Loading video...

Video Failed to Load

Go Home

A tool returns an image of a secret number. The model reads it back. 👁️ TanStack AI now supports multimodal tool results: return an Array<ContentPart> with an image part and the model sees the actual pixels - not a stringified blob.

tan_stack's profile picture

TANSTACK

62,785 subscribers

16,098 views • 3 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Rodin Gen-2 API node, Rodin’s most powerful image-to-3D tool, is now live in ComfyUI! Turn any image into a 3D model with one click. It supports 4× Mesh Quality, T/A Pose, PBR textures, and Multiview to 3D model. 👇 Try it now in ComfyUI!
0:29

Rodin Gen-2 API node, Rodin’s most powerful image-to-3D tool, is now live in ComfyUI! Turn any image into a 3D model with one click. It supports 4× Mesh Quality, T/A Pose, PBR textures, and Multiview to 3D model. 👇 Try it now in ComfyUI!

ComfyUI

19,076 views • 11 months ago

With Gemini 3, you can take an image of anything, like a board game, a floor plan, or a doodle, and make it an interactive experience. This is because of Gemini 3’s deep multimodal understanding. The model is able to analyze the content of the image, distill the most compelling parts, and then translate the image’s details into a functional, interactive experience.
0:47

With Gemini 3, you can take an image of anything, like a board game, a floor plan, or a doodle, and make it an interactive experience. This is because of Gemini 3’s deep multimodal understanding. The model is able to analyze the content of the image, distill the most compelling parts, and then translate the image’s details into a functional, interactive experience.

Google AI

98,340 views • 9 months ago

i used AI to make an ad for an AI tool one product image. one prompt. it generated a cinematic cookie breaking apart in slow motion. no studio. no photographer. no edit. The tool is called eComrads it’s not even launched yet and it just marketed itself?
0:41

i used AI to make an ad for an AI tool one product image. one prompt. it generated a cinematic cookie breaking apart in slow motion. no studio. no photographer. no edit. The tool is called eComrads it’s not even launched yet and it just marketed itself?

K

17,387 views • 5 months ago

Claude Fable 5 built a 3D product website with Claude Code Generate an image of a product with the Magnific MCP, and convert it into a 3D model. Download that model and give it to Fable 5 to develop an interactive page with. Here's the final result + prompts:
0:29

Claude Fable 5 built a 3D product website with Claude Code Generate an image of a product with the Magnific MCP, and convert it into a 3D model. Download that model and give it to Fable 5 to develop an interactive page with. Here's the final result + prompts:

Jerrod Lew

33,687 views • 2 months ago

Occasionally I try an AI tool so incredible that I simply can’t stop playing with it. The new World Labs model definitely qualifies here. It’s almost impossible to describe how cool it is to walk through a 3D world that you generated from a single image.
0:20

Occasionally I try an AI tool so incredible that I simply can’t stop playing with it. The new World Labs model definitely qualifies here. It’s almost impossible to describe how cool it is to walk through a 3D world that you generated from a single image.

Justine Moore

272,963 views • 11 months ago

Excited to share Muse Spark! It's a strong natively multimodal model with many surprising properties that emerged. Here, the model is able to use Python tools to make a playable Sudoku game on the web from an image input of the board. ✨
0:42

Excited to share Muse Spark! It's a strong natively multimodal model with many surprising properties that emerged. Here, the model is able to use Python tools to make a playable Sudoku game on the web from an image input of the board. ✨

Matt Deitke

29,581 views • 4 months ago

Imagine a world where every image has a ZK verified checkmark, proving that the image came from an authentic camera, not generated by an AI model. threadguy wants to know, "Who's building this? I want to invest."
1:38

Imagine a world where every image has a ZK verified checkmark, proving that the image came from an authentic camera, not generated by an AI model. threadguy wants to know, "Who's building this? I want to invest."

Succinct

19,382 views • 1 year ago

🌎 GeoSpy AI can determine the location of an image using just a few pixels of reflection. No metadata required.
0:37

🌎 GeoSpy AI can determine the location of an image using just a few pixels of reflection. No metadata required.

Lord Bebo

46,653 views • 9 months ago

Playing with open-ended AI Agent behavior. Here's an AI Agent (claude code) making a self-portrait. It "evolves" the image by: writing code that generates image -> view image -> modify image -> view -> modify -> repeat.
0:41

Playing with open-ended AI Agent behavior. Here's an AI Agent (claude code) making a self-portrait. It "evolves" the image by: writing code that generates image -> view image -> modify image -> view -> modify -> repeat.

Max | Emergent Garden

22,963 views • 1 year ago

New art project: the concept is to carve an image into wood in a semi-abstract form that allows the viewer to both recognize and personalize the image. The image is carved as an array of precisely cut dimples in a piece of pale wood pre-coated with black paint. 1/7
0:44

New art project: the concept is to carve an image into wood in a semi-abstract form that allows the viewer to both recognize and personalize the image. The image is carved as an array of precisely cut dimples in a piece of pale wood pre-coated with black paint. 1/7

David R. Liu

85,057 views • 2 years ago

I used an image of my wife and me, along with Sora from OpenAI and an AI voice, to create a short film. The crazy part? Sora not only aged us realistically but also kept us wearing the exact same outfits from the original image.
0:28

I used an image of my wife and me, along with Sora from OpenAI and an AI voice, to create a short film. The crazy part? Sora not only aged us realistically but also kept us wearing the exact same outfits from the original image.

Brian Krassenstein

59,258 views • 1 year ago

a GPT alternative where each tool is provided by a third party and gets paid by the platform per use the main LLM will just be an orchestrated, selecting what tool to use when and pays it with x402 per task (search, image generation...)
3:19

a GPT alternative where each tool is provided by a third party and gets paid by the platform per use the main LLM will just be an orchestrated, selecting what tool to use when and pays it with x402 per task (search, image generation...)

Ash

15,056 views • 10 months ago

You imagine it. We create it. 🎨 Introducing #PixelStudio, a first-of-its-kind image generator on #Pixel9 powered by an on-device diffusion model¹ running on Tensor G4 and our Imagen 3 text-to-image model in the cloud.
0:34

You imagine it. We create it. 🎨 Introducing #PixelStudio, a first-of-its-kind image generator on #Pixel9 powered by an on-device diffusion model¹ running on Tensor G4 and our Imagen 3 text-to-image model in the cloud.

Made by Google

28,283 views • 2 years ago

Designing an Encoder for Fast Personalization of Text-to-Image Models TL;DR: use an encoder to personalize a text-to-image model to new concepts with a single image and 5-15 tuning steps abs: project page:
0:43

Designing an Encoder for Fast Personalization of Text-to-Image Models TL;DR: use an encoder to personalize a text-to-image model to new concepts with a single image and 5-15 tuning steps abs: project page:

AK

165,168 views • 3 years ago

Okay, OpenAI’s o3 is insane. Spent an hour messing with it and built an image-to-ASCII art converter, the exact tool I’ve always wanted. And it works so well
0:22

Okay, OpenAI’s o3 is insane. Spent an hour messing with it and built an image-to-ASCII art converter, the exact tool I’ve always wanted. And it works so well

Mike Bespalov

896,703 views • 1 year ago

🚀Introducing LLaVA Lightning: Train a lite, multimodal GPT-4 with just $40 in 3 hours! With our newly introduced datasets and the efficient design of LLaVA, you can now turbocharge your language model with image reasoning capabilities, in an incredibly affordable way.🧵
0:20

🚀Introducing LLaVA Lightning: Train a lite, multimodal GPT-4 with just $40 in 3 hours! With our newly introduced datasets and the efficient design of LLaVA, you can now turbocharge your language model with image reasoning capabilities, in an incredibly affordable way.🧵

Haotian Liu

302,319 views • 3 years ago