? how can i do that cause after training my data later i have to do it again or if i keep backup in the drive, i dont know how to use it later in the colab. a tutorial would be appreciated. Hope you reply this...

[@TechMIs]

Hoping to here from you...

[@stevePurvis1]

Brilliant lesson Matt, Please keep up the good work and thank you

[@bordenj71]

Yep - I got the CUDA SETUP: Setup Failed! error as well Bummer - this looked like it would be cool.

[@Emraphel]

Very interesting idea but I can't seem to get it to work! Following instructions exactly but getting error 'CUDA SETUP: Setup Failed!' on the step under the 'upload your images' part!

[@frederiksally]

Same - did you find a solution?

[@Emraphel]

​@@frederiksally unfortunately no. I ended up finding other method for training my local stable diffuson instance using built in embedding a1111.

[@subhacasual]

great explanation and very detailed tutorial sir, I was thinking, if i mount google drive then how much storage the whole process will take, like saving the weights and all ? because generally we get 15 GB free storage, the full process will fit into that ?

[@DarrenOderinde]

how do i save this setup so that I don't have to retrain the ai every time I want to create images?