I'm already using WD14 for magic prompting lol but I would use concatenate text which is not as nice as this String Function node. So thanks for the trick, I'm gonna update my workflow again ^^ it never stops really
Its mind blowing how amazing all this is, generating an image you couldn't even imagine is an amazing thing, no matter how amazing your drawing is, you are limited by imagination, but here you can just batch run your initial ideas to get endless inspiration. It seems the major issue with image generation our communication with the models, with img2img and control net you can get more control.
Hi Olivio, like the WD14 tagger node, is there a node which can get you the BLIP captioning of an image? Would ideally like to use that as input to a segmentation model for swapping things.. TIA! 😊
I don't have the Image Resize node, I downloaded the named image resize node that came into the manager, but it's not the same one and cannot do what you do, just crop the image
cant access the cloud workflow due to having to join discord and i dont know how to do that, how can i follow this workflow? i've download the node locally but im missing some of the properties that this set up has so my only option is to get to the cloud setup but i cant do that cuz of discord? what should i do next?
@XuRZaL 1 hour ago Thank you, this has been so helpful. ComfyUI is very user friendly once you get past the learning curve (which you have shown me), and you have absolutely made that curve so much shorter. On to L6!!!
Can we get an explanation as to why all of these videos load different VAE's for the decoding? Why is it constant that the vae is never the one from the initial model???
For those of us who are trying to construct these from scratch (following along) I don't see where/how we are supposed to be able to find this "Image Resize" node. There's no "search node" and I don't see it on the node options. Where do these things come from and how are we supposed to know what node collections we need to load down?
The workflow is linked below the Video. This is part 5. If you don't know how to find nodes, watch the other videos. For node search you double click on the background and a search pops up. Use the workflow i provide and install the packs i use via the manager (watch the other videos to learn how to install and use the manager)
how would you add latent upscale in this type of workflow, where you are using low denoise to get close to input image result. I tried to do latent upscale with low denoise on second K-sampler, but end with a poor image quality. If I increase denoise it changes image which is not I want.
Thank you for making these vids! They really help me get into Comfy without feeling too overwhelmed
I'm already using WD14 for magic prompting lol but I would use concatenate text which is not as nice as this String Function node. So thanks for the trick, I'm gonna update my workflow again ^^ it never stops really
Thank you for the amazing lectures as always!!!
Its mind blowing how amazing all this is, generating an image you couldn't even imagine is an amazing thing, no matter how amazing your drawing is, you are limited by imagination, but here you can just batch run your initial ideas to get endless inspiration.
It seems the major issue with image generation our communication with the models, with img2img and control net you can get more control.
Thank you Olivio for this Series,, so many tool for creativity --- i scream!
Wonderfully explained. Above all, nice and slow and relaxed 🙂I spend most of my time looking for and installing missing nodes though 😀
This is absolute wonderful tutorial! Thank you!
Awesome teachings, thank you!
This is an amazing technique. I'm getting great results with it.
great work Olivio kepp going on 💪
Using WebcamCapture node as the input photo was fun
As I read "WD14" I thought this was some kind of motor oil - but it's quite handy indeed 👍
Hi Olivio, like the WD14 tagger node, is there a node which can get you the BLIP captioning of an image? Would ideally like to use that as input to a segmentation model for swapping things.. TIA! 😊
Indeed amazing!
Thanks for your lesson, it helps a lot, thanks !
Thank you for this tutorial video!
this could be applied to have congruent detailed styles in animated generations
I have a short question regarding Automatic 1111. While some checkpoints give fast results, why other check points don't work the same.
Díky!
Thanks Olivio. Love you.
How to download the WD14 in ComfyUI model and which folder to install it in?
amazing
I don't have the Image Resize node, I downloaded the named image resize node that came into the manager, but it's not the same one and cannot do what you do, just crop the image
You need Comfyui essentials node. Its been updated since this video came out and looks different.
Yeah I noticed, but still cannot resize, it just squeeze the image
Thanks!
thank you very much for your support :)
Next you could do controlnet to make the pose that you want, by another picture you have
cant access the cloud workflow due to having to join discord and i dont know how to do that, how can i follow this workflow? i've download the node locally but im missing some of the properties that this set up has so my only option is to get to the cloud setup but i cant do that cuz of discord? what should i do next?
@XuRZaL
1 hour ago
Thank you, this has been so helpful. ComfyUI is very user friendly once you get past the learning curve (which you have shown me), and you have absolutely made that curve so much shorter. On to L6!!!
vielen dank
Can we get an explanation as to why all of these videos load different VAE's for the decoding? Why is it constant that the vae is never the one from the initial model???
For those of us who are trying to construct these from scratch (following along) I don't see where/how we are supposed to be able to find this "Image Resize" node. There's no "search node" and I don't see it on the node options. Where do these things come from and how are we supposed to know what node collections we need to load down?
The workflow is linked below the Video. This is part 5. If you don't know how to find nodes, watch the other videos. For node search you double click on the background and a search pops up. Use the workflow i provide and install the packs i use via the manager (watch the other videos to learn how to install and use the manager)
How to fix problem with install imageResize+?
On the window that lets you load and save workflows. go to manager and click install missing custom nodes
the problem is not so easily solved :)@@MrStronghole
@@ingabuga me too, but i find upscale image , its the very similar and work. later i dont find string function...i dont find it
I found the solution! After launching its model, go to "Install Missing Custom Nodes" in the manager, install everything, restart and BOOM, it's done!
@@SedidNewEnvironment it's working for me too! thanks
how would you add latent upscale in this type of workflow, where you are using low denoise to get close to input image result. I tried to do latent upscale with low denoise on second K-sampler, but end with a poor image quality. If I increase denoise it changes image which is not I want.
Man I m stuck with this same issue, have you figured a solution yet?
I loved it when he created a gundam lol.
I can't find Image Resize node :(
me too, but i find upscale image , its the very similar and work. later i dont find string function...
@@guille1935 I've found the node, calls image-resize-comfyui on github :)
6:42 here I'm not able to find string function.
you need ComfyUI-Custom-Scripts
Olivio - Did you give up on A1111 ?
You have to give up on a1111 too,
Comfyui is the future.
Yep comfy is way better.
@@J3R3MI6 not really
👋
How ai read and convert prompt, i mean who write the code to interpret english words .
the model is trained to create a english word description
InvokeAI is better for me)
Gracias Olivioooooooo