sometimes a vibecoded visual generator isn't a deliverable for... clients; it's to help me think and explore faster. i wanted to try a graphic element today for a brand identity i'm designing: colored rays, with progressive blur. described it to Claude, pasted in some image references, had a minitool in a minute. then i just played with it: spacing, color, falloff, blur, grain... i could've made this manually, but it's a much faster way to explore and iterate early in the creative process — and honestly, sometimes stumble into a happy accident.show more

Another example of a quick, throwaway visual tool that... I vibecoded to explore an idea (this time with Claude Fable). It exports video loops, and I can play around with colour, grain, direction... Took around 5 prompts and gave me a massive head start on a brand identity direction.show more

Got early access to MiniMax H3, so I had... to try something with it. I generated 5 still frames for a fictional series intro, used them as Omni References and turned them into a short title sequence. Just sharing my first test and there's still a lot more to explore, but it's been fun playing around with it so far. I'll keep experimenting and share more as I go. #MiniMaxH3show more

➡️It's a little embarrassing to share, but I feel... like it took me way to long to realize the better workflow with rigging. So here's a little #live2d tip for those beginner artists that clicked for me a while back! I used to rig all body, clothing, and accessories for one given area all at once, but I think it ended up being inconsistent to other parts of the model. My workflow was slower too. 😬 It's similar to the inconsistencies you'd get by not drawing the bone structures of your character drawing, and just trying to draw the clothes right away. Body parts can sometimes seem to not line up, especially as a newer artist. It's a small change, but rigging only the nude base in full and then slowly adding one clothing part at a time makes the entire rigging process easier.😄 I know it seems really obvious, but I actually didn't start doing this until early last year. Everything comes together much faster and much more consistently, so definitely give it a try! Hope you enjoy this #vtuber leg rigging ☺️show more

I underestimated Sora 2. After using it for a... while I honestly think it's being undersold. I went in comparing it 1:1 to Veo but they are not really aiming for the same thing anymore. This is a meme machine. It's specialized. A TikTok generator. It's also very fun.show more

hate to beat a dead horse but sometimes I... think about how sharkyleo blocked me for no reason and said this when I made a satirical tweet about it and giggle a littleshow more

I had a chance earlier this season to watch... some Ultimate Frisbee and it was a revelation to me: it's a majestic game. My guy Charlie Wagner with an incredible catch and then scoring pass in the title game 👌show more

🐰: in the end, i really wanted to put... my own color and energy into it. 🐰: it means a lot to me, so i hope it reaches you all in a meaningful way too. 🐰: that’s what i wanted to share with you! 🐰: 🥰🥰🥰show more

Made this commercial demo entirely with Seedance 2.0 via... Yapper Everything you see here is done by one single prompt shot, from the cuts, edits, graphic effects, to the voice over. Basically within the prompt I gave detailed instructions on how many shots I wanted, the timestamps, the copywriting, visual and graphic effects, etc. The full prompt sample is available for my subscribers only in the comment section below ⏬ + + + There are so many use cases for Seedance 2.0 instead of just recreating existing IP. I think for me as a copywriter, what I like about it is that I can create a pre-visualization of an ad we're about to make, with its specific tone and style. Like I said before, the AI generated content here wasn't meant to be the final product, but rather a starting point for our creative direction regarding the potential style that will go into our ads. It's just that it's now so much faster to iterate ideas, and to test many different concepts with Gen-AI. Like I've always said, the technology is here, and it's up to you how you want to use it.show more

$PONS officially made me a millionaire. the tears are... literally coming to my eyes. it's crazy how quickly life can change, sometimes i think it was just luck. but that would take away from all the work i've put in to get here. starting september with over $1m in my account still feels like a dream, but it's real. i love this world, and i love myself for never giving up.show more

i tried Framer Agent to build a brand guidelines... website template, something i've meant to do for a while. a site i can swap a logo, nudge a colour, update the type, and send a link instead of re-exporting a pdf nobody opens. a few observations on the AI process: - i started with references. pulled together a handful of minimalist grid layouts and had Claude describe the visual style back to me. you can do the same inside Framer, feeding it the references directly. - from there i had it write a detailed prompt aimed at that exact style, then asked it to break it into a few smaller steps. then i fed those into the agent, one at a time. - the scaffolding stage is the satisfying part. for something this grid-driven (the columns, the spans, the whole underlying structure) watching it land in seconds is hard to look away from. - but then i still have to sweat the details: text alignment, line-heights, image sizes. i don't mind it at all; it's the part i like, making these design decisions. the strength of the agent is the mundane work. point it at the stuff that eats your time: cleaning up the build, adding responsiveness, dropping in small effects, checking text and colour styles stay consistent, writing alt text for every image. then i get the time back for the parts of web design that are actually fun. 🤝show more

i found the code for this in the files!!... it's in an object called obj_bushjump, it's a bit broken by default due to the assets being moved at some point and a bit of the code being fucked with/deleted for some reason, but i was able to fix itshow more

I had an early access to GPT-6 Astra and... I can say, everyone in the world now has a 3D designer at their fingertips. I gave it an image of a house and asked to create it in 3D with all the details including toys, appliances and furniture. This a full 3D model reconstruction in Blender with geometry that you can manually tweak and run 60fps as a locally rendered "game" on device.show more

I can break down stats and numbers -- analyze... this and that, but sometimes a team just has to have that *it* factor. The Tampa Bay Rays are a special group. Rays-Yankees in the Bronx will be must-watch TV for baseball fans this weekend.show more

I used to play way too much Vampire Survivors.... I stopped for about a year after I had maxed most everything and all the DLC content. Decided to start over today. It's such a ridiculously addictive game. At some point in a level you're basically invincible and just coin farm to build character XP.show more

I spent a day playing with GPT-5.6-Sol, and I... can now say with much more confidence that it hasn’t improved at design tasks. I haven’t noticed any meaningful improvement in its coding capabilities, either. Maybe it's just in the tasks I gave it. However, I finished an app we started building on a stream yesterday and brought it close to the original idea I had in mind. It’s incredibly easy to build tools like this these days. I basically gave Codex a batch of editorial grid examples, then combined those layouts with formula-based pattern generation. A few prompts and some polishing, and you have something that can serve as a basic brand identity system.show more

At Tozaisen this week, Tomoza landed what appears to... be a crossup Double Knee. I took it into training mode for a bit, but the timing and spacing is so specific that I couldn't hit it with much consistency. By the way, TMF and TMZ had a great run so check out the video!show more

I enjoy @DaHeckSaJerry's art a lot so I wanted... to do a thing just to do something for me for the day. Not sure of Reynard and Cauli's headcanon voice so I could probably try again with feedback but it was fun to make a little dub after so long ^^; Hope it's alright!💖show more

A little experiment I wanted to try with Wan... Vase, Flux.1 Kontext, and Act 1. ❗️Disclaimer: Posting this is not me saying it would be better in color, that it should be made in color, or that this would be suitable for final production use. I just wanted to test what’s possible. 😊show more

a fun workflow for prepping a talk: > record... a draft video without a script > have Claude Code turn the video into a Notion page with slides + transcript of what I said > ask people for feedback on the video; Claude processes their notes and attaches things as inline comments in the relevant spots > read through the page, manually edit to refine the wording of what I want to say Crucially, I'm in creative control. AI is *not* writing the talk for me in any way! It's providing tools that make it easier for me to think together with my team. h/t Thariq for inspiration, his video editing workflow got me thinking about how useful coding agents can be for video processingshow more