正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

I made a development that turns any product image into a 3D surface and allows logo positioning on it. It's pretty good for a first try. I used fal and Three.js for this. Let me share a few tips with you on how this works. 🧵

Aykut

4,822 subscribers

43,860 次观看 • 1 年前 •via X (Twitter)

教育科学技术

Anya Rossi• Live Now

Private livecam show

11 条评论

Aykut 的头像

Aykut1 年前

Using "image-preprocessors/depth-anything/v2" on @fal, I created a depth map to transform the product image into a 3D surface.

Aykut 的头像

Aykut1 年前

You can convert your 2D product image to 3D using this depthmap with @threejs.

Aykut 的头像

Aykut1 年前

All that remains is to add the interactions. 🪄 If you're interested, I can share all the code as open source. I hope this example has given you some ideas.

Raj Jha 的头像

Raj Jha1 年前

I made $4.2M from $500 this way: - Idea - FB Ad Test - Iterate - Statistical Analysis - Revenue Experiment - Scale a Winner This isn't a vague feel-good tweet This is how you use the scientific method to start a profitable business on the cheap

Antony Adhiban 的头像

Antony Adhiban1 年前

@FAL @threejs @pissang1 showcases cool stuff in the same vibe

Aykut 的头像

Aykut1 年前

@FAL @threejs @pissang1 I liked it! Thanks for sharing . ✨

lee 的头像

lee1 年前

@FAL @threejs Epic

Carlos DP 的头像

Carlos DP1 年前

@FAL @threejs Nice!

Kabooki AI 的头像

Kabooki AI1 年前

@FAL @threejs very cool!

Dan Benyamin (Æ) 的头像

Dan Benyamin (Æ)1 年前

@FAL @threejs @threadreaderapp unroll

Thread Reader App 的头像

Thread Reader App1 年前

@aykutkardas @FAL @threejs @dbenyamin Hi! here is your unroll: Talk to you soon. 🤖

相关视频

I miss how photos looked in the 90s. So I made a small tool that turns any photo into a retro one I used .BLACKBOX AI while building it to move faster and try things quickly. Works on mobile. Download instantly.

I miss how photos looked in the 90s. So I made a small tool that turns any photo into a retro one I used .BLACKBOX AI while building it to move faster and try things quickly. Works on mobile. Download instantly.

Prasenjit

63,274 次观看 • 6 个月前

Google Earth now allows importing ANY 3D model, so I used Tripo on fal to get Godzilla into Tokyo, and my Chrome extension to transform it into a movie scene 🎥

Google Earth now allows importing ANY 3D model, so I used Tripo on fal to get Godzilla into Tokyo, and my Chrome extension to transform it into a movie scene 🎥

Blendi

24,458 次观看 • 2 个月前

Okay, so I'm pretty sure I've found the best way in the world to create dynamic Open Graph images! And I've turned it into a little product that I'd love to show you 🤩 Check out this quick video tour of Ogkit to see how it works 👇 (I promise it's pretty cool!) TL;DR: Drop any HTML into a tag and Ogkit turns it into a dynamically generated Open Graph image for that page. Works with literally any stack. The only dependency is a tiny JS script. Got any questions about Ogkit? Would love to answer them!

Okay, so I'm pretty sure I've found the best way in the world to create dynamic Open Graph images! And I've turned it into a little product that I'd love to show you 🤩 Check out this quick video tour of Ogkit to see how it works 👇 (I promise it's pretty cool!) TL;DR: Drop any HTML into a tag and Ogkit turns it into a dynamically generated Open Graph image for that page. Works with literally any stack. The only dependency is a tiny JS script. Got any questions about Ogkit? Would love to answer them!

Peter Suhm

97,695 次观看 • 11 个月前

You can now train a 3D LoRA, exclusively on fal! TRELLIS.2 LoRA Trainer turns a folder of 3D assets into custom image-to-3D adapters, fine-tune shape and texture, then generate GLBs that match your style.

You can now train a 3D LoRA, exclusively on fal! TRELLIS.2 LoRA Trainer turns a folder of 3D assets into custom image-to-3D adapters, fine-tune shape and texture, then generate GLBs that match your style.

fal

50,927 次观看 • 1 个月前

I made an add-on that allows cameras and objects to target the clicked point on a surface. I'll share it soon. #b3d

I made an add-on that allows cameras and objects to target the clicked point on a surface. I'll share it soon. #b3d

Ilyasse L 🔸

44,021 次观看 • 1 年前

I recorded my entire 32mins session with In 32mins, I was able to produce a landing page with a product comparison chart. Video is uncut and at normal speed. I just added music so you don't get bored. I made this for those who haven't used and are interested to see how it works. This might be useful also for those asking me how I prompt. 700K tokens used for this session.

I recorded my entire 32mins session with In 32mins, I was able to produce a landing page with a product comparison chart. Video is uncut and at normal speed. I just added music so you don't get bored. I made this for those who haven't used and are interested to see how it works. This might be useful also for those asking me how I prompt. 700K tokens used for this session.

Melvin Vivas

56,340 次观看 • 1 年前

Presenting sir hiss, the first ever Swap Bot on Sorare Swaps 120% AUTOMATIC INSTANT answer, try it🚀 I made this account for me and for the community as a tool, I hope you like it🦾 I'm giving away my Kurzawa UNIQUE to 1 person who likes, retweets & follows me How it works🧵

Presenting sir hiss, the first ever Swap Bot on Sorare Swaps 120% AUTOMATIC INSTANT answer, try it🚀 I made this account for me and for the community as a tool, I hope you like it🦾 I'm giving away my Kurzawa UNIQUE to 1 person who likes, retweets & follows me How it works🧵

Sir Hiss - The Swap Bot

336,756 次观看 • 3 年前

i needed a *nice-looking* qr code for a recent project and wasn't happy with any of the results i found, so i made an app to do it for me and shipped it. this is qewie - make beautiful qr codes (qews?) with a few taps. save or share them wherever you want. live and free on the app store (link below)

i needed a nice-looking qr code for a recent project and wasn't happy with any of the results i found, so i made an app to do it for me and shipped it. this is qewie - make beautiful qr codes (qews?) with a few taps. save or share them wherever you want. live and free on the app store (link below)

jpa

540,612 次观看 • 1 年前

✨ Made a new mini feature on Photo AI: [ Grab from 3d model ] So the problem is we're at that stage in time (typical for AI) where image-to-3d models are not good enough but are fun to play with, but we know they'll be good enough in 1-2 years With [ Make 3d model ] you already can turn any Photo AI pic into a 3d model but it still looks hyper clunky and deformed, but it works! One cool idea I had to make that more useful and made now: Let people make a 3d model then change the view of the it with the 3d viewer, then press [ o ] and it grabs a frame of the 3d That image you can then [ Remix ] (img2img), and it becomes a real photo again and that in turn you can then turn into a video again with [ Make video ] So that essentially gives you a fully freeform camera position control to take photos with One thing I need to fix is the background/skybox, I kinda need to take the original photo and remove the person and just get the background for the 3d model viewer, in this case it should be white, but it's a start!

✨ Made a new mini feature on Photo AI: [ Grab from 3d model ] So the problem is we're at that stage in time (typical for AI) where image-to-3d models are not good enough but are fun to play with, but we know they'll be good enough in 1-2 years With [ Make 3d model ] you already can turn any Photo AI pic into a 3d model but it still looks hyper clunky and deformed, but it works! One cool idea I had to make that more useful and made now: Let people make a 3d model then change the view of the it with the 3d viewer, then press [ o ] and it grabs a frame of the 3d That image you can then [ Remix ] (img2img), and it becomes a real photo again and that in turn you can then turn into a video again with [ Make video ] So that essentially gives you a fully freeform camera position control to take photos with One thing I need to fix is the background/skybox, I kinda need to take the original photo and remove the person and just get the background for the 3d model viewer, in this case it should be white, but it's a start!

@levelsio

119,210 次观看 • 1 年前

Was working on a plugin that allows you to create a ragdoll skeleton for any single-part skinned mesh with a few button clicks If enough people want this I might polish it up and release it at some point #Roblox #RobloxDev

Was working on a plugin that allows you to create a ragdoll skeleton for any single-part skinned mesh with a few button clicks If enough people want this I might polish it up and release it at some point #Roblox #RobloxDev

tyridge77

16,792 次观看 • 2 年前

I was checking how the site for the Apple Vision Pro was made. Can confirm that this section was made with Three.js. They're using a pretty clever technique that breaks the Vision Pro model in segments using GLTFs and it's reassembled on the browser. Pretty darn cool.

I was checking how the site for the Apple Vision Pro was made. Can confirm that this section was made with Three.js. They're using a pretty clever technique that breaks the Vision Pro model in segments using GLTFs and it's reassembled on the browser. Pretty darn cool.

Davo

232,447 次观看 • 3 年前

Grant Nelson on signing with the Nets: "From the beginning, they had interest... I just saw that this would be the best opportunity... They believed in me and my development, so I felt like it was a good step for me to come here and learn a lot. It's been going pretty good."

Grant Nelson on signing with the Nets: "From the beginning, they had interest... I just saw that this would be the best opportunity... They believed in me and my development, so I felt like it was a good step for me to come here and learn a lot. It's been going pretty good."

Erik Slater

18,290 次观看 • 1 年前

RIP video editors I made these ads using only a product link and people thought it was a professional agency job. Let me show you how it works:

RIP video editors I made these ads using only a product link and people thought it was a professional agency job. Let me show you how it works:

Farhan

74,614 次观看 • 11 个月前

this morning I taught the 3D team at my agency how I make my videos we worked together on a new video in a 3D CGI style, and it reminded me how much I love that render character made on Midjourney and animated with Runway

this morning I taught the 3D team at my agency how I make my videos we worked together on a new video in a 3D CGI style, and it reminded me how much I love that render character made on Midjourney and animated with Runway

INK

85,929 次观看 • 12 天前

One of the most common challenges of indie hacker is product demand positioning and marketing. On March 8, I launched a Skill collection website in just three days, and I’ve been maintaining it ever since. Along the way, I’ve done a lot of work: optimizing features, updating content, adjusting positioning... but something always seems missing. Recently, I came across a very impressive AI research product that helps validate product feasibility and avoids falling into the trap of self-indulgence. It’s called atypica.AI. Let me break down why this product is actually impressive How it works？ It's very simple. After you give it a business problem, it first clarifies your needs and plans the research approach like a research team. It will help you step into the perspective of your target users and validate whether a product is worth building — before you commit.

One of the most common challenges of indie hacker is product demand positioning and marketing. On March 8, I launched a Skill collection website in just three days, and I’ve been maintaining it ever since. Along the way, I’ve done a lot of work: optimizing features, updating content, adjusting positioning... but something always seems missing. Recently, I came across a very impressive AI research product that helps validate product feasibility and avoids falling into the trap of self-indulgence. It’s called atypica.AI. Let me break down why this product is actually impressive How it works？ It's very simple. After you give it a business problem, it first clarifies your needs and plans the research approach like a research team. It will help you step into the perspective of your target users and validate whether a product is worth building — before you commit.

Jason Zhu

84,745 次观看 • 2 个月前

Waterfall breakdown time! Been working on this waterfall material for the last few days, I want to share a few neat things and gotchas I found when working on it. It's not very complex of an effect, really just a few panning textures! 🧵1/n

Waterfall breakdown time! Been working on this waterfall material for the last few days, I want to share a few neat things and gotchas I found when working on it. It's not very complex of an effect, really just a few panning textures! 🧵1/n

Dylan Meville

510,040 次观看 • 3 年前

I 3D Printed a working 3D Printer, let me show you how it works.

I 3D Printed a working 3D Printer, let me show you how it works.

Unnecessary Inventions

31,107 次观看 • 1 年前

After a few days of hard work, I’m finally able to share a tour of my new home. I was nervous about filming this felt pretty self-conscious about how I might come across on camera. But this is a big step for me, and I wanted to share it anyway. Hope you enjoy the video. 😊

After a few days of hard work, I’m finally able to share a tour of my new home. I was nervous about filming this felt pretty self-conscious about how I might come across on camera. But this is a big step for me, and I wanted to share it anyway. Hope you enjoy the video. 😊

Ben Canham

15,899 次观看 • 10 个月前

I just found a web agent framework built specifically for LLMs. It turns any site into clean, agent-ready text. Any LLM can now act on the web. It’s called Notte, and it changes everything. Let me show you how:

I just found a web agent framework built specifically for LLMs. It turns any site into clean, agent-ready text. Any LLM can now act on the web. It’s called Notte, and it changes everything. Let me show you how:

Markandey Sharma

52,026 次观看 • 1 年前

I built a free tool that shows how night-time lights have changed anywhere on Earth. Here's how it works and why it's useful for monitoring conflict, disasters, development and growth. 👇

I built a free tool that shows how night-time lights have changed anywhere on Earth. Here's how it works and why it's useful for monitoring conflict, disasters, development and growth. 👇

Benjamin Strick

41,639 次观看 • 5 个月前