pixco

1.4K posts

pixco banner
pixco

pixco

@CoresPix

3D Artist, Open Source Enthusiast Amateur Game Dev Atheist and science lover. ✌️ (No politics, Just vibes)

🌏 Katılım Ekim 2021
74 Takip Edilen88 Takipçiler
pixco retweetledi
goku 🍃
goku 🍃@AshSatoshi4ever·
the way this doraemon movie shifted the tone from a standard gadget adventure to a high stakes sci-fi war drama blows me away every single time. the animation was so smooth holy shit.
English
28
228
1.7K
38.3K
pixco retweetledi
DillonGoo Studios
DillonGoo Studios@dillongoostudio·
ANIME PHYSICS IN BLENDER After years of R&D, we're finally releasing our custom-built physics solution for Blender! Introducing: Goo Physics Goo Physics brings bouncy, floppy, and gooey stylized bone simulation to your rigs with a single click of a button. Available now at ➡️ dillongoostudios.com/add-ons
English
140
4.7K
41.9K
1.8M
pixco retweetledi
lovedarksoul
lovedarksoul@lovedarksoul·
When animators forgot their budget
English
60
2.6K
47.5K
1.1M
pixco retweetledi
Booster 10
Booster 10@booster_10·
Still wild to me that Stoke's first Zenith engine was made by a team of less than 10 people in under one and a half years.
English
29
189
2K
115.5K
pixco
pixco@CoresPix·
One of the best ways to shut up these space-denier losers is to make space travel so easy and frequent that these losers have to delete their socials because their socials will be filled with people enjoying space.
English
0
0
0
6
pixco retweetledi
ゆとりCG
ゆとりCG@yutorikoubo·
Blender5.1以降に出たレイキャストノードで、なんとなくわかってきたことをメモ! ・異なるオブジェクト同士が重なっても、輪郭を自動で形成してくれる。これが画期的かもしれない。 ・カメラ視点に追従するエッジ検出ができる。どのアングルから見ても輪郭線が崩れず、アニメーションにも自動で対応する。これも凄いかもしれない。 ・3種のエッジを独立して制御できる。シワ・ハードエッジ・シルエット輪郭線をそれぞれ別の太さや色にカスタマイズできる。輪郭のカスタマイズ性が高そう。 ・カメラとの距離に応じてエッジの見え方を自動補正できる。遠くでもエッジが消えず、近すぎても太くなりすぎないよう自動で調整される。従来のソリッド化を使った輪郭線によりも美しい!! ・エッジ情報を使って、ベースのシェーディングそのものを制御できる。ディフューズBSDFのカラーに繋ぐかどうかで、スケッチ風かハードコントラスト風かを切り替えられる。影の色をすぐにコントロールできそう。 ・既存のAOやディフューズ BSDFと組み合わせることで、カスタムNPRシェーダーの質が上がる。 結論、NPR表現を非常に高めるツールでありそうという感じです!! まだまだ理解が追いつきませんが、色々試してみようと思います。 #blender #b3d
ゆとりCG@yutorikoubo

Blender5.1 シェーダーノードのレイキャストを理解するには、忍耐力が要りそうです。 NPR表現の輪郭、影の落ち方には使える。頑張る。 #blender #b3d

日本語
4
201
1.6K
115.5K
pixco
pixco@CoresPix·
@ashlee3dee This is new to me. Is this in 5.2 Beta?
English
0
0
0
54
pixco
pixco@CoresPix·
Many tech-illiterate people simply cry CGI. They have no idea it is nearly impossible to fake that perfect interaction with humans. If you make the whole thing CGI, it will be easily detectable because CGI humans still look weird.
English
0
0
0
10
pixco
pixco@CoresPix·
Many people have exposed themselves as complete smooth brains. They are having complete meltdowns and screaming their age old excuse that it is fake and CGI.
English
1
0
0
13
pixco
pixco@CoresPix·
Vibrance Filter: This has been missing from GIMP for a long time, and it is finally native. It boosts color exactly where it is needed, preventing skin tones and already saturated areas from blowing out.
pixco tweet media
English
0
0
0
159
pixco
pixco@CoresPix·
Vector Layers: GIMP finally has support for non-destructive shapes. Right now, this acts as a highly effective way to create and edit clean graphics without rasterizing them. This lays the necessary groundwork for full, dedicated shape tools.
English
1
0
1
19
pixco retweetledi
the tiny corp
the tiny corp@__tinygrad__·
TIL that Linux isn't free cause I had to buy the computer to run it 😭 This is the biggest load of cope I have ever heard. I hope Opus gets smoked by DeepSeek v4 and the only people who continue to use closed source models are Windows users.
Dustin@r0ck3t23

Dario Amodei just dismantled the biggest myth in the AI industry. Open source AI isn’t free. It never was. Amodei: “It’s not free. You have to run it on inference and someone has to make it fast on inference.” For decades, open source meant something real. It meant a teenager in a basement could download the same tools as a Fortune 500 company. Could read the code. Could modify it. Could build something that competed with the giants. That was genuine democratization. That actually happened. AI is different. Fundamentally. Physically. In ways the ideology hasn’t caught up to yet. Downloading the weights is the easy part. The part that actually costs something is turning the weights into a running system. Into responses. Into intelligence operating in real time at scale. That requires compute. Power. Infrastructure. The kind measured in billions of dollars and years of construction. Amodei: “These are big models. They’re hard to do inference on. Ultimately you have to host it on the cloud. The people who host it on the cloud do inference.” The open source debate was never about who owns the model. It was always about who owns the cloud. And Amodei goes further. When a competitor drops a new open model, he doesn’t ask whether it’s open or closed. He doesn’t care about the licensing. He doesn’t engage the ideology. Amodei: “I don’t think it mattered that DeepSeek is open source. I think I ask, is it a good model? Is it better than us at the things that matter? That’s the only thing that I care about.” That’s the ruthless clarity of someone actually trying to win. While the media debates licensing frameworks, Amodei is asking one question. Is it better. Everything else is a distraction. Amodei: “I don’t think open source works the same way in AI that it has worked in other areas. Here we can’t see inside the model.” This isn’t Linux. You can’t read it. You can’t fork it. You can’t understand it the way generations of developers understood the tools they inherited. You can download it. And then you need a data center to run it. The teenager in the basement who was supposed to be empowered by this revolution needs a billion dollars of infrastructure before the empowerment starts. The era of the basement coder rewriting civilization on a laptop is over. The future belongs to whoever commands the compute, owns the power grid, and can actually turn the intelligence on. Open weights without infrastructure isn’t democratization. It’s a promise the physics of the universe won’t let us keep.

English
90
232
3.9K
177.4K
pixco
pixco@CoresPix·
A cheap, moderately useful model runs even on mediocre PCs, you don't need to build supercomputers for that. Even though many people specifically build monster PCs with lots of RAM for running models, many have optimized things for inferencing them.
English
0
0
1
14
pixco
pixco@CoresPix·
Big companies being scared of open source and lobbying against it is a very old tale. Power concentration is more problematic and probable than all the world ending delusions you may have.
Dustin@r0ck3t23

Dario Amodei just dismantled the biggest myth in the AI industry. Open source AI isn’t free. It never was. Amodei: “It’s not free. You have to run it on inference and someone has to make it fast on inference.” For decades, open source meant something real. It meant a teenager in a basement could download the same tools as a Fortune 500 company. Could read the code. Could modify it. Could build something that competed with the giants. That was genuine democratization. That actually happened. AI is different. Fundamentally. Physically. In ways the ideology hasn’t caught up to yet. Downloading the weights is the easy part. The part that actually costs something is turning the weights into a running system. Into responses. Into intelligence operating in real time at scale. That requires compute. Power. Infrastructure. The kind measured in billions of dollars and years of construction. Amodei: “These are big models. They’re hard to do inference on. Ultimately you have to host it on the cloud. The people who host it on the cloud do inference.” The open source debate was never about who owns the model. It was always about who owns the cloud. And Amodei goes further. When a competitor drops a new open model, he doesn’t ask whether it’s open or closed. He doesn’t care about the licensing. He doesn’t engage the ideology. Amodei: “I don’t think it mattered that DeepSeek is open source. I think I ask, is it a good model? Is it better than us at the things that matter? That’s the only thing that I care about.” That’s the ruthless clarity of someone actually trying to win. While the media debates licensing frameworks, Amodei is asking one question. Is it better. Everything else is a distraction. Amodei: “I don’t think open source works the same way in AI that it has worked in other areas. Here we can’t see inside the model.” This isn’t Linux. You can’t read it. You can’t fork it. You can’t understand it the way generations of developers understood the tools they inherited. You can download it. And then you need a data center to run it. The teenager in the basement who was supposed to be empowered by this revolution needs a billion dollars of infrastructure before the empowerment starts. The era of the basement coder rewriting civilization on a laptop is over. The future belongs to whoever commands the compute, owns the power grid, and can actually turn the intelligence on. Open weights without infrastructure isn’t democratization. It’s a promise the physics of the universe won’t let us keep.

English
1
0
1
25