Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Ok deployed it on and integrated into the full site Only thing is perspective is a bit off, so I'll try edit the printer with GPT Image 2 to get a slightly left view of it so it fits better But it works, fucking crazyyyyy

@levelsio

891,813 subscribers

75,285 views • 2 months ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

The full ARDY breakdown is out. Deployed it on a 5090 with zero problems. Then pushed further — retargeted the G1 skeleton motion onto a MetaHuman with Claude Code. It works, and it looks awesome (hands still need a bit of love). Full video:

The full ARDY breakdown is out. Deployed it on a 5090 with zero problems. Then pushed further — retargeted the G1 skeleton motion onto a MetaHuman with Claude Code. It works, and it looks awesome (hands still need a bit of love). Full video:

Stefan 3D AI

14,319 views • 1 month ago

We've decided that 5D wasn't enough, so we added another camera perspective to make it 6D. It took quite a bit of mental math to get the 2d game view on the second screen, but we got it 🙏 #screenbound #gamedev #indiedev

We've decided that 5D wasn't enough, so we added another camera perspective to make it 6D. It took quite a bit of mental math to get the 2d game view on the second screen, but we got it 🙏 #screenbound #gamedev #indiedev

Screenbound - A game about being distracted

31,959 views • 2 years ago

GPT Image 2 is live on Skywork. Try it, and win credits while you're at it. Repost + Like + Quote this post. Follow Skywork. You'll have a chance to win 1,000 credits—your ticket to generating with GPT Image 2.

GPT Image 2 is live on Skywork. Try it, and win credits while you're at it. Repost + Like + Quote this post. Follow Skywork. You'll have a chance to win 1,000 credits—your ticket to generating with GPT Image 2.

Skywork

13,560 views • 4 months ago

I vibe coded a game called Aether Breach for my son today. Built the whole thing in about 2 hours using Cursor, Grok 4.5, and GPT Image 2.0. He gave it a try and really liked it. I just need to make Easy mode a bit more relaxed so he can make it to the later stages. The full game has DualSense support too. I published my WebHID DualSense npm package a few days ago, so adding controller support to new games is pretty straightforward now. Really happy with how it turned out.

I vibe coded a game called Aether Breach for my son today. Built the whole thing in about 2 hours using Cursor, Grok 4.5, and GPT Image 2.0. He gave it a try and really liked it. I just need to make Easy mode a bit more relaxed so he can make it to the later stages. The full game has DualSense support too. I published my WebHID DualSense npm package a few days ago, so adding controller support to new games is pretty straightforward now. Really happy with how it turned out.

AshutoshShrivastava

116,280 views • 1 month ago

Hey! the Dream MCC11 PKW Macro info is all over the place, so I thought I'd condense the info into one quick video so people can understand it easier (from a parkour perspective) I'll put Hamm's twitch VOD in the description because it explains it better but this is something LOL

Hey! the Dream MCC11 PKW Macro info is all over the place, so I thought I'd condense the info into one quick video so people can understand it easier (from a parkour perspective) I'll put Hamm's twitch VOD in the description because it explains it better but this is something LOL

Kaelan

390,710 views • 6 months ago

Precise Edit is now available on Grok Imagine. It allows you to easily edit a specific part of an image without changing the rest. Grok automatically splits your image into multiple segments that you can select and edit individually. A super useful upgrade. Try it now!

Precise Edit is now available on Grok Imagine. It allows you to easily edit a specific part of an image without changing the rest. Grok automatically splits your image into multiple segments that you can select and edit individually. A super useful upgrade. Try it now!

DogeDesigner

68,901 views • 24 days ago

so i think this image is the most popular thing i’ve made. i didn’t put a ton of effort into it and later made a video out of it which was pretty simple. i always wish it was better when i see it get liked or shared. so i made a refreshed video! ai generated video and music 🔊🎶

so i think this image is the most popular thing i’ve made. i didn’t put a ton of effort into it and later made a video out of it which was pretty simple. i always wish it was better when i see it get liked or shared. so i made a refreshed video! ai generated video and music 🔊🎶

cybertied

13,262 views • 1 year ago

Vibe coding with Claude is so addictive… But does it ever feel a bit uncomfortable not fully understanding how any of it works?

Vibe coding with Claude is so addictive… But does it ever feel a bit uncomfortable not fully understanding how any of it works?

Gregory John

17,441 views • 7 months ago

Asked God’s Eye View to explain why there’s so much military activity in this area -- all using voice, while it sees what I’m seeing on the 3D map. Turns out Fort Rucker is a hot spot for helicopter training. So I jumped into cockpit view to track one of the choppers live in the middle of a drill. IMO gpt-realtime-2 is quite underrated for geospatial apps. Voice is such a natural interface for exploring the world and the data underpinning it. Code is open source if you wanna try it.

Asked God’s Eye View to explain why there’s so much military activity in this area -- all using voice, while it sees what I’m seeing on the 3D map. Turns out Fort Rucker is a hot spot for helicopter training. So I jumped into cockpit view to track one of the choppers live in the middle of a drill. IMO gpt-realtime-2 is quite underrated for geospatial apps. Voice is such a natural interface for exploring the world and the data underpinning it. Code is open source if you wanna try it.

Bilawal Sidhu

30,423 views • 6 days ago

i probably shouldn't be giving this away but f*ck it i built an agent that turns your ad script into model-specific prompts for AI video generation, based on skills for each model i use day-to-day here's how it works: > pick your mode - first frame or full video generation > pick your model - gpt-image-2, omni, kling, seedance 2.0 or 2.5 > paste your script - it splits it into scenes > get a prompt per scene, tuned for the exact model you picked most people think the model is what makes the ad... and it's true, but the prompt is what gets you a good generation on the first try instead of wasting money on rerolls - seedance wants timestamps. - omni wants references tagged. - gpt-image wants art direction and reference feed them all the same generic prompt and they all hand you slop these skills took me months of daily reps to get right, now i'm sharing it with you RT + reply "SCENES" and i'll send you the full thing so you can run in on your PC (must follow so i can dm)

i probably shouldn't be giving this away but f*ck it i built an agent that turns your ad script into model-specific prompts for AI video generation, based on skills for each model i use day-to-day here's how it works: > pick your mode - first frame or full video generation > pick your model - gpt-image-2, omni, kling, seedance 2.0 or 2.5 > paste your script - it splits it into scenes > get a prompt per scene, tuned for the exact model you picked most people think the model is what makes the ad... and it's true, but the prompt is what gets you a good generation on the first try instead of wasting money on rerolls - seedance wants timestamps. - omni wants references tagged. - gpt-image wants art direction and reference feed them all the same generic prompt and they all hand you slop these skills took me months of daily reps to get right, now i'm sharing it with you RT + reply "SCENES" and i'll send you the full thing so you can run in on your PC (must follow so i can dm)

MAX

17,129 views • 20 days ago

GPT Image 2 is actually insane I made this video with the images from it and it looks so much better than NBP but imo NBP is still way better GPT was a pain in the arse to work with >Constant NSFW tags (on gym pics) >Cant create backgrounds like NBP >Cant swap characters as good as NBP >Less consistent So yeh I’ll be sticking with NBP for now Im going to test making the back grounds and character swaps in NBP then changing them to higher quality with GPT though

GPT Image 2 is actually insane I made this video with the images from it and it looks so much better than NBP but imo NBP is still way better GPT was a pain in the arse to work with >Constant NSFW tags (on gym pics) >Cant create backgrounds like NBP >Cant swap characters as good as NBP >Less consistent So yeh I’ll be sticking with NBP for now Im going to test making the back grounds and character swaps in NBP then changing them to higher quality with GPT though

Pounds

42,082 views • 4 months ago

I tested MiniMax M3 so you do not have to. It is free in OpenCode right now and it claims to beat GPT 5.5 on SWE-bench. So I put it on real production code. It broke my push-to-talk. It glitched a game through the floor. It took two tries to render a video and still looked rough. The benchmark said one thing. The real work said another. The one thing it has going for it is price. I ran all of BridgeBench for $4.09. If budget is your only constraint, it is the cheapest Chinese model out there. But cheap is not free when it breaks your codebase. No BridgeMind stamp of approval. Full breakdown in the video.

I tested MiniMax M3 so you do not have to. It is free in OpenCode right now and it claims to beat GPT 5.5 on SWE-bench. So I put it on real production code. It broke my push-to-talk. It glitched a game through the floor. It took two tries to render a video and still looked rough. The benchmark said one thing. The real work said another. The one thing it has going for it is price. I ran all of BridgeBench for $4.09. If budget is your only constraint, it is the cheapest Chinese model out there. But cheap is not free when it breaks your codebase. No BridgeMind stamp of approval. Full breakdown in the video.

BridgeMind

46,557 views • 3 months ago

GPT Image 2 + Codex: or how to make Codex not suck at UI. Step 1: Generate a UI image (native in Codex) Step 2: Get Codex to implement the UI based on it Step 3: Get Codex to iterate until it aligns with the image as much as possible Codex is bad at initial UI, but very good at implementing a reference design, so this is your way out - iterate with the image model first and then Codex will do a good job.

GPT Image 2 + Codex: or how to make Codex not suck at UI. Step 1: Generate a UI image (native in Codex) Step 2: Get Codex to implement the UI based on it Step 3: Get Codex to iterate until it aligns with the image as much as possible Codex is bad at initial UI, but very good at implementing a reference design, so this is your way out - iterate with the image model first and then Codex will do a good job.

Peter Gostev

67,245 views • 4 months ago

the score for OBSESSION is insane. the song in this edit is from when they first start dating and everything seems all cute and the score feels happy but there’s something off with it, it’s so sad and beautiful and it being another version of “turning page” fits the theme so well

the score for OBSESSION is insane. the song in this edit is from when they first start dating and everything seems all cute and the score feels happy but there’s something off with it, it’s so sad and beautiful and it being another version of “turning page” fits the theme so well

xan 🕷️🦇

75,092 views • 3 months ago

Elon Musk on Starship “This is the largest flying object ever made. So, to catch it with giant robot arms and pluck it out of the sky is pretty insane, but I think it's got a decent chance of working. It might take a few kicks at the can before it works. But we're not breaking physics, so success is one of the possible outcomes here.”

Elon Musk on Starship “This is the largest flying object ever made. So, to catch it with giant robot arms and pluck it out of the sky is pretty insane, but I think it's got a decent chance of working. It might take a few kicks at the can before it works. But we're not breaking physics, so success is one of the possible outcomes here.”

Tesla Owners Silicon Valley

1,245,267 views • 1 year ago

🖨️ Little progress: I generated a dot matrix printer with GPT Image 2 and then some Photopea'ing to make the paper go through And I got COM1 to work for dial up internet to (my ISP) while COM2 still works for the printer (that was a challenge) Which means I can now print anything from the internet, like Hacker News! Some todo fixes: - page should scroll out not already be there - we need some perspective so the paper slowly goes into distance - integrate it into pieter .com page fully - add a local print command so you can actually IRL print your printed dot matrix print You can try it the current WIP here:

🖨️ Little progress: I generated a dot matrix printer with GPT Image 2 and then some Photopea'ing to make the paper go through And I got COM1 to work for dial up internet to (my ISP) while COM2 still works for the printer (that was a challenge) Which means I can now print anything from the internet, like Hacker News! Some todo fixes: - page should scroll out not already be there - we need some perspective so the paper slowly goes into distance - integrate it into pieter .com page fully - add a local print command so you can actually IRL print your printed dot matrix print You can try it the current WIP here:

@levelsio

43,147 views • 2 months ago