Відео

Absolutely fantastic! You have given me plenty of good help. However i have a batch of pre existing a.i images i made of an underground abandoned tubeway. I would like to use these and create VR content. I assume i can use these to convert them into 360 ?

I've been using Stable Diffusion for about a month now, and I'm blown away by how amazing the software is-especially considering it's free! The quality is incredible, and with all the available extensions, it becomes even more fantastic. I’ve even canceled and deleted my Photoshop subscription because I no longer need it.

Wow~ No wonder "Stable Diffusion" is so Good to use! Thanks for this in-depth video. I think you explained it so well. I can't help watching it twice!!

This does not work anymore.

Great work

Taylor Amy Jackson Laura Harris Ruth

You put RealVisXL V2.0 into C? Really? You underestimate this model, I guess. Cause I now use RealVis V5, and it's fantastic - nothing to compare with.

A1111 now works with mac with the half precision parameter

Lewis John Williams Nancy Perez Shirley

Nice! Just a nit-pick about the neural network part at around 3:35; you are correct that each neuron has input weights (w1 & w2) plus the bias - these are the trainable parameters (including the bias, it is not a constant) for this neuron. The output calculation b+(w1*w2)=1.1 is unfortunately not correct - it would reduce the whole thing into a single matrix multiplication and not be capable of adapting to the input data in the manner we desire when using NN:s. The calculation is a two step process. In step one, you multiply the weights with the value/output of the previous connected neuron. In your case if the neuron connected through w1 has an output value of - let's say 1.5 - the input value from that neuron is 1.5*0.2. So you add all the inputs (multiplied with their corresponding weights) up and add the bias as step one. Secondly you take this summed up value and put it through a "transfer function" that can be pretty much anything you'd like as long as it is not linear to obtain the neuron output value. But, as you say, it is these weights (including the bias value) that are adjusted by tiny fractions in each training pass.

excelent. no video I found explains how stable diffusion works this simple and concise

wow Thank you very much

Amazing, I hope to see more videos like this. Very much appreciated

well done man great presentation i came here to find a video for a friend im glad i clicked this one :D

Amazing!

Brilliant

My experience with my PCs: Win10, Fooocus 2.5.0 (SDXL 1.0), 1024x1024 image, base "realistic" preset, no other models or LORAs. Latest GPU drivers installed. Ryzen 5600X, 32GB DDR4-3200, 8GB RX7600 with PRO 24.Q2 drivers, Fooocus AMD version: avg 261 seconds per image Same PC with 24.7.1 gaming driver: 318 seconds per image Same PC with ComfyUI ZLUDA, PRO drivers, same model and settings: 340 sec per image Ryzen 5600G, 16GB DDR4-3200, 8GB RTX3050, standard Fooocus CUDA version: avg 33 seconds per image Newegg has a 12GB 2060 (refurb) for $170 so I have it on the way for additional testing this week.

The mac’s speed can be improved by running macOS Sequoia and by converting the Stable Diffusion model from Safetensors (or any other type) to CoreML so it can run on the Nerual Engine instead of the GPU or CPU. These can vastly improve the performance.

rtx 4090 vs rtx 3060, with more than 5 times more expensive. we would only get 3 times of performance.

Great tutorial!! I have one question: how to make the talking avatar more realistic by adding some eye blinking?

Please tell me about the difference between learning objects (people etc.) and learning concepts (painting style, etc.). Thank you very much. The explanation was very easy to understand, and I am grateful.

What about the next video? 🤣

Neat explanation.

Seems like it needed to be 20 minutes. xD

Is this an Unlocked and Unleashed version that you are talking about or is this software just a normal Locked version? Thanks and I look forward to your reply. John E

I have done all the process but in the end stable diffusion don't let me to choose my custom model. One thing I notice is that my model is a ckpt file, and all the other models that I can choose ends with safetensors

Hello. help me with choosing a video card for the difusion stem. I have a choice between rtx 3060 12gb, intel arc 770 16gb and rtx 4060 8gb, what do you advise?

This is amaz8mg!

This was perfect! 👍

what if i wanted to generate pictures of two different real people in the same picture?

where can i get the app?

When I watched this, You said to press Shift + Option. I'm using a Dell computer with no option button and you gave no alternate methods so I'm now just stuck.

thank you, very very much

Thank you.. exactly what I was after..😅

Thanks for the video: after months of trying finally I've managed to install Stable Diffusion on my Mac. Only one problem now, when I try to generate an image this text pops up: AttributeError: 'NoneType' object has no attribute 'lowvram' Time taken: 0.0 sec. Do you know whay is this happening and what can be done?thanks

How do i cast an on-the-ground shadow from the dancer?

lots has changed since then. now there are plenty of ai services that will extract mocap from video and export as fbx

Faboulus video. Will used as ref in my Master thesis.Thanks!!!

"smack lips" Mac is slow. I agree

Congrat ! What a nice job ! I have my own set of test but I think I will integrate your prompts. I noticed that many models change drastically from one version to another (Juggernault XL 9 to 10 for instance, classic or Turbo/Lightning versions)

Has something changed with this process? It seems like the "Safetensors" checkbox in the Model Download section is gone.

It seems great!! i couldn't test because the manager don't give me access to "IPAdapterApplyEncoded" missing for me...

Thanks for this detailed video. One question: what minimum GPU is needed for the complete workflow, and which of the individual steps need the most GPU RAM?

Which one is better, the Rtx 3060 12GB or 3060Ti 8GB?

7:57 i been using colab to get to familiarize myself with SD. I feel I am now enough and want to start generating locally. I don't want to invest too much initially, so I am trying to figure out what's the best low with good enough performance and I thought the 3060 would be a good start, nothing less. Your test suggest that, now I trying to decide between RTX 3060 vs RX 6600 vs Arc 580 >. I am next going to see if Arc can generate and if so, at what results. 5700XT should be good too, but for SURE the power consumption will be crazy.

Fantastic job! Well done and thanks. But like you said,, it is getting a liitle bit stale… I would really like an small update on your A and B models and maybe some other up-and-comers. I mostly use Juggernaut, but you have given me nice pointers on other, maybe better models. Thanks again.

I didnt understand about colabs, does it has limit on generated image per month?

Promo-SM

Thank you so much fow this easy and detailed tutorial! im a total noob with computers and very new to stable diffusion and until this video i was just confused and intimidated because i dot know any of these words and couldt follow. but this time i made it and it worked and tbh it was so much easier than expected... thx a lot!!!

Great, thank you, easy to understand visual lecture!