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
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.
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..
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.
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.
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?
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
This was very helpful with understanding Lora.
But you will never understand Laura.
I'm still just happy with the base Fooocus thing
Nothing wrong with that. Makes things easier. 👍
I'm just a simple man haha @@KLEEBZTECH
The Mech_Dystopia LoRa is my favorite this week,
Will have to check it out. 👍
Nice one Kleebz, I'm an SD-Forge user but you've shown me the versatility of Fooocus.
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.
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..
Thanks!
Welcome!
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?
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.
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.
Skip just skips to the next one and stop completely stops all generation.
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?
Actually been working on training LoRAs the last few days. Trying out OneTrainer at the moment.
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.
@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. 🙏
Can we use this on fastsdcpu I'm trying but it's not working please make a fastsdcpu tutorial for this midjourney mimic lora
I am not really familiar with fastdcpu myself to say. I have a feeling probably not since not all UIs seem to support it.
Personally I prefer the non Midjourney loook. It seems more natural, most of the time at least.
If going for that then yes I agree in most cases.
How add lora in fooocus with Google colab plz
This should guide you in the right direction. github.com/lllyasviel/Fooocus/discussions/1609
Why aren't you using JuggernautXL v9?
I don't use that one for testing things out yet.
@@KLEEBZTECH It's all clear :)