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。

Image to Light - the first AI implementation test on for lighting estimation, and it's🔥 It can generate 360 HDRI light based on just one reference image. Ideal for capturing the lighting from real photos and creating renderings with backplates. I had planned any AI implementation for later, but... show more

max

1,808 subscribers

42,441 次观看 • 2 年前 •via X (Twitter)

科学技术艺术

Anya Rossi• Live Now

Private livecam show

11 条评论

Scotty 的头像

Scotty2 年前

Does it generate a HDR image for you or LDR? Impressive regardless!

XAQQTIN 3D 的头像

XAQQTIN 3D2 年前

wow this is actually super useful.

Brian @ AHXE Labs 的头像

Brian @ AHXE Labs2 年前

This is insane 😳

RΞNN 的头像

RΞNN2 年前

Agree with Brian, that’s definitely could be marketed as a separate product, as well as integrated into packshot

max 的头像

max2 年前

Thanks

Brian Donlin 的头像

Brian Donlin2 年前

People would pay for just this by itself as an app or plug-in for other rendering platforms

max 的头像

max2 年前

Yeah, maybe I'll develop it as an extension, but currently it's quite immature. I'm more focused on the rendering part

Maciek Czarnik 的头像

Maciek Czarnik2 年前

Crazy! I’ve been actually thinking about such use case today 😀 Just thinking though, I’m light years behind you in rendering 😅 Just curious - what resources helped you to get to that place?

max 的头像

max2 年前

thanks! currently it's based on this

˗ˏˋ⚡️ˎˊ- 的头像

˗ˏˋ⚡️ˎˊ-2 年前

Very interesting can you share some technical details? It reminds me of WonderDynamics generated environment map

max 的头像

max2 年前

It's still in its fledgling stage, I've just tested proof of concepts based on currently, I'm more focused on the actual rendering and product side

相关视频

I prompted Omma to build a #threejs app with real dynamic lighting on a 3D mesh - generated from a single image, using Depth Anything v2 + Transformers from Hugging Face ⚡ Depth estimation in the browser 🫧 3D mesh from the depth map 💡 Dynamic lighting reacting to the geometry No manual code. Pure AI prompting. The future of 3D on the web feels wide open.

I prompted Omma to build a #threejs app with real dynamic lighting on a 3D mesh - generated from a single image, using Depth Anything v2 + Transformers from Hugging Face ⚡ Depth estimation in the browser 🫧 3D mesh from the depth map 💡 Dynamic lighting reacting to the geometry No manual code. Pure AI prompting. The future of 3D on the web feels wide open.

Joseph Azar

14,041 次观看 • 2 个月前

My canvas based AI image generation tool is live! It's built on top of tldraw and uses Nano Banana Pro for image generation. You can sketch, annotate, collage in a frame... And then click to generate an image. Check it out 👉

My canvas based AI image generation tool is live! It's built on top of tldraw and uses Nano Banana Pro for image generation. You can sketch, annotate, collage in a frame... And then click to generate an image. Check it out 👉

Charlie Clark

44,335 次观看 • 7 个月前

Vidu is the craziest AI video model I’ve tested this week. I used just a prompt and one image, and got cinematic results with motion, lighting, and effects. Hard to believe this level of cinematic videos it can generate. 10 wild outputs: 1. Crime thriller

Vidu is the craziest AI video model I’ve tested this week. I used just a prompt and one image, and got cinematic results with motion, lighting, and effects. Hard to believe this level of cinematic videos it can generate. 10 wild outputs: 1. Crime thriller

Atal

40,114 次观看 • 1 年前

Your AI employees are here! MetaGPT not only thinks, but it assigns you a whole AI team of product manager, architecture, engineer, etc based on your prompt. It provides a universal AI chat interface you can use to build software, write blogs, create documents, generate videos, etc. Why I like it and you will too: • everything at one chat interface • chat with each AI agent • Supabase integration • deploy with one click The MetaGPT team is kind enough to give me early access and collaborate with me for this post. In the video below, I am building a quick web application that converts any image to ghibli-style image.

Your AI employees are here! MetaGPT not only thinks, but it assigns you a whole AI team of product manager, architecture, engineer, etc based on your prompt. It provides a universal AI chat interface you can use to build software, write blogs, create documents, generate videos, etc. Why I like it and you will too: • everything at one chat interface • chat with each AI agent • Supabase integration • deploy with one click The MetaGPT team is kind enough to give me early access and collaborate with me for this post. In the video below, I am building a quick web application that converts any image to ghibli-style image.

Pratham

54,106 次观看 • 1 年前

3D AI is leveling up! Rodin 3D AI can create stunning, high-quality 3D models from just text or image inputs. And with its latest update, it can even generate 8K HDRI textures to bring your models to life. Check out the link in the comments!

3D AI is leveling up! Rodin 3D AI can create stunning, high-quality 3D models from just text or image inputs. And with its latest update, it can even generate 8K HDRI textures to bring your models to life. Check out the link in the comments!

el.cine

46,032 次观看 • 1 年前

Just Shipped: The AI Ads Cloner 🧬🤖 Took me 3 days of tryhard to make it, but the result is worth it You can now clone any ad with AI in just one click with the Chrome Extension 😃 Can be done from: - The "Clone Ad" button in the Facebook Ads library - By doing a right click on any image! Available for all Generate Ads customers :)

Just Shipped: The AI Ads Cloner 🧬🤖 Took me 3 days of tryhard to make it, but the result is worth it You can now clone any ad with AI in just one click with the Chrome Extension 😃 Can be done from: - The "Clone Ad" button in the Facebook Ads library - By doing a right click on any image! Available for all Generate Ads customers :)

Nico

36,368 次观看 • 1 年前

VEO 3.1 just unlocked something massive for AI video Consistent characters, seamless transitions, reference to image. And now, for the first time, you can bring them together to create complete videos, inside one powerful AI platform — invideo

VEO 3.1 just unlocked something massive for AI video Consistent characters, seamless transitions, reference to image. And now, for the first time, you can bring them together to create complete videos, inside one powerful AI platform — invideo

Future Stacked

108,374 次观看 • 8 个月前

I made a quick little threejs previewer for patina outputs. paste the json, click apply, preview it within threejs on a plane or sphere with an HDRI or basic lighting (via the Three Lights option in the HDRI dropdown)

I made a quick little threejs previewer for patina outputs. paste the json, click apply, preview it within threejs on a plane or sphere with an HDRI or basic lighting (via the Three Lights option in the HDRI dropdown)

Codetaur

54,218 次观看 • 2 个月前

You can now use rendered frames for image-to-image and image-to-video AI Generation on The Render Network Simply click “Iterate with AI” and instantly create new image + video variations right from the Render job page. No downloads, no switching tabs - just click and create. Try at: Learn more:

You can now use rendered frames for image-to-image and image-to-video AI Generation on The Render Network Simply click “Iterate with AI” and instantly create new image + video variations right from the Render job page. No downloads, no switching tabs - just click and create. Try at: Learn more:

The Render Network

37,689 次观看 • 1 年前

So randomly, I got a "Image to 3D Model using AI" AD, and I decided to test it with the best guy possible. Its CURSED💀! but not that bad for only 1 reference. I wanna hear your opinion! what do you think?🤔

So randomly, I got a "Image to 3D Model using AI" AD, and I decided to test it with the best guy possible. Its CURSED💀! but not that bad for only 1 reference. I wanna hear your opinion! what do you think?🤔

Games Production (COMMISSIONS OPEN!)

33,948 次观看 • 1 年前

Akari - Our 2D light tracing experiment just goes live!! It comes with a few mini light demos for you to explore!! Light must go on!! ✨🌈 ↳ #threejs #webgl

Akari - Our 2D light tracing experiment just goes live!! It comes with a few mini light demos for you to explore!! Light must go on!! ✨🌈 ↳ #threejs #webgl

Lusion™

90,561 次观看 • 2 年前

If you've ever had to wait minutes for simple changes to be handled by your ai agent, I encourage you to give this XML Edit workflow a try! It's great for rapid iteration, but it's also excellent for a first pass implementation with GPT-5 Pro. Here's how it works 👇

If you've ever had to wait minutes for simple changes to be handled by your ai agent, I encourage you to give this XML Edit workflow a try! It's great for rapid iteration, but it's also excellent for a first pass implementation with GPT-5 Pro. Here's how it works 👇

eric provencher

36,621 次观看 • 9 个月前

Fiverr just launched a platform for freelancers to train a custom AI model, and "sell" the ability to generate work with it. They're pitching it as a way for creators to scale the number of projects they can handle at once. Models are trainable on text, image, and sound.

Fiverr just launched a platform for freelancers to train a custom AI model, and "sell" the ability to generate work with it. They're pitching it as a way for creators to scale the number of projects they can handle at once. Models are trainable on text, image, and sound.

Olivia Moore

117,853 次观看 • 1 年前

A useful trick for making AI photos look 100% real: (it's not always the model — it can be the color grading) Out of the box, Nano Banana Pro can have a gray, flat look. Good composition, but these scream AI. Here's the system that fixes it: → Grab a reference photo from Pinterest with the exact aesthetic you want → Feed it to ChatGPT 5.2 with a prompt that extracts a detailed color grading JSON → Paste that JSON into image generator (Calico AI) → Generate your product photo. (the colors are now based on the reality you specify, not AI defaults) → Save that character as your reference for facial consistency across future shots From here you can build a full UGC model library. No creators. No shoots. Comment "IMAGE" if you want me to send you every prompt in this system (must be following so I can dm you!).

A useful trick for making AI photos look 100% real: (it's not always the model — it can be the color grading) Out of the box, Nano Banana Pro can have a gray, flat look. Good composition, but these scream AI. Here's the system that fixes it: → Grab a reference photo from Pinterest with the exact aesthetic you want → Feed it to ChatGPT 5.2 with a prompt that extracts a detailed color grading JSON → Paste that JSON into image generator (Calico AI) → Generate your product photo. (the colors are now based on the reality you specify, not AI defaults) → Save that character as your reference for facial consistency across future shots From here you can build a full UGC model library. No creators. No shoots. Comment "IMAGE" if you want me to send you every prompt in this system (must be following so I can dm you!).

David Roberts

20,901 次观看 • 4 个月前

IKON-2 for brands is here! Achieve state of the art GenEval scores, Ikon-2 pushes the pareto frontier of quality and efficiency for image generation. Built for brands, Ikon-2 can generate up to 8MP photos (2K x 4K pixels) with strong product consistency via fine-tuning. Achieve camera-quality for the first time with AI — with improved lighting, contrast, and textures, for beauty, beverage, and other products. Sign up for a demo here

IKON-2 for brands is here! Achieve state of the art GenEval scores, Ikon-2 pushes the pareto frontier of quality and efficiency for image generation. Built for brands, Ikon-2 can generate up to 8MP photos (2K x 4K pixels) with strong product consistency via fine-tuning. Achieve camera-quality for the first time with AI — with improved lighting, contrast, and textures, for beauty, beverage, and other products. Sign up for a demo here

NEX

106,033 次观看 • 1 年前

Depressing. Did a little image search for the fake ai generated image of a native American with wolf (based on a photo of someone from Siberia with a dog) to see how far it hat polluted the internet... judge for yourself:

Depressing. Did a little image search for the fake ai generated image of a native American with wolf (based on a photo of someone from Siberia with a dog) to see how far it hat polluted the internet... judge for yourself:

Fake History Hunter

17,488 次观看 • 11 个月前

Took it further with Omma AI, (Spline ) now it works on video, and everything working in a Web Browser. Drop a video, Depth Anything v2 calculates the depth map frame by frame, and Three.js renders a fully lit 3D mesh in real time. Depth estimation on video in the browser +Automatic baking pass + Dynamic lighting reacting to the geometry #vibecoding #threejs #webgl

Took it further with Omma AI, (Spline ) now it works on video, and everything working in a Web Browser. Drop a video, Depth Anything v2 calculates the depth map frame by frame, and Three.js renders a fully lit 3D mesh in real time. Depth estimation on video in the browser +Automatic baking pass + Dynamic lighting reacting to the geometry #vibecoding #threejs #webgl

Joseph Azar

147,333 次观看 • 2 个月前

AI just fired the video editor 3D Motion just dropped the fastest way to turn any image into a cinematic video. With depth mapping, smooth camera moves, and movie-like lighting, it makes static photos look like Hollywood shots. Tutorial below + Prompts:

AI just fired the video editor 3D Motion just dropped the fastest way to turn any image into a cinematic video. With depth mapping, smooth camera moves, and movie-like lighting, it makes static photos look like Hollywood shots. Tutorial below + Prompts:

Robin Delta

137,751 次观看 • 9 个月前

📽️ AI Agent for image-to-video video generation (beta) Combine with Pumpzy AI Agent - Add an image - Add a few words to generate video - Launch Pump Fun token right from AI chat Use-case: Make angry video & launch it on Pump Fun There is a short showcase from the AI chat 🔽

📽️ AI Agent for image-to-video video generation (beta) Combine with Pumpzy AI Agent - Add an image - Add a few words to generate video - Launch Pump Fun token right from AI chat Use-case: Make angry video & launch it on Pump Fun There is a short showcase from the AI chat 🔽

ZODs

14,673 次观看 • 1 年前

Grok just dropped a crazy AI feature you can now edit image by chatting to Grok and.. it can even change specific object in the image this is incredible for AI artist

Grok just dropped a crazy AI feature you can now edit image by chatting to Grok and.. it can even change specific object in the image this is incredible for AI artist

el.cine

159,848 次观看 • 1 年前