I'm watching your videos and they are great! Things just work as expected and I have to say that is amazing (I watched a lot of random videos that look amazing and after trying the workflow the results were bad). You know how I can use an image as reference to other for the inpaint? I'm trying to generate multiple images from the same person but I'm having trouble with the clothes or other details that change all the time (like diferent figures at the shirt, diferent cuts at the jeans, different earings...). I will keep searching for the best solution but it would be greath to have your opinion about it. Thanks for the videos!
I had some more unruly hair and it didnt work very well. The model was generating faces and weird stuff where the hair was supposed to be. Think I'll do it with photoshop for now :(
My video suggestion is the use of other Non-image models such as for example LLM's, or 3d generative models and even directed movement "move here, do this, do that" sort of thing
can you plug this differential diffusion node into any impainting solution? Combined with COntrolNet for example. Edit: yes it does. Just plug in the Differential Diffusion node and you're good to go. Just that little node changes everything. What a discovery, wow
I'm new to this but shouldnt the Gaussian Blur Mask output be connected to the InpaintModelConditioning Input? It seems to work better this way for me at least.. Anyway thank you for the tutorial!
Greetings, I have had problems with the video face swap workflow with the extensions using pinokio stability matrix and ComfyUI portable. You could delve deeper into the solutions in pinokio in particular. Thank you so much
Thank you for pointing that out! Differential diffusion is a powerful technique used for image inpainting, which enhances the process by providing smoother transitions and more natural-looking results. Let me know if you have more questions!
my impact pack broke yesterday and failed import tried fix, update, removing nodes and readding, uninstalling them and reinstalling, reinstalling comfyui, cant figure out why lol but saving the video for when i do lol
Man this was amazing liked the VID. However, i have one request PLEASE! Maybe you can be of help. I always used to use 2 models in Fooocus: 1) Juggernaut XL for Fantasy compositions 2) Realism Engine SDXL for in-painting the faces (ONLY the faces) and it works wonders. I'm very new to Comfy UI but judging from what you are doing and your previous videos, this workflow should not be an issue to replicate in Comfy UI right? Any chance at all you could give some pointers, I'll try to send you that well deserved coffee money soon as I have my payday my guy!
Thank you for your support! I'll be posting several videos soon that will help you replicate and enhance your workplace from Fooocus in comfyui. Feel free to join my Discord if you need assistance or want to discuss any challenges you're facing. I'm here to help. Have a great day!
What would you like to see next?
Real time voice cloning 👍
ipdapter pleas !!)))))
Videos? Is it possible?
I'm watching your videos and they are great! Things just work as expected and I have to say that is amazing (I watched a lot of random videos that look amazing and after trying the workflow the results were bad). You know how I can use an image as reference to other for the inpaint? I'm trying to generate multiple images from the same person but I'm having trouble with the clothes or other details that change all the time (like diferent figures at the shirt, diferent cuts at the jeans, different earings...). I will keep searching for the best solution but it would be greath to have your opinion about it. Thanks for the videos!
Yes, I could share you one workflow on discord
@Aris_28 thanks! I will msg you there
Great video, got it working in minutes by following this guide! I'd love to see an example of adding a LORA to this workflow? :)
Soon!
2:04 definitely picked the right spot to select, lol😂
Thank you so much for the tutorial! Learnt a lot. Is there any way to do this programmatically? Thanks!
I had some more unruly hair and it didnt work very well. The model was generating faces and weird stuff where the hair was supposed to be.
Think I'll do it with photoshop for now :(
My video suggestion is the use of other Non-image models such as for example LLM's, or 3d generative models and even directed movement "move here, do this, do that" sort of thing
Can you help? Pressed 'open in sam detector' multiple times but nothing come up.
Do you got any error Message?
@@Aris_28 Nope. Just nothing when i press.
Can you make a tutorial on inpainting with mask and IP adaptor V2 to swap a reference cloth image to a model
can you plug this differential diffusion node into any impainting solution? Combined with COntrolNet for example.
Edit: yes it does. Just plug in the Differential Diffusion node and you're good to go. Just that little node changes everything. What a discovery, wow
I'm new to this but shouldnt the Gaussian Blur Mask output be connected to the InpaintModelConditioning Input? It seems to work better this way for me at least.. Anyway thank you for the tutorial!
Greetings, I have had problems with the video face swap workflow with the extensions using pinokio stability matrix and ComfyUI portable. You could delve deeper into the solutions in pinokio in particular. Thank you so much
looking forward ComfyUI Inpainting Tutorial Part 2
You mention Differential Diffusion but you do not explain what it is, how it works, or why we should use it.
Thank you for pointing that out! Differential diffusion is a powerful technique used for image inpainting, which enhances the process by providing smoother transitions and more natural-looking results. Let me know if you have more questions!
my impact pack broke yesterday and failed import tried fix, update, removing nodes and readding, uninstalling them and reinstalling, reinstalling comfyui, cant figure out why lol but saving the video for when i do lol
but nice video for sure! probably one of the easiest to understand and actually learning what some nodes do from your channel! keep it up!
Thank you for your support. Come to my discord I will help you with your problem, I am sure we will find a solution.
@@Aris_28 joined (jett the jester) i think I know the issue though, possibly moved a file, going to try and find it
What do u thing about brushnet?
It's helpful
how did you get left sidebar? what's node is that?
This is Pinokio that is not a node. Watch my first video and you'll understand what it's for.
Tried to join the Discord group, inside the own Discord, but I couldn't. Error, link expired. I'd like to join :/
Did you try the link in the description? For me it is working.
thank you
I enjoyed the good video
I will support you
Thank you❤️
Man this was amazing liked the VID. However, i have one request PLEASE! Maybe you can be of help. I always used to use 2 models in Fooocus:
1) Juggernaut XL for Fantasy compositions
2) Realism Engine SDXL for in-painting the faces (ONLY the faces)
and it works wonders. I'm very new to Comfy UI but judging from what you are doing and your previous videos, this workflow should not be an issue to replicate in Comfy UI right?
Any chance at all you could give some pointers, I'll try to send you that well deserved coffee money soon as I have my payday my guy!
Thank you for your support! I'll be posting several videos soon that will help you replicate and enhance your workplace from Fooocus in comfyui. Feel free to join my Discord if you need assistance or want to discuss any challenges you're facing. I'm here to help. Have a great day!