Free workflows are available on the Pixaroma Discord server in the pixaroma-workflows channel discord.gg/gggpkVgBf3 You can now support the channel and unlock exclusive perks by becoming a member: pixaroma ruclips.net/channel/UCmMbwA-s3GZDKVzGZ-kPwaQjoin Check my other channels: www.youtube.com/@altflux www.youtube.com/@AI2Play
I cannot begin to thank you enough! The amount of (FREE!!!) resources you offer, the way you explain and teach (that even the most layman of us can easily follow), and, have I mentioned, the amount of FREE resources you offer?! Really, I hope you know that your hard work does not go unnoticed! At the moment, I'm unfortunately unable to reward you financially for your amazing work and effort - which I truly intend on doing as soon as I'm able to, cuz again, you deserve every penny! - so, until then, I'm hoping that this message will in some way show you my (our) appreciation. 1000 x and more, THANK YOU!!! 🙏🙏🙏🙏💯💯🏆🏆💪💪💖💖🥰🥰
another great video 😃 But what if you want to go the other way? I've made an image that ins'nt quite as realistic as I want. Can I do the same but just use a "Realistic" LoRA?
@pixaroma i have tried in a couple of ways, but never succeed in doing it. So if you have any ideas? 🤔 It seems a bit harder to remove a style than adding one. And please share, I'm still pretty new at this so it's not exactly easy 😊
I didn't have time to test it, is possible to be harder, but i usually just generate how i want it, like directly realistic in the first place, but with image to image with high denoise probably will do something, just Will be hard to keep same face with people
Hey @pixaroma. Regarding the "Image to Watercolor with Lora and ControlNet" workflow, could you please tell me why you are using a different seed number for KSampler in the upscale section? Can we use the same seed number as one in the image generation section? It looks like if I use the same seed number and change the number of steps to '1', I am able to get the same image but upscaled in two different sizes.
If is the exact same seed the noise is the same and the image will look ugly you can use a fix seed if you want that will work just to be different from the first seed from ksampler, i also i let it random because i upscale multiple times until I get a version without errors, and since first seed is fixed it doesn't regenerate that step so it only upscale from where it left
@pixaroma I see. From the upscaling tests that I did, when using the same seed number as the one used for image generation and changing step to 1, it produces the same image but upscaled, which is what I am looking for.
Not sure it can do much with one step probably is using the model upscaler, so that probably will give you same results without ksampler only using model upscaler
All i saw for comfyui is a node that hasnt been update from a year and used sd1.5 models, so the quality is more like GIF like not what other video models can do github.com/spacepxl/ComfyUI-RAVE?tab=readme-ov-file
depends on what you do, are apples better than pears? Android better than Apple🙂 that continuous discussion. For me yes is better because I can do my own workflow and combine different nodes to create a workflow that other can not do or didnt think to do. But you need some times to learn all the basics to be able to use it how you want.
With flux it works but somehow not as good as with sdxl, probably because Flux knows less art styles compared with flux, that kind of struggle with some watercolor paintings. And sdxl is way faster, but it should be the same process like in this workflow
i didn't manage to install ComfyUI-Easy-Use node even with cmd and trying pip install -r "G:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Easy-Use equirements.txt" so i remove easyuse prompt and replace them with 2 normal PROMPT and add a powerlora it seems to work well thank
Glad you figured it out , usually that node is installed from manager, and if your comfyui is portable you usually use a different command because python is embeded
![Felix "Unfair" | [Stray Kids : SKZ-PLAYER]](http://i.ytimg.com/vi/Oswujxm2Ag0/mqdefault.jpg)
Free workflows are available on the Pixaroma Discord server in the pixaroma-workflows channel discord.gg/gggpkVgBf3
You can now support the channel and unlock exclusive perks by becoming a member:
pixaroma ruclips.net/channel/UCmMbwA-s3GZDKVzGZ-kPwaQjoin
Check my other channels:
www.youtube.com/@altflux
www.youtube.com/@AI2Play
The entire video series is a gift that helps so many of us who want to learn and experience ComfyUI. Thank you!
Thank you so much for your support ☺️ lets hope this will be a long series ☺️
I cannot begin to thank you enough! The amount of (FREE!!!) resources you offer, the way you explain and teach (that even the most layman of us can easily follow), and, have I mentioned, the amount of FREE resources you offer?! Really, I hope you know that your hard work does not go unnoticed! At the moment, I'm unfortunately unable to reward you financially for your amazing work and effort - which I truly intend on doing as soon as I'm able to, cuz again, you deserve every penny! - so, until then, I'm hoping that this message will in some way show you my (our) appreciation. 1000 x and more, THANK YOU!!! 🙏🙏🙏🙏💯💯🏆🏆💪💪💖💖🥰🥰
Thank you, any like and comment help to boost the channel, that works for me ☺️
Btw, this workflow was EVERYTHING I needed!!!! You, Sir, are THE Man!!! 💪💯🙏🙏
Good tips ! Thank you for the tutorial !
Great work as always, thank you so much!! 🙂
Another great tutorial! 👌
Another great episode, thank you!!!!
Wow, what an amazing tutorial! 🎨✨ Thank you, Pixaroma, for sharing this incredible workflow
you are welcome Uday 🙂
Really interesting work flow with great results thank you.
Thanks marcel ☺️
You are great!!!
thank you so much, legend
Excellent tutorial. Thanks for putting this together. Looking forward to trying it out in the coming days.
thanks 🙂
Nice. Very nice output.
Thanks 🙂
Wow. Thanks!
amazing tutorial as always, can you also create a tutorial on image/text to 3d? with how instructive your videos are I know it would be awesome
I will see what i can do :)
For the algorithm!
Thank you ☺️
another great video 😃 But what if you want to go the other way? I've made an image that ins'nt quite as realistic as I want. Can I do the same but just use a "Realistic" LoRA?
Yes you can try, there are some realistic lora out there
@pixaroma i have tried in a couple of ways, but never succeed in doing it. So if you have any ideas? 🤔 It seems a bit harder to remove a style than adding one. And please share, I'm still pretty new at this so it's not exactly easy 😊
I didn't have time to test it, is possible to be harder, but i usually just generate how i want it, like directly realistic in the first place, but with image to image with high denoise probably will do something, just Will be hard to keep same face with people
Could you please tell me where to get the ComfyUI resource monitor that you show in your video?
Found it! Crystools custom node is what I needed to download.
Yes that is the one
Hey @pixaroma. Regarding the "Image to Watercolor with Lora and ControlNet" workflow, could you please tell me why you are using a different seed number for KSampler in the upscale section? Can we use the same seed number as one in the image generation section? It looks like if I use the same seed number and change the number of steps to '1', I am able to get the same image but upscaled in two different sizes.
If is the exact same seed the noise is the same and the image will look ugly you can use a fix seed if you want that will work just to be different from the first seed from ksampler, i also i let it random because i upscale multiple times until I get a version without errors, and since first seed is fixed it doesn't regenerate that step so it only upscale from where it left
@pixaroma I see. From the upscaling tests that I did, when using the same seed number as the one used for image generation and changing step to 1, it produces the same image but upscaled, which is what I am looking for.
Not sure it can do much with one step probably is using the model upscaler, so that probably will give you same results without ksampler only using model upscaler
@@pixaroma ah ok. There were just quick tests anyway 😁. You're the teacher and I'm just the student. Thanks for responding to my questions. 🙏
hi , can you do a video on rave?
and how to get a consistent vid
It'll be a great help
All i saw for comfyui is a node that hasnt been update from a year and used sd1.5 models, so the quality is more like GIF like not what other video models can do github.com/spacepxl/ComfyUI-RAVE?tab=readme-ov-file
is comfyui better than forgeui?
depends on what you do, are apples better than pears? Android better than Apple🙂 that continuous discussion. For me yes is better because I can do my own workflow and combine different nodes to create a workflow that other can not do or didnt think to do. But you need some times to learn all the basics to be able to use it how you want.
Why SDXL? In what situations is it better to use SDXL instead of Flux?
With flux it works but somehow not as good as with sdxl, probably because Flux knows less art styles compared with flux, that kind of struggle with some watercolor paintings. And sdxl is way faster, but it should be the same process like in this workflow
gracias , me pasa el worflow por favor
Is on discord, link in the description of the video, free to download
hello, your discord says invite expired or might not have premision to join. can you send a fresh link
The link from the RUclips header should always work, here discord.com/invite/gggpkVgBf3
@pixaroma thank you!
i didn't manage to install ComfyUI-Easy-Use node even with cmd and trying pip install -r "G:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Easy-Use
equirements.txt" so i remove easyuse prompt and replace them with 2 normal PROMPT and add a powerlora it seems to work well thank
Glad you figured it out , usually that node is installed from manager, and if your comfyui is portable you usually use a different command because python is embeded
Next Ep. Please teach "How to change Anime or comic charector style to realistic. Please
I will see what i can do, i think it is a bit more difficult, but I will do some tests
@@pixaroma Thank you Sir.😍