Such a useful video, thank you!!! Love your Twitter posts too 💯

Not working, (WinError 5) in installation now. This issue is known and ControlNet is considered as broken now.

test video thanks, you mentioned that training can take over 20 mins, does this mean that this gets expensive on replicate? Thanks

Your videos are quality and so informative! I hope you come back from your break soon.

No matter what I do, I get a 500 internal server error in my endpoint. When I click on the link and go to the browser, it shows 401 error no auth token given. It's 100% the right API key, same one I use for all my other api calls. I even tried hardcoding it. I'm trying to finetune fooocus-api by Konieshadow, could it be that it doesn't support finetuning? Only other thing I can think of is my images url is wrong. It's a public google drive url but it doesnt end in /x.zip/ if that matters? It is a zip file though. Just very lost. Thanks for any help.

Whenever I use this code I get: Error: API request failed: Unauthorized. And yes I've checked my API key and added Token before the key. Any idea how to fix the issue?

Excellent video

Phenomenal!!! Thank you 🙏🏽

Awesome work. Did you manage to use this Loras in A1111 maybe, for research is better

Nice video man. Thanks. Is there a good model for adding furniture? E.g. I upload a photo of an empty living room, set the style in the prompt, and let the model keep the same room structure but add several furniture and decoration?

Thanks

How can I run this from windows, I have wsl already

Fantastic tutorial. Thanks a lot.

Is there any resources on how to upload the downloaded files locally & run the fine tuned model

How do I do this on windows?

What was the prompt for these? 😂

super helpful, thank you

Super precious video. Thanks so much for your work!

is it possible to download de model in order to use in our own computer ?

Would love to know how to do this locally on a 3090. Seems to be a complete void of anyone sharing a walkthrough.

Get a real mouse cursor. 😆

Is this lora training? Do you have koyha_ss to finetune base model on your platform.

Is it possible to create a model destination through an API? I'm currently developing an app that allows users to generate their own avatars. For each user, I aim to create a unique and dynamic destination such as 'myUserName/usersUserName'. However, I'm encountering an error message stating 'The specified training destination does not exist'. I am new to this would appreciate any help or better solutions. Thank you!!

how much does it cost?

How to use the webui interface and extensions, the old conolnet of SD while still achieving vladmandic's optimizations?

Awesome video!!

that is exactly what I have looked for days or even weeks :) OpenAI have a great fine-tuning feature, but I needed alternative as well thx

This is an awesome tool!

"30 something couple, so an older couple". Wasn't feeling old today... until

Unfortunately I am still at loss on how to use this. I would like you to have done a live example (seeing you type in the prompt, seeing you click the buttons, seeing you generate the image so I can see exactly what you're doing. We saw none of this. I'm lost where I put the base prompt and common prompt. I assume both within the main prompt box? How does it look? Maybe I am just stupid.

The best tutorial of controlnet!😂❤

Hello I'm a beginner at programming can you make a video explaining how to use replicate apis to make a website. I have a really good idea but I'm stuck 😭

I don’t know man

wow

Why don't you show the setting in the GUI? Does the video explain the preprocessor (canny) or the model (control_canny-fp16 [e3fe7712])?

Hi, I have been experimenting with this quite a bit, when I try to script it I get a lot of issues: --prompt "woman" --negative_prompt "deformed" --seed 342396165 BREAK --prompt "man" --negative_prompt "deformed" --seed 342396165 This is how I script it (my script is way bigger), had to get rid of the negative prompt and use common negative, I stacked 60-120 images in the script, and the more text the worse result. It's like the text bleeds over, and affects all the prompts, with too many negative prompts all the generated pictures will be prompted with the negative words. It's the same if I have many pictures, they all bleed together. Any ideas or thoughts?

what model and propmts did you use for the company Logos? like Burger King etc. im struggeling to recreate something similar : /

Hi, I have tryied everything and I never get something base on what I upload in AI. It always does what it wants. I have all the models, styles, everything but it just doesn´t do it.

Great job. Did you use both the preprocessor and model version of every technique for these examples? Can you use one without the other and/or can you mix and match? Thanks.

A time stamp as between the different models would have been helpful.

Brilliant!

A million thanks...great explanation!! Do you know the difference between those smaller and full sized model files? My C drive can barely contain the full sixed files.

Great !! Very good explanation.

so im not even able to place text beneath each other. either enter or shift enter just generates text, and if i but the breaks in on the same line it doesnt seem to work

welcome to matrix !!! which voice you used for video narration?

I really enjoyed the way you laid this out with consistent examples across each model so the effect of each was more clear.

Thank you very much. You deserve a new subscriber!

Good results.

Thank you for a very clear explanation of how to use control net. Your other videos give very clear yet concise information. It is very much appreciated.

i can't change model in controlnet it only show none. can someone tell me pls