👀

I respect people who have the attention span to carve out a niche and perfect it.

In the span of a year I’ve done “Pixar”, anime, cartoon, face swaps, VFX shots, object removal, 3D texturing renders, live action character replacement, in betweens…. Why am I like this 🫠

Anyone else ever just get hyper focused on this stuff and forget to eat? 😅

Viggle had 58,000 members in their Discord before my Joker video

They have 2,500,000 now.

Keep that in mind when you DM me asking for promo and gauge accordingly....

New idea proposed by a colleague

Getting closer but still some jitter to stabilize… I think I have a path forward though. This is overkill but the general idea seems to work.

Would have to do some manually masking of the teeth too as they got lost

Fun

New idea proposed by a colleague

Getting closer but still some jitter to stabilize… I think I have a path forward though. This is overkill but the general idea seems to work.

Would have to do some manually masking of the teeth too as they got lost

Fun

Proved to be a lot more difficult in the end.

Things to improve on:
1) Specular highlights. Skin not shiny enough
2) The 'emotion' is hard to transfer

Still decent for ComfyUI only and would be near perfect for more forgiving shots. This is a punishing close up.

My pixel experiments seem to have garnered next to zero engagement 😂

I guess I just need to start putting Shrek into more movies I guess… 6.5M views and counting on that one

This is something I’ve never shared before!

Had the opportunity to collaborate with Corridor Crew to develop VFX with AI to present at an annual event hosted by the HPA (Hollywood Press Association) as a demo

Very fun project 🤍

I’ll share another clip from this tomorrow

'Hi I'm A.I.Warper and I make silly videos...'

Deepfake.exe loading

🔊 SOUND ON 🔊

It’s been about a year since I played with Pixelart and the tools have significantly improved.

Stylized with ComfyUI and composited (text boxes) in After Effects

If you enjoy this content please consider sharing and following 💙

Think I can get Deep Face Labs results with just using ComfyUI (preliminary tests for a Client - can’t share)

I’ll experiment with something I can share later but very promising stuff for exponentially faster deep fakes.