H.art.code

𝕳.𝖆𝖗𝖙.𝖈𝖔𝖉𝖊 | Ḩ̵͐̓͑̒͌͘.̶̛͕̳̩͎̹̙̈͆̒͘a̴̛͈̤̻̲̝̥̻͒͂r̶̢̼̩̭̙͍̙̣̣̈́̐t̶̮͕͖́͝͝.̶̝̘̲̩̆̒͛̈́͌́̕͘ĉ̷͍͒̈̀̄̕̕͝ó̷̺͋́̚d̵̨̀̎̿̇̀̇̋̾͜e̴̠̼̼̙͎̝͌̾͗̀͗ | art | web disgn | mag |

[Matt Shumer @mattshumer_]

The more I use it, the more I feel like Veo 3 is a realllyyyyy big model

The knowledge it can embed in videos is insane

For example, here, it gets the basic recipe for a vodka pasta right (minus the vodka)

[Cyrus @cyrusnewday]

Wow #Veo3 is crazy, I can’t believe it did this with just a single prompt:

“Japanese fashion 80s Tokyo cutscenes retro montage”

[Tim Soret @timsoret]

2 years apart.
Again, don't look at the finger when it is pointing at the moon.

Many mocked the early results, but it was already profound to witness a machine clumsily hallucinate from its learning. To me, it felt like mocking a child's drawing.

[ex_mortal_ @ex_mortal_]

_MEMOREX DREAMS
_
_Thank you @halving_fun + @Vince_Van_Dough for multiple collects / offers in the HOT ELECTRONIX
collection!!

[philz1337x @philz1337x]

✨ I increased the max resolution for my open-source upscaler to 20,000 x 20,000 pixels (or 400 megapixels) 🤯

This makes it by far the highest resolution AI upscaler available

It takes 26 minutes to run on an A100 GPU 80GB and produces a 100MB JPG file 😱

The higher upscale resolution is possible because I am running a second replicate model now which runs on a larger GPU with 80GB VRAM

I would like to increase the resolution even higher but it runs out of VRAM for higher resolutions which I might be able to fix by changing the tiling settings

🛠️ My code is open-source, and I also host a very easy-to-use version on my website Clarity AI, where users can upscale anything between 2 and 20,000 pixels now

[Guandanarian @Guandanarian]

Treachery

[Krea @krea_ai]

Imagen 4 is now available on Krea.

Veo 3 coming soon :)

check it out!

[Cayde.wav @caydeplanet]

I made an oil painting of Terminal from Modern Warfare 2

[VideoArtGame @VideoArtGame]

Pixel art | Super Metroid

Artist: @BryanHeemskerk

[ぽんず | AI映像 @ponzponz15]

Runway Gen-4

プロンプトはカメラワークから書くのがいいそうです

tracking shot from behind as a person sprints at high speed through a dark forest, branches whipping past, then suddenly slows into emotional slow motion as they reunite with a long-lost parent, embracing tightly under moonlight, cinematic drama

[doron ˗ˏˋ ´ˎ˗ @doronstudio]

combining circuit + bayer algorithms

[PJ Ace @PJaccetturo]

WOW. This may be the most gorgeous AI film I've seen so far.

Pro filmmakers are rapidly learning the tools, and we're about to see a MASSIVE shift in the entertainment industry.

2025 will be the year AI films stop looking like “AI” and start looking great.

[Nathie @ AWE @NathieVR]

This guy straight up altered his reality using a Quest.

[Krea @krea_ai]

previewing Stage.

this new tool lets you create entire 3D scenes with AI and get consistent snapshots of it.

more soon!

[Krea @krea_ai]

previewing Krea Stage.

this new tool lets you create entire 3D scenes with AI and get consistent snapshots of it.

more soon!

[Brute Force @BruteForceGame]

I made a free game in 72 hours
#ludumdare #indiegame

[Strano @5tr4n0]

rolling and coasting

[H.art.code @hartcode]

@80Level @gorsvie So cool !

[Michelle Lu @michlu2]

.@annnnhe and I won the @agihouse_org ai x commerce hackathon on saturday! we built taste space: a 3d representation of 1500 clothing items that, through rating, you can place yourself in.

built with CLIP, UMAP, synthetic labeling, react three fiber, and more. thread 👇