AI Projection Mapping Tutorial

Подписаться 1,8 тыс.

Просмотров 11 тыс.

50% 1

Learn an easy way of creating content for projection mapping with AI and how to map it on an object with TouchDesigner. This method is beginner friendly, quick and gets you impressive results.
Have fun experimenting!
PromeAI: www.promeai.pro/?vsource=i_8f...
For more content check out my Patreon / reflekkt and Instagram / reflekkt_
0:00 Intro & overview
0:45 Projector setup
1:25 Source photo of to be mapped object
1:45 AI content generation
3:38 Creating a mask
4:32 Preparing content 1 & mapping in TouchDesigner
6:46 Preparing comntent 2
8:00 Stoner tool mapping in TouchDesigner
8:32 Projection mapping result
9:05 Review & outro

Опубликовано:

1 июл 2024

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист

Посмотреть позже

Комментарии : 29

@evadermusic 3 дня назад

This is an amazing tutorial man, thankyou so much.

@TheClumsyAcrobat 2 месяца назад

This is an awesome concept and good for quick projects Please continue sharing projection mapping tutorials!

@arnonymous7211 4 месяца назад

This is awesome! Many thanks for making this video. Really appreciated and provides me with tons of creative input. Kudos!

@joshuabrost9431 4 месяца назад

This is exactly what I was looking for! Thank you so much!!

@freivonstil 6 месяцев назад

clean and simple - thanks for sharing!

@markus_knoedel 6 месяцев назад

so relaxed and so cool. thanks.

@hablalabiblia 6 месяцев назад

Nicely done. Clean.

@ithamardimarco9082 6 месяцев назад

Great tutorial! Thanks!!!

@user-ot9is2pw7l 5 месяцев назад

Thank you for this super video! Wanna try to do something like this.

@user-vb3hz8dr8t 6 месяцев назад

Amazing and accurate thank you

@neokortexproductions3311 Месяц назад

Thank you!

@Nono-cd7wg 4 месяца назад

wooow! Really great tutorial

@julianhaidbaner1634 6 месяцев назад

Thanks you so much 4 share

@CallMehBrite 5 месяцев назад

super underrated channel!!

@reflekkt_net 5 месяцев назад

Thank you, I appreciate your words! It's the little things like this that pushes my motivation to work on more videos 🙂

@victorcerda4862 5 месяцев назад

please more videos!!! thank you very much!

@reflekkt_net 5 месяцев назад

Thank you! Next tutorial is already in progress 🙂

@helloteko 6 месяцев назад

Thanks!

@prinnycupcakes4992 5 месяцев назад

awesome \m/

@user-nw1kp6oo9g 4 месяца назад

👍👍👍

@pizzakarton468 4 месяца назад

hey, i am a long-term videomapper and it's cool to see how you implement AI into mapping in a very hands-on approach. in my opionen the 'creative fusion' of prome-ai is the key, bc it respets the givin' proportions of the image, which you need for using it in mapping. so far I haven't figured out a way to use stable diffion (or similiar) to work in similar ways. have you?

@reflekkt_net 4 месяца назад

Thank you! I tried some workflows with Stable Diffusion and ControlNets, but couldn't get high quality results like with PromeAI yet. Right now I'm doing a lot of research tho for a video to video workflow in SD and am getting closer to what I want. Might do a tutorial in future if I figure it out properly!👍

@osamajamil4804 4 месяца назад

thats great. How can we connect this to depth camera so the projection changes with human motion?

@reflekkt_net 3 месяца назад

Thank you! You could for example use data from a depth camera to drive the switch, so the images projected changes depending on the distance of persons. Or composite the projection with a noiseTOP, which is connected to depth data that drives the transform parameter of the noise or something like that. You can literally use external data on almost every operator by referencing the value of your incoming data to a parameter of the network, almost no limits there :-)

@brandonjoffe Месяц назад

What projector are you using?

@reflekkt_net Месяц назад

It's a NEC ME372W with a NP47LP lamp. I got it used from ebay for ~300$. It is not FullHD, but for hobby stuff or smaller parties it is really good, as it has a brightness of 3700lumen.

@Septin1983 6 месяцев назад

ich wette dass man das mit comfyui mit weniger aufwand hinbekommt. mein ansatz wäre zb. das pikachu bild ins comfyui laden dort erstellt controlnet die maske die du dann auch automatisch speichern lassen kannst und an hand der maske erstellt comfyui im selben atemzug die bilder bzw kannst du auch gleich ein video draus machen lassen somit musst du dann in touch designer nur das vieo laden anstelle der einzelnen bilder.

@reflekkt_net 5 месяцев назад

Das ist eine Möglichkeit mit der ich mich auf jeden Fall mehr auseinander setzen möchte, sodass externe Tools wie PromeAI evtl garnicht mehr nötig sind. Wäre nice alles komplett in TD erstellen zu können.

@Septin1983 5 месяцев назад

externe tools sind in manchen fällen nicht verkehrt zb hab kann man comfyui mit krita oder protoshop verbinden und wenn man ein bild malt wird mit comfyui aus deinem gemalten in realtime ein bild generiert oder du verbindest eine webcam mt comfyui wo dann über die helleren und dunkleren bereiche des webcam bildes die bilder in comfyui beeinflusst werden wie zb posen von personen oder so @@reflekkt_net