Видео

Missed opportunity, they should of named it SpaghettiUI.

After trying to install StableDiffusion with automatic1111 from different videos, I have to say, this is the most complete one. THANK YOU <3

How do you add that restore faces checkbox? No one mentions it in tutorials.

if you guys are getting an error when running the webui-user batch file saying "runtime error: could not install torch", to fix this look up how to install pytorch manually and follow the video tutorials. Also deleting the venv file in the a1111/stable diffusion file seemed to help too

Thank you! Installing Comfyui now. I was scared of duplicating my 1111 models, happy to see we can link them together!

Very well explained! Wish you could create a crazy workflow and explain them as this. Especially IPAdapters and controlnet,wildcards,lycoris and other model types. thank you so much

If SDXL is the checkpoint then how do I use other checkpoints that require SDXL? such as Pony Diffusion

Awesome!! thank you!! btw can you show us how to implement this function in ComfyUI.. and how to setup MuseV and MuseTalk in ComfyUI as well.. thank you!!

how can i downgrade the python version . i tried but webui did not recognize

wonderfull tutorial, pls make more so we can learn, in img2img lighting tutorial im trying to exactly as u explained but why my images appear black and white? although they pick the lighting direction from black and white gradient but images renders black and white. can u help me out

0:23 well default new instal should be fast. you can allways change something get faster removing quality xD that look slower than my rtx 2060, but rtx 4090 its blink of eye. why i need make faster than blink LOL xD. its not just 4090 it whole new PC. price was 2x more. have to be faster bcoz usually things cost same and you get faster, but yeah 2k gpu blink of eye vs. what eva 2060 cost 500 back then LOL

The video content is very good. But it's too fast. Thumbs down, sorry.

does it matter which checkpoint i use for this?

Thank you for being very clear and informative in this video. There are some really use-worthy tips in it too. Subscribed.

superb video. thank you

This has to be the clearest and most comprehensive descriptive tutorial of control net that I have seen. Again, your videos are top-notch! Saving these to rewatch and sharing these with my friends getting started

Thanks so much! What does it mean if I download a file from CivitAI and try to copy it in and run, but clicking "Queue Prompt" does nothing? Does that mean I am missing a model or something?

The humor in the first 30 seconds was amazing! Your videos are some of the clearest and most concisely packed video tutorials. Excellent work!

but HOW DO YOU GET THE CHECKPOINTS AND MODELS YOU ALREADY DOWNLOADED WITH A1111? you never showed how to load them up!!!

Why did you stop making new video? All your videos here very detailed, easy to learn. You should do more.

Mind blown with the skin tone sketch to place your person. Nice one!

I keep getting an error of "TypeError: Failed to fetch" when i click queue prompt dunno what this could mean, does it has something to do with my web user bat file only producing black photos in stable diffusion?

Why is ipadapter keep saying failed install? Thanks

and yet nothing about controlnet

what is the batch tab?

I dunno whats changed but my control doesnt show... weird...

Your voiceover and editing is just right bro 😂

i don't have restore faces in my sd-webui img2img pannel

why its hard and complicated ????!! why they dont make easy menu ?

Exactly what I was looking for. Thanks for sharing.

thanks

Perfect.

No restore faces or tiling option for me, only hires. fix

7:50 Just 1 note here about inpaint sketch + de-noise: In inpaint SKETCH, you give a base with what you draw. So you usually don't want to bump up the de-noise too high when using "Original" mode, or SD might veer off of what you intended with your drawn thing too much. The limit is dependent on the image ofc. But 0.8 is usually too much for me in that mode.

This taught me so much, I really appreciate it. I only have one question. Do the colours used in inpaint sketch make any difference?

Yeah really helped me well. I was working on those but don't know how to use multiple checkpoints and Lora now you cleared me thank you so much brother.

im lost on your upscale what was the previous output?? and how much did you upscale? all I see is a image change

Im using comfyui on the web, is there another way to install checkpoints lora without first downloading it, for example how do i use the GitHub link in the manager to download models from civitai, or do you know any other other way around as long as i dont download it

Yeah I’m scared of comfy, I’ll try to do this video

There no more refiner on the huggingface site. Why is that?

ive been running v1.5, so can I just drop SDXL base and refiner into the program files and use sdxl models

What about the CUDA drivers? Does the installer install those on its own or do I have to download them separately?

Awesome explanations! I've only been playing with SD for a week, and have been struggling with sorting this out.....no longer! Quick concise explanation with a brief visual demo. thank you!

Okay making progress! so im using a preexisting image for a pose i found on images and if i set denoising strength to over 0.2 it will start deviating heavily so i cant touch that denoise setting at all i will get cats and cows again! hmmm........ quantum physics realm i will figure it out eventually.

This was awesome and very well done. Sub!

Thanks for the fresh install help. Not sure why but I don't see the "refine faces" option. Was there an update that eliminated that?

Even doing what you are doing its not working and ive been at it for weeks! i want to cry and just give up! At least im good in the computer hardware department ! i better leave my hand of sutff i dont understand! so frustrated, i cant anymore. When you guys get a bit of variation form your original im getting cats and dogs! xD what the hell is going on! i just want the original image!

Love your content. Thank you for all the work you put out. Been having problems running some Preprocessors in ControlNet a1111 and hoping you can help me. I've tried updating, deleting and reinstalling, I've tried running SD a1111 in different browsers, redownloading the models, tried etc., and I just keep getting the following error: " urllib.error.URLError: <urlopen error [WinError 10054] An existing connection was forcibly closed by the remote host> " Anything come to mind that could help me solve this? Like I mentioned, only a few preprocessors work. For example, for "Depth," only the "depth_zoe" works, all others give the error. For "OpenPose", none of the preprocessors work. This happens both in SDXL and in 1.5 models. "Canny" on the other hand, they all work. Any ideas would be great. Thank you in advance.

No matter what I do, I can't seem to get any of the prompt to affect the original image- it almost acts like it's just trying to "redo" the original image itself- no new changes from the prompts. I'm new to Automatic1111, but I'm familiar with the basics of SD. Any tips or solutions? Thanks!