Загрузка видео...

Не удалось загрузить видео

На главную

FORGET MY PREVIOUS POST, LET ME BLOW YOUR MINDS! 🤯NEW METHOD! AI 2D SPRITES ARE SOLVED. PERIOD. Day 50 of building a webGL game engine using Cursor 🔽🔽🔽 I was wrong. The previous system had flaws. It wasn't the best. If you use it on VFX heavy sprites, it...

71,180 просмотров • 5 месяцев назад •via X (Twitter)

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

I MADE THE BEST 2D SPRITE AI PIPELINE EVER! After testing so much, doing tons of math, trying various different methods I finally got truly the cleanest sprite result I could ask for! You should bookmark this post! ✅ I think this is the happiest 'aha' moment I've had since starting this journey. Day 48 of making a custom webGL game engine using Cursor 🔽🔽🔽 I've been trying to solve sprites since I started this project. I came close a couple of times but it was always something - either dynamic lights wouldn't work, or the genAI results would make them grainy, or I would have to have incorrect alpha etc. After so much struggling, wanting to give up, thinking it's impossible - it was finally done! Perfect matte interpolation of black & white backgrounds resulting in a clean outline of the sprite, half transparent effects keeping their full quality. But this was not enough for me. I wanted more. I wanted those dynamic lights for the most badass anime effects that I'll be creating for the next many weeks! And somehow, I managed to come up with the perfect balance that is nice to the eye with almost no visible imperfections or artifacts when using any kind of dynamic lights. See for yourself! 🔽🔽🔽 How does this magic happen? 1⃣ First, the animation is created using Kling AI. I found it the best to keep the quality anime 2D style I wanted, but I guess others may work as well. 2⃣ Then, the frames are carefully extracted at lossless quality and processed via automation through Nano Banana pass to create an opposite background (white->black or black->white). 3⃣ Once we have a proper spritesheet, I then used MiDaS to compute the depth maps, and then algorithmically create PBR maps for lighting. The remaining depth maps can also be used for various effects, although haven't explored it much yet. 4⃣ Finally, all elements are cut into single frames and overlapped with their respective normal maps. If done right, they're pretty much ready for runtime. I like my heroes to be 512 to truly stand out like fighting game characters, but all of this works with far smaller or bigger sprites. Mind you, it's important to note that Nano Banana has a max output of 4k. Therefore you don't want to make your atlases larger than 4k - which is still quite a lot since it allows you 8x8 512 frames. 💡💡💡 I believe the output quality is beyond anything currently available, and I'll be looking into packaging the whole thing into a web app so people can use it. If you find this useful, please repost it! I really wanted to share this method to the world. Thank you for reading! Look forward to day 49 update!

Startracker 🔺

145,925 просмотров • 5 месяцев назад

I vibe coded and built a sprite animation pipeline 🛠️ (Day 22 of making the engine+game) ⬇️ Watch the video if you don't wanna read the wall of text - it directly shows what I do. Shoutout to Jidé ✨ for showing me a paper on black/white combination to get alpha, it's the cleanest method yet, and to Cursor for enabling this entire journey. If you prefer the wall of text here you go: The hardest part of using general image models for 2D sprites isn’t getting a nice-looking frame, it’s getting consistent motion across a whole sprite sheet. You can fake a sheet, but frames won’t align, timing drifts, and you end up with weird artifacts. Even if you manually cut frames + interpolate, the animation often looks “off” because each frame is basically a new interpretation, not the same character evolving over time. This is especially noticeable with public API models like gpt-image-1.5 and Nano Banana. Some custom LoRAs for open models exist, but this is intended for less techy folks. My workaround: use a video model first, then post-process into a sprite sheet. Render the animation over a solid background (white/black/magenta/green), then chroma-key it out (my engine tool supports this). If the motion stays inside the silhouette, this works surprisingly well. You can do this in almost any video editing software too! The catch: keying almost always leaves an “aura” (edge spill). My best results come from interpolating the keyed animation with a clean base sprite, so you keep crisp edges and only “borrow” motion/detail where needed. If the animation extends outside the silhouette (tree branches, hair wisps, foliage), I usually skip “true sprite animation” and do it with shaders instead. Keying can’t fully remove halos there, no matter how much feathering/tuning you do. Another annoying issue: pixel corruption. AI rarely generates a perfectly flat background (pure #000000 or #FF00FF). That tiny noise breaks clean extraction and creates crawling garbage pixels around the subject. For clean base sprites (and even PBR maps), a useful trick is generating the same asset on white + black backgrounds and deriving alpha from the difference. This is basically a matte workflow: white = opaque, black = transparent. It fixes aura… but you’d need it per-frame to fix animation, which is still hard. For simple pixel art (single-digit frames), you can sometimes generate a sprite sheet, then ask the model to recreate it on black/white while preserving alignment… but it’s still manual-heavy. Honestly, at this point, for some projects it’s easier to go 3D → 2D and render clean sprites/maps directly. But I still love pushing “pure 2D” and seeing how far we can take it. Thanks for reading! Follow/bookmark/repost if interested in this kind of content!

Startracker 🔺

20,181 просмотров • 6 месяцев назад

How I get shit done, Episode 001 I've set up a playbook called ‘land’, which is triggered automatically when I drag an issue into the merging column in Linear. That reliably runs CI and merges any green PRs. This has allowed me to ship way faster than before. I think the key takeaway here is you can try to build your own code factory and your own agent orchestration layer, but it is a huge amount of work. The truth is there are entire companies with massive funding that are already tackling this and it's just easier to use their platform. I think this is a lot like if you were a carpenter: you could build your own generator, fuel it, wire it up, and then build a plug and then you could plug your saw into it. Or you could just plug your saw into the wall. Because the electricity company has already done all the work in the infrastructure and investment to make that plug work. I think more of us who are building companies should just be plugging into the wall instead of trying to build all this tooling ourselves. As a dev it's so tempting to build your own dev tools but I think a lot of times, even though you can build fast with agents now, it's a complete waste of time. It probably sounds like I'm being paid by Devin or something but I have zero financial interest here. They don't give me credits. I'm not an investor. I'm not being paid. I just think the tooling is really damn good. If you used Devin a long time ago and wrote it off, you really should have another look - for $500/month it's pretty obscene what you can get done.

Ryan Carson

14,059 просмотров • 3 месяцев назад

All these demo videos make HEAD SWAPPING with Nano Banana look so easy, but then you give it a try and you're like... uh... what? Why didn't that work? Here's what I've found. Nano Banana reads your image, almost literally, so if you write on the image, it reads the text. This is how Higgsfield AI 🧩 has capitalized on the tech: "Write on the image" and give it direction, right? Totally true, but you don't need Higgi to write on your image. Nano Banana will understand your direction regardless of where you write on your image. On one hand, Higgi is really smart, because they're hranessing the tech in a unique way, but the whole "Higgsfield's Banana Placement" is a bit of a misnomer. It's more of a "Banana Placement" and Higgi is just giving you a sort of basic Photoshop-type tool to work with (again, pretty smart), but the real tech is the Banana. 🍌 This is how I head swapped heads in Runway, but Nano Banana maintains the aesthetic qualities of your image almost perfectly, whereas Runway Reference spits out a very Gen-4 looking image. I like using Nano in Freepik (now Magnific), mainly because it's fast and I can get 4 gens at a time, and you need to gen a dozen times of so before you get a winner (most of the time). I was pumped when I saw Freepik introduce the @ reference feature, just like Runway has, but it doesn't seem to work for head swapping. My guess is because that's not really how Nano Banana tech works... ideally. Marco is the person I saw using this "A" and "B" method, back when Nano was on LM Arena, and man-oh-man, it just works... like a charm. You need experiment with how much of the face you blot out, and the angle and facial expression of your new head if you want the blend to be perfect. All of the results in this video are 100% Nano Banana. I did not do any Photoshop work to the images after the fact. I really hope this helps. Let me know if you have any questions. I'm happy to help. And I'll keep posting videos like this if you guys find them useful. Let me know! And if you want more serious, one-on-one AI consultation you can throw something on the books here:

Jordan Daniel Chesney

61,803 просмотров • 10 месяцев назад

For months, I've been quietly building a prototype of something just because I want it to exist. Papyrus is a word processor, editor, proofreader, fact-checker, deep researcher, brainstorming partner, all in one. It takes your rough draft and helps you skip three revisions. Now I'm considering pivoting my whole team to build it out, but first, I need your vote. You email is your vote. LINK IN COMMENTS. I don't even care if you use some email you never look at and just use for sign ups. To me one email is one vote and says, go ahead and build this damn thing out and make it awesome. I built it because today's apps are the bloated dial-ups of writing (Word, GDocs). They've got a hundred freaking buttons I don't need and bury the ones I do need. Or they're AI marketing slop toys that promise to read my mind and pump out garbage. They just don't get the real work of writing and they don't get me. I want a clean, focused space with a real AI co-pilot. I don't need it to do the all the writing for me, just like I don't need Claude Code to do all the code for me. I want to work with it. I want a writing partner that acts like a full writing team on-call 24X7: proofreading, fact-checking, and running deep research in the background while I focus on the hard parts. I'm tired of cutting and pasting between a dozen tools so I started writing this thing. But won't the big guys just build something like this? Sure. But it will just bolt your ass into their ecosystem. Google Docs will force Gemini on you. Whatever office suite OpenAI pumps out will only use GPT. I want to use any model. Open or closed. They're commodities. The app is the thing. I want the best tool for the job, GPT-5, Kimi, Qwen, Claude, whatever comes tomorrow. I want a fluid, flexible workspace. I'm building this thing for people who've got critical thinking and who build, who don't want to outsource every damn thing to the machine. So if that's you and you believe this should exist, I really need your vote. Tell me to build it and I'll go all-in and make it a reality. Thanks for giving me a moment of your time.

Daniel Jeffries

20,811 просмотров • 10 месяцев назад

A mental model everyone should know: The Regret Minimization Framework. This is how Jeff Bezos used this model to decide to start Amazon: I went to my boss and told him, "I'm going to go do this crazy thing — I'm going to start this company selling books online." This is something I had already been talking to him about in a more general context, and he said, "Let's go on a walk." So we went on a 2-hour walk in Central Park in New York City. The conclusion of that was, he said, "This actually sounds like a really good idea to me, but it sounds like it would be a better idea for somebody who didn't already have a good job!" He convinced me to think about it for 48 hours before making a final decision. So I went away and was trying to find the right framework to make that kind of big decision. I had already talked to my wife about this, and she was 100 percent supportive, saying, "You can count me in – whatever you want to do." It's true, she had married this guy with a stable career and path, but she was 100 percent supportive. So it was really a decision I had to make for myself. The framework I found, which made the decision incredibly easy, was what I called — only a nerd would call — a regret minimization framework. I wanted to project myself forward to age 80 and say, "I'm looking back on my life, I want to have minimized the number of regrets I have." I knew that when I was 80, I was not going to regret having tried this. I was not going to regret participating in this thing called the Internet that I thought was going to be a really big deal. I knew that if I failed, I wouldn't regret that. But I knew the one thing I might regret is not having ever tried. And I knew that would haunt me every day. When I thought about it that way, it was an incredibly easy decision. If you can project yourself to age 80 and think, "What will I think at that time?" it gets you away from some of the daily pieces of confusion. I left this Wall Street firm in the middle of the year, and when you do that, you walk away from your annual bonus. That's the kind of thing that in the short-term can confuse you, but when you think about the long-term, you can really make good life decisions that you won't regret later. *** Summary Ask yourself: in X years, will I regret not doing this? • If Yes → DO IT! • If No → Don't bother. This can apply to any decision: • Should I switch jobs? • Should I start my dream business? • And more... *** Takeaway: Optimize for Asymmetric Upside • Record content (podcast, video) • Write content (book, blog) • Go to a cocktail party • Move to a big city • Invest in startups • Go on first dates • Build in public • Start a biz • Tweet Shoot. Your. Shot. Life is too short not to do so. *** That's a wrap and I hope you found this helpful. If you found value in this post: 1. Follow me Arjun Mahadevan (Mr. LLC 🇺🇸) for more. 2. Re-post this, if you can, to share this mental model with a friend and to remind them to: Shoot. Your. Shot. Life is too short not to do so.

Arjun Mahadevan (Mr. LLC 🇺🇸)

25,577 просмотров • 2 лет назад

Robert De Niro originally wanted to play Max Cherry in Jackie Brown, the role that eventually went to Robert Forster. However, Quentin Tarantino had written the role with Forster in mind and had already promised him the part. Tarantino explains… “I wrote Jackie Brown, and I decided at some point in writing the script that Robert Forster would be terrific as Max Cherry. So, while I’m still writing the script, I bump into Robert Forster - we go to the same coffee shop. ….so I decided I’m gonna give him the part, because I figure, look, this would be a big, big deal part. So if I don’t give him the part, then once I’m done with it and it gets out in the town, then it’s gonna be Gene Hackman and Paul Newman and people like that, and it would be pretty hard to say no to. But if I just give him the part right now, I’ve got the juice to get it through, and now I can’t take it back because I wouldn’t be a man of my word. So to lock myself into that decision, I give it to him before I finish writing it. And then now comes the time to do it. Robert De Niro reads it, and he wants to be in it, but he wants to play Max. And I go, “Well, look, you would be a fantastic Max, but I’ve already given that to Robert Forster, and I’m a man of my word. I can’t take it back.” Now, De Niro is very much a man of his word, so he understands that. He gets that. And he’s just like, “Yeah, yeah. That’s just disappointing. It’s just regretful.” I go, “What?” “Well, just because, you know, you were thinking about him, so you wrote it for him. But if we had had more dinners and hung out a little bit more, then you would have been thinking about me and you would have written it for me. And I understand what happened, but that could have been changed if we had spent more time with each other before this.” And so he kind of gives me the – “just think about it for a couple of days, all right? - and then let’s talk again. Maybe Bob (Robert Foster) could play Louis, the other guy.” So then I actually have Bob read Louis with me, and then read Max. And if that could work, maybe that could work. But no, everything that made him perfect for Max made him wrong for Louis. And so I get on the phone with De Niro — and I go, “Yeah, you know, I explored that. But no, everything about him that makes him perfect for Max makes him wrong to play this ex-convict guy.” And he goes, “Yeah, yeah, I get that. I get that, I get that, I get that. Okay, so tell me about this Louis character.” And I go, “You would consider playing Louis?” “Yeah, it’s a good character. It’s a good movie. I wanna be part of it. It’s a good character. I wanted the other character, but yeah, this is a good character. I’d be happy to play it.” I go, “Well, you didn’t let me know that before.” He goes, “Well, I didn’t wanna let you off the hook. I wanted you on the hook. But now if that ship has sailed, then let’s talk about Louis.” And then it was a done deal.”

Gangster Cinema Central

88,340 просмотров • 9 дней назад

Okay y'all this may be nothing, but this could be HUGE! I'd be remiss if I didn't share it with you. 🎆🔽📢📢🔽🎆 Last night when I was listening to POTUS' speech I heard something, but then became distracted by some negativity in the chat I needed to address. I then paused the chat so everyone including myself could truly understand what POTUS was trying to get across to us, if indeed it was meant for us. And by the way, that closing post took me 2 hours to write because my main focus was the military and being so grateful for them having a nice Christmas. The words are usually very hard to come by and I have to wait for God to give me the proper ones. However, as I thought more and more about it, I knew there was something more that caught my attention and I couldn't quite place it, it nagged at me all night even while I slept. This morning I asked one of our admins Claudia to help me find it. I knew it had something to do with our wallets. Thank you Claudia, you are such a precious friend to me and I thank God you are part of our team. So here it is folks... 🎙️ Captain Kyle, myself & several of our guests speakers have been talking to y'all for years about the new financial system and the changeover. We've talked about one day you looking at your accounts or wallets in shock. Thinking how could this possibly be. This I believe was the comm folks... "Nobody can believe what's going on, here are just some of the efforts that are underway. You will see in your Wallets, in your Bank Accounts in the New Year" 📢 PDJT National Address 12/17/2025 We also remember Tulsi saying something about clearing the debt for the New Year! Whatever it may be, I think we are in for one heck of a celebration for the 250th year, the Semiquincentennial... 🎆 Finally claiming our True Independence! 💥🎆🎆🎆🎆🎆🎆🎆💥 As always take what resonates, it's always sent with love, Kelly❤️ Capt Kyle

Capt Kyle

31,099 просмотров • 7 месяцев назад