Stable Diffusion - Midjourney Mimic LoRA - Check it out!

Подписаться 12 тыс.

Просмотров 6 тыс.

50% 1

Master Generative AI for Creative Image Generation! 🎨 In this video I check out the Midjourney Mimic LoRA. #Fooocus #StableDiffusion #DigitalArt #ImageManipulation #CreativeTools
Download link: civitai.com/models/251417/mid...
Adding LoRAs to Fooocus: • Stable Diffusion - Che...
Fooocus is a great interface for using Stable Diffusion and is very easy to get started. It also will run on systems with only 4GB VRAM.
I am running on an i5 32GB RAM Nvidia 3070 8GB VRAM
If you find the video useful and would like to tip, RU-vid does have the Super Thanks option. Those are greatly appreciated so I can have my coffee!!
☕ BUY ME A COFFEE: ko-fi.com/kleebztech
Download Fooocus: github.com/lllyasviel/Fooocus
How to install Fooocus video: • Stable Diffusion - Dow...
Fooocus Beginners Guide: • Super Easy Stable Diff...
Fooocus Upscales and Variations: • Stable Diffusion - Foo...
Checkpoints and LoRAs the Basics: • Stable Diffusion - Che...
Fooocus Poses and FaceSwap - Image Prompts: • Stable Diffusion - Pos...
Zoom with Outpainting: • Stable Diffusion - Zoo...
Inpainting with Fooocus - Don't Regenerate, Fix!: • Stable Diffusion - Inp...
Background Replacement with Fooocus: • Stable Diffusion - Bac...
Fooocus Tips and Tricks (and AI Hands) • Overlooked Fooocus Tip...
Stable Diffusion - Styles in Fooocus - How do they work?: • Stable Diffusion - Sty...
FaceSwap and Consistent Character TipsPart 1: • Stable Diffusion - Fac...
FaceSwap and Consistent Character Tips - Part 2: • Stable Diffusion - Fac...
00:00 Intro
01:30 How to Download and use
02:20 Lightning Results
03:10 Standard Results
05:05 Comparison Lightning vs Quality

Наука

Опубликовано:

11 июл 2024

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист

Посмотреть позже

Комментарии : 36

@KLEEBZTECH 3 месяца назад

If you find the video useful and would like to tip you can buy me some electricity for all these image generations. It is greatly appreciated! ko-fi.com/kleebztech

@lucashuse3572 3 месяца назад

This was very helpful with understanding Lora.

@KLEEBZTECH 3 месяца назад

But you will never understand Laura.

@sb6934 3 месяца назад

Thanks!

@KLEEBZTECH 3 месяца назад

Welcome!

@jimp925 3 месяца назад

The Mech_Dystopia LoRa is my favorite this week,

@KLEEBZTECH 3 месяца назад

Will have to check it out. 👍

@Designing-hc5pz 3 месяца назад

thx for the tutorial mate it's have much midjourny like influence and can you also make a tutorial on how to take any cloth with no background and wear it to any person..

@iseverynametakenwtf1 3 месяца назад

I'm still just happy with the base Fooocus thing

@KLEEBZTECH 3 месяца назад

Nothing wrong with that. Makes things easier. 👍

@iseverynametakenwtf1 3 месяца назад

I'm just a simple man haha @@KLEEBZTECH

@nikgrid 3 месяца назад

Nice one Kleebz, I'm an SD-Forge user but you've shown me the versatility of Fooocus.

@KLEEBZTECH 3 месяца назад

I use many different ones myself and find they all have their uses but Fooocus is great for most of what I do. I see great potential for Fooocus overall.

@MattyMilligan 3 месяца назад

Thanks Rodney. Also use midjourney and fooocus. Still learning comfyui but unable to get some nodes to work, which frustrated the heck outta me. Hate the a1111 interface. Akool has the best video face swap so I create my characters in fooocus or mj, then use reactor or akool for that one thing. Runway has an incredible rotoscoping tool and the motion brush is something I've been using to animate the fooocus, mj and comfyui images, then edit it all together in final cut. Should be using Adobe premiere or DaVinci resolve but learning too many tools at once is overwhelming. Have you tried training your own Loras via Kohya or in general?

@KLEEBZTECH 3 месяца назад

Actually been working on training LoRAs the last few days. Trying out OneTrainer at the moment.

@KLEEBZTECH 3 месяца назад

One downfall of doing these videos is I spend too much time testing that I don't get to experiment with other stuff as much as I would like.

@MattyMilligan 3 месяца назад

@KLEEBZTECH I figured. You are the best at fooocus tutorials I've seen and no one else has a better understanding of this tool. Mad respect. 🙏

@a_vin7644 3 месяца назад

I use this LoRA as default with 0.6. Not bad. I have a stupid question. What I can do with "skip" and "stop" buttons? When I worked with DD, I can stop image generation and get under generated image. In Fooocus I can only skip image generation.

@KLEEBZTECH 3 месяца назад

Skip just skips to the next one and stop completely stops all generation.

@tristanthedarkstar 2 месяца назад

My images tend to look kinda blurry or painted. What settings, styles, and prompts do you use to get ultra realistic detailed pics of people?

@KLEEBZTECH 2 месяца назад

That can be difficult to say since there are so many factors. I usually use the defaults for many things and the quality settings since that will have more steps and better for realistic content. the speed setting is good for other stuff like comics and anime. You can also try adding things like "highly detailed" to your prompts. When using styles I recommend knowing what they add to the prompt by looking into the style files or just looking at the metadata/log for the final prompts that those styles create.