No video :(

ControlNet Reference-Preprocessor Comparison, Settings, Troubleshooting, and Style Transfer Workflow

Подписаться 4,8 тыс.

Просмотров 11 тыс.

50% 1

In today’s video, I will teach you everything you need to know about using the ControlNet Reference Preprocessors for Stable Diffusion in the Automatic1111 Web GUI.
Starting out simple, I show you very basic usage of the tool then quickly move onto a comparison of the three Reference Preprocessors to identify what each does and doesn’t do.
Next, I get technical to identify which settings like Style Fidelity are key for using ControlNet Reference. To round things out, I provide solutions to common problems that can occur with ControlNet Reference so you can maintain image quality while pushing it to the limit.
Finally, I show some examples for workflows for Style Change and for creating variations of an initial image.
Intro - 00:00
Preprocessor Explanation and Comparison - 01:45
ADAIN - 02:00
Reference Only and ADAIN+ATTN - 04:20
Preprocessor Review and Pros and Cons - 05:46
Settings for ControlNet Reference - 06:25
Ending Control Step - 07:15
Style Fidelity - 07:40
Weight - 09:02
Troubleshooting Blurriness- 09:50
Troubleshooting Excessive Brightness or Darkness - 10:41
Workflows, the law of equivalent exchange - 12:49
Workflows, model selection - 13:39
Workflow, Style Change - 14:19
Workflow, Image Variation - 16:39

Опубликовано:

16 авг 2024

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист

Посмотреть позже

Комментарии : 34

@CheckTheWiki Год назад

Finally a channel that is actually teaching things intermediate users need to know. I'm so sick of every video showing how to install SD/Controlnet at the start for padding and then not much else of substance.

@siliconthaumaturgy7593 Год назад

Thanks! That is why I started the channel. When I was starting out, I watched other RU-vid tutorials and found them a bit less informative than I personally prefer.

@lefourbe5596 Год назад

@@siliconthaumaturgy7593 indeed, i still hit my head against a wall when it comes to dreambooth training and Lora for some parameters. many written guide helped me understand what i was missing but as shown in your video. it comes with time and effort.

@lefourbe5596 Год назад

As Always thanks for providing this knowledge for free to the small "deep divers" audience. You work save us precious Time on question we didn't dare to research. I hope you keep on experimenting and stay motivated.

@BabylonBaller 5 месяцев назад

The community misses you bro, your vids are still in a league of their own!

@msampson3d Год назад

Yay! A channel providing high quality SD content. Subscribing!

@Aertuun Год назад

re: your section on excessive brightness or darkness. My experience is that this tends to happen when controlnet is "fighting" against what the model/prompt would usually want to produce. i.e. both sides are pulling in different directions. I've tended to solve this by improving the prompt so that the model's "standard" output more closely resembles the controlnet image, or by simplifying the prompt to give more flexibility and remove the conflict of model vs controlnet. Your solution also works of course; weakening the "strength" of either side of the fight lets one of the sides win more easily.

@jamarti Год назад

Your style reminds me a lot of the "Battle(non)sense" yt channel, which is great. Comprehensive and to the point. I love your content

@patricklearn6536 Год назад

I love this channel. I use comfy UI but everything here I can translate to that. Thank you for these very informative videos.

@lefourbe5596 Год назад

an incredible amount of work i should say ! pure madness to pull out in only two weeks !

@siliconthaumaturgy7593 Год назад

Thanks. This one was definitely rough to research.

@RieslinZ Год назад

Thank you so much for all the contents you have provided! I never thought about using hires fix without upscaling!

@lioncrud9096 Год назад

thank youu! I've been struggling with this tool and needed in-depth overview

@philiproberts Год назад

I've been trying to do Tiled Diffusion with the multi diffusion upscaler extension. And all I ever get is multiple images forced together ungracefully. A video on this extension and the tile controlnet model would be awesome. And your awesome too thanks for the videos 😊

@siliconthaumaturgy7593 Год назад

Tiled Diffusion is on my radar and near the top of my list. It's probably going to end up being multiple parts since there is so much in that extension

@user-yu4ix4qs9q Год назад

Great job. Helpful, clear. Thanks

@mr2ti41 10 месяцев назад

Just found your channel - Great stuff!

@ekot0419 10 месяцев назад

Thanks for the tutorial. Short, but every second of the video is knowledge. I took a lot of notes from this 1 video. I would like to ask you why you think that highres fix is necessary for text to img? I haven't used SD enough to make a call. But from a professional designer's point of view, also using my not too cheap PC to try, adding this step does significantly increase the render time. So I incline to think that finetuning can be moved to img to img. But again, I am just a baby in SD. What do I know. Please explain a bit if possible. thank you. liked and subbed. xyz plot is amazing. 1 shot and we get to see all of them. Perhaps this is why you suggest using Hires fix everytime. Only issue is, I can totally feel the difference in terms of the wait.

@DanailDichev Год назад

you are the boss! (I'd love to see your take on outpainting:1.5)

@andresklagges460 Год назад

Great video as always!

@MrSongib Год назад

10:00 for this part we can fix stuff with Adjusting prompt like you said and maybe adjusting other stuff like VAE, Lora for darken or lighten the image without destroying the composition and some CFG rescaling like "Neutral prompt" extension, There is some setting in aswell similar to this but from the webUI dev they said this one is a bit better (I'm forgot where in the setting tab as well. xd) 18:47 maybe we can use ctrlnet segmentation here. idk great content as always. ty and have a nice day. (I'm done rewatch this and maybe ill watch again if I forgot some stuff as most likely would happen in the future. xd)

@siliconthaumaturgy7593 Год назад

Thanks. ControlNet Reference is definitely the most challenging to use feature I've covered yet, so thanks for your patience. Unlike most other ControlNets, almost everything seems to matter and have a chance to mess it up. It's like riding a raging bull. So I really appreciate the suggestions and I'll try them out soon.

@shorts.cookingasmr 6 месяцев назад

do you know if theres a way to use reference-only without using a prompt? i have an image and i want it to be replicated, but i don't want to prompt it

@KillMode13X Год назад

Thank you.

@krystiankrysti1396 Год назад

best episode yet, very useful info, thanks ! Darksushi is a borked model thats overtrained on anime, you cant do photographs with it which is probably the reason for overbaking

@feizhouji Год назад

very helpful！！

@37hp72 4 месяца назад

how can i made that in comfyui

@meh2063 Год назад

Thanks

@MrSongib Год назад

cool content but hard to follow, the editing jumping around as always and it's kinda hard to focus on what you talking about and what I actually seeing atm. idk how to explain it. i think I need to rewatch this later. ty and have a nice day.

@BabylonBaller Год назад

Yea, I felt the same, but simply pausing often to intake / review the grids helped a bunch.

@roymathew7956 9 месяцев назад

I agree as well. It would be helpful when showing a big grid of images to actually mouse over or highlight the specific ones that you’re talking about. There’s just too much to process all at once when you show the entire grid and it moves very quickly from scene to scene.