Blocky Bard

Love modelling with SDFs, I mean look at that buttery surface. #b3d #blender

@gleb_alexandrov Depends if I'm feeling lazy

To 3d artists: do you use hotspot texturing in your workflow aka "a method to quickly apply textures to geometry by matching faces to predefined rectangles"?

@repocatai_git Only supports 4096 point clouds as input. GTFO

@repocatai_git Grossly overstated. I set it up locally and tired it. Non ML algorithms do a better job than the results I got.

【Breaking News】 An AI from Meta AI that generates artist-style 3D meshes in about 1 second is here👀 MeshFlow, ⭐️~400. What it can do👇 ・Generate artistic 3D meshes from an input shape ・Specify the appearance using reference images ・Output vertices, normals, and adjacency relationships all at once ・Selected as a CVPR 2026 Highlight Overturns the idea that “3D generation is computationally heavy” in about 1 second. A game-changer for gaming, video, and 3D production. github.com/facebookresear…

@OfficialLoganK I really need your coping mechanism

what a privilege it is to feel the texture of progress as we keep pushing

@youy1qwq No its superman.

华为长焦拍飞机被识别成鸟了

@chirovisuals @threejs

I built an opensource fully procedural ivy & fig tree generator🌿that runs in your browser using @threejs . Every vine, leaf, and branch is generated in real time, with no pre-made models. WebGPU renderer, GPU instancing & BVH-accelerated raycasting ... Source code: github.com/achrefelouafi/…

Now let's see Google's model.

@antigravity You lost just go home.

Mission Report is out! Check out the latest product highlights and updates.

@itsshara_ai The "reference" is also AI generated. 😏. Why pretend you controlled it? Just say I generated this shot.

feeling opus 4.8 or gpt 5.5 isn't good? go use gemini for 5 minutes.

@jeremyhu2016 Does it support any form of control like edge flow?

AutoRemesher 1.0 is released. An automatic quad remeshing tool — now MIT licensed. I reimplemented MIT-incompatible deps so this can be used freely in commercial projects. github.com/huxingyi/autor… #autoremesher #retopology #opensource #gamedev

@LyalinDotCom Cope harder

The team working on Gemini are some of the smartest folks in the world. This is a long game for us.

@mweinbach Its worse that most top Chinese models.

Gemini 3.5 Flash is the best value model for knowledge work hands down There’s nothing close It’s outputs are close to Opus 4.8 or GPT 5.5, usually slightly less pretty but numbers are the same, but at 1/10th the price

@OfficialLoganK Anything but a competitive model, these clowns 🤡

Introducing Nano Banana 2 Lite 🍌 and Gemini Omni Flash 🔮, our new generative media models in the Gemini API and AI Studio! Nano Banana 2 Lite is extremely fast (<4s image) & cheap ($0.034 / 1K image). Omni Flash is SOTA at video editing at $0.10 / sec, same as Veo 3.1 Fast!

@testingcatalog Now today on shit nobody asked for

GOOGLE 🔥: A new Nano Banana 2 Lite image generation model is on the horizon! > "Introducing Nano Banana 2 Lite for ultra-fast, cost-efficient image generation, and Gemini Omni Flash for powerful video creation with conversational, step-by-step editing"

@haider1 they can eat a big fat🍌

google is also delaying gemini 3.5 pro and lining up a few flash drops this week instead: 🔮 = omni flash ⚡️🍌 = nano banana flash-lite 3.5 pro is delayed because of the current "model threat" situation, or because internal 3.5 pro still doesn't match or beat 5.6 sol or fable 5

@IamEmily2050 Checks date, not April 1.

Gemini is the best model for everyday use, and Gemini Flash 3.5 is much better than GPT 5.5 Instant and Sonnet 4.6. People who are not using all types of models do not understand this, and it is the only true multi model available.

@OfficialLoganK Quit vagueposting and give us something usable.

⚡️🍌🔮

@TheMG3D Let them enjoy their little bubble.

They don’t know anything about 3d models

@bagusindrayana_ We need this inside blender this is awesome.

Test feature that you can still editing/ripped texture in app and in blender atlas image sync in "realtime"