The problem with germans they’re too smart, and consider complicated programming and coding something easy, and everyone can do it.

This is super cool. Depth and Height are oddly still red for me. Anyone else?

amazing vid, i have one little issue, where do i get and put the upscale model at? it seems i am missing this ? edit: nvm i seen the file name so i just google it and found the upscale model and everything runs good.

Followed every step and made it work for canny and depth and made a cool video, but when I added a mask it will not populate it in the mask preview (although in image preview does show the mask) and I'm quite sure I got the right Hex code (#ffff00 by the way). Anyone having the same result?)

Stunning content !

GREAT TUT!

"download for free on my P*tre*n". LOL. Good video though!

This is amazing

Awesome

THIS IS WHAT I'VE BEEN LOOKING FOR! THANKS A LOT!!!!!

Theft is theft.

Stupid, characters are generated completely differently, neural networks are extremely primitive today.

I tried to do it in COMFY and I just couldn't... is there a way to develop it directly in Midjourney?

If anyone is able to get this workflow to work lmk. Willing to commission some work with it

Super complicated for someone with no coding or IT experience. Could not figure out how to run the manager as there is no run feature after getting it from github. After seeing the rest of the instructions, I know now I do not have the level of proficiency to do this tutorial. Any resources for learning this kind of thing?

So we dumbed art down to prompts. Ok

I'm getting this error... When loading the graph, the following node types were not found: - Integer Nodes that have failed to load will show as red on the graph. All missing nodes were installed, and I can't find any nodes to instal that might be that one. Not sure how to describe but it is the node for width and height... Any ideas?

great work !

Absolutely disgusting that everyone can do this now.

I'm searching for something that correct the lipsinc of a real video, would be very useful in music video

Excelent! Congratulations ❤

i am geting this error in colab ERROR: Could not find a version that satisfies the requirement mediapipe==0.8.11 (from versions: 0.9.1.0, 0.9.2.1, 0.9.3.0, 0.10.0, 0.10.1, 0.10.2, 0.10.3, 0.10.5, 0.10.7, 0.10.8, 0.10.9, 0.10.10, 0.10.11, 0.10.13, 0.10.14) ERROR: No matching distribution found for mediapipe==0.8.11

Thank you for the great tutorial! I'm trying this tutorial, but I keep getting the Ksamper error. Has anyone encountered the same error? I'm using the 'flat2DAnimerge' model. - Error occurred when executing KSampler: 'ModuleList' object has no attribute '1'

Hey man, thanks for this incredible content, I'd love that so much, with my computer I can't handle with this much, my GPU is a GTX 1660Ti, 16GB ram, and I5 7th gen, but I bought a new PC with a RTX 4070 Super, how is the configuration of you PC? and, this workflow still work?

Oh boy this is an amazing workflow ! Thank you so much for sharing !

Killer Workflow maaaan , thanks!!!

This is awesome! you´re the man! Keep up the fantastic work you are doing.

Amazing!! How to learn!?!?!?!!!

Which gpu are you using for this

that's awesome! I've just finished a personal project which this would have been so helpful and I wouldn't have to generate literaly thousands images and compose everithing with photoshop and hour and hours of inpaint and outpaint. I'm looking foward to use it in a new project. Could you show us now how to make it with multiple characters?

Great Job and Images. THX 😻 You sad this is future of rendering. You have 100% right. I play with comfyUI Addon in blender. This is amazing and It's so powerfull tool and realy "dangerous" for Us...🤯

I don’t think the end results are good enough to use yet, too wobbly etc. However I can see a current use where you try different style permutations and then feed back to creating the result in 3D. Until the animation is stable this is a very interesting gimmick. I can’t wait to actually try it myself.

You are insane, more one sub

Hallo, Nick Mumpitz. Ich höre und vermute, dass du Deutscher bist, deswegen verzichte ich mal darauf, Englisch zu schreiben. Ich finde es toll, was jetzt bald mit AI und 3D Rendering möglich sein wird und wünsche dir viel Erfolg!

Error occurred when executing IPAdapterUnifiedLoader: ClipVision model not found. 😭

as an artist i have to admit this is impressive and if this helps me create stories so be it. i'll still do art but this will speed up the pipline

this is next level

Thanks fo this greate tutorial!!! in the second workdlow theese two nodes, CannyEdgePreprocessor DepthAnythingPreprocessor because the ComfyUI Nodes for Inference.Core conficts with lots of elements. trie to install manually alnso bu still nothing. any solution so that we can follow ?

if ai could texture the real world live, for ar glasses... ai could just replace all real world surface textures :) make it look like we are walking in a tron movie or a matrix movie

I am no longer wanted to learn AI, I just want cheese!!

Man, you are simply God! A year ago I tried to do the same thing in A1111, and it didn’t work. What you created is a masterpiece. Thank you!

No way I use this in my life. BUT I am so happy someone did, This is directly a Subscribe after watching this ' oh do you remember how someone did it before Sora' video

Thank you! I've been trying to figure out a good workflow for this for some time now. Well done.

You don't have enough subscribers, bro, but it's coming.

Impressive!!! Thanks! Subscribed

Compared to regular rendering tools, how long did it take?

Very smart workflow! Human in charge of the AI. Thank you!

This is very cool. Can you do also this for a very realistic person, please?

very, very cool

the problem is it's still based on appearance and thus ends up with inconsistencies. What would be useful without discrediting animators and artists is an ai render tool that is strictly simulation. All the light, texture, and physics would be calculated rapidly--still using NVIDIA graphics cards, but with an efficiency otherwise only possible with a render farm