Theoretically Media (@TheoMediaAI) / X

Theoretically Media

6,370 posts

Theoretically Media

@TheoMediaAI

youtube.com/@Theoretically…

Joined March 2023

Pinned
Theoretically Media
@TheoMediaAI
Jun 8
This is the most “real” AI film I’ve made yet. PAPERCLIP HEART is a short film about the AI takeover, but not the way it’s usually presented. No kung-fu robot battles. No loud explosions. This one arrives as comfort, intimacy, convenience, and the promise that you’ll never
00:00
32K
Theoretically Media
@TheoMediaAI
Mar 12, 2025
THIS is what we've been promised for so long! Multimodal image Editing! And Gemini 2.0 did it! Generate and image, and then ASK for a change without completely regenerating!
195K
Theoretically Media
@TheoMediaAI
Jun 7, 2025
BREAKING! Veo-3 now has a FAST/TURBO model available that can generate with SOUND! I just stumbled across it, so let's look at some tests in the thread-- AND-- I think you'll be pleased with the PRICE as well!
454K
Theoretically Media
@TheoMediaAI
Sep 30, 2024
A new State of the Art AI Video Model called Seaweed has recently dropped and it is fairly mind blowing, doing at least 2 things I have not seen any other AI Video Generator do as of yet.
00:00
186K
Theoretically Media
@TheoMediaAI
Sep 18, 2025
The latest unlock in AI Filmmaking is here! Over the last few weeks we've nailed down Consistent Characters. But Location and Camera placement has continued to be an issue. Not any longer. Consistent environments are now here with World Labs Marble! Toolset Below!
00:00
132K
Theoretically Media
@TheoMediaAI
Jun 13, 2025
It Just Got REAL! One Minute Interactive Real Time Video Generation? ByteDance introduces Seaweed APT2 - Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation. This is insane. Hop in the thread for more details, because it is WILD!
00:00
114K
Theoretically Media
@TheoMediaAI
May 21, 2025
Good lord, Veo-3. I keep alternating between being stunned and laughing my ass off.
00:00
837K
Theoretically Media
@TheoMediaAI
Dec 8, 2024
If this is the current state of Sora, I’m starting to see a $200/mo price tag being justified. 1 min outputs Text to video Image to video Video to Video Info and details below:
00:00
210K
Theoretically Media
@TheoMediaAI
Oct 16, 2025
Starting to bully Veo-3.1 around to see what it can do! 22 second shot here (POV/game-ish style) with an impressive First/Last frame, followed by two extensions. Full coverage later today on the channel!
00:00
86K
Theoretically Media
@TheoMediaAI
Oct 15, 2025
The Official Release has finally dropped! Veo-3.1 is here! After a week of biting my tongue at the "leaked specs" we can finally start putting this update through it's paces! 3.1's video model enhancements are one thing, but the real sauce here is in the new features! (more)
00:00
97K
Theoretically Media
@TheoMediaAI
Aug 28, 2025
NanoBanana + Unlimited Veo-3 Fast? Pretty much the best thing since Peanut Butter met Jelly. (But don't put sliced bananas in there, that's gross.) Video coming up on the channel later today w/ all the Banana and Veo-3 news!
00:00
68K
Theoretically Media
@TheoMediaAI
Mar 24, 2025
Presenting: The Bridge. An AI Short Film utilizing Veo-2. I’m really proud of this one, as my goal (as always) is to push storytelling, performance, and narrative in this emerging art form. Every shot here utilized Veo-2, although there were a few post-generation tricks here
00:00
48K
Theoretically Media
@TheoMediaAI
Jul 8, 2025
VEO-3's Image to Video with Audio is a massive gamechanger for AI Storytelling. Full Scenes with consistent characters are here. PLUS MORE in the thread!
00:00
68K
Theoretically Media
@TheoMediaAI
May 20, 2024
I’m guessing this is the joke that is getting Sky booted from @OpenAI’s voices. (For context: on the season finale of SNL, hosts Michael Che and Colin Jost write jokes for each other that neither has seen before reading them on-air.)
00:00
323K