Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Ideogram just released the #1 open weight image model in the world. It punches way above its weight - it's small enough to run on a consumer GPU, but goes head-to-head with Nano Banana and GPT Image for design. We went deep with Mohammad Norouzi on how they did... show more

Justine Moore

215,582 subscribers

39,900 Aufrufe • vor 3 Monaten •via X (Twitter)

Nachrichten & Politik Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Ideogram announced Ideogram 4.0, a new SOTA open image generation model! > Ideogram 4.0 lands in the 8th spot on LM Arena and the 5th spot on Design Arena in the text-to-image category, and is getting close to Nano Banana Pro's performance. > Ideogram 4.0 features dense, accurate text rendering, native 2K resolution, active background transparency, and precise layout control.

Ideogram announced Ideogram 4.0, a new SOTA open image generation model! > Ideogram 4.0 lands in the 8th spot on LM Arena and the 5th spot on Design Arena in the text-to-image category, and is getting close to Nano Banana Pro's performance. > Ideogram 4.0 features dense, accurate text rendering, native 2K resolution, active background transparency, and precise layout control.

🚨 AI News | TestingCatalog

19,674 Aufrufe • vor 4 Monaten

🚨🍌Big Reveal: who was "Nano Banana?" The anonymous model, “nano-banana,” that caught the world's attention with its ability to follow complex instructions, preserve character identity, and maintain contextual details was: Gemini-2.5-Flash-Image-Preview by Google DeepMind 🍌✨ - Now ranked #1 on the Image Edit Arena - Also ranked #1 for Text-to-Image In two weeks, “nano-banana” has driven over 5 million votes to the Image Edit Arena. With 2.5M+ votes for this model, it is the highest number of votes any model has received, with the largest Elo score lead (171) in Arena history. Congrats to the Google DeepMind team on this incredible milestone in image edit and generation. 👏

🚨🍌Big Reveal: who was "Nano Banana?" The anonymous model, “nano-banana,” that caught the world's attention with its ability to follow complex instructions, preserve character identity, and maintain contextual details was: Gemini-2.5-Flash-Image-Preview by Google DeepMind 🍌✨ - Now ranked #1 on the Image Edit Arena - Also ranked #1 for Text-to-Image In two weeks, “nano-banana” has driven over 5 million votes to the Image Edit Arena. With 2.5M+ votes for this model, it is the highest number of votes any model has received, with the largest Elo score lead (171) in Arena history. Congrats to the Google DeepMind team on this incredible milestone in image edit and generation. 👏

Arena.ai

106,535 Aufrufe • vor 1 Jahr

We gave four frontier image editing models the same photo and 30 edits in a row: Ideogram 4.5 keeps most of the room intact, while the others drift, GPT Image 2.5 Sunburst most visibly. We've seen some interesting demos of multi-turn editing consistency from the latest image editing models, so we ran our own test: GPT Image 2.5 Sunburst, #1 on our Image Editing leaderboard, against Ideogram 4.5, FLUX 3 and Nano Banana 2.1. Our leaderboard scores single edits; this tests what happens when 30 consecutive changes stack up, with each model editing its own previous output through a 30-step real estate staging sequence: light the fire, add a sofa, repaint the walls, swap day for twilight, and more. Why are the final results so different? Ideogram's Ideogram 4.5 and BlackForestLabsAI - Unofficial's FLUX 3 edit locally. On small edits like adding a vase of tulips, we measured that they left 95% or more of the image essentially untouched. GPT Image 2.5 (Sunburst) re-renders most of the entire image on every edit, leaving only about a fifth of the image unchanged, so small shifts in colour and detail compound over turns. Nano Banana 2.1 sits in between: its edits stay local, but the rest of the image shifts slightly and gradually darkens.

We gave four frontier image editing models the same photo and 30 edits in a row: Ideogram 4.5 keeps most of the room intact, while the others drift, GPT Image 2.5 Sunburst most visibly. We've seen some interesting demos of multi-turn editing consistency from the latest image editing models, so we ran our own test: GPT Image 2.5 Sunburst, #1 on our Image Editing leaderboard, against Ideogram 4.5, FLUX 3 and Nano Banana 2.1. Our leaderboard scores single edits; this tests what happens when 30 consecutive changes stack up, with each model editing its own previous output through a 30-step real estate staging sequence: light the fire, add a sofa, repaint the walls, swap day for twilight, and more. Why are the final results so different? Ideogram's Ideogram 4.5 and BlackForestLabsAI - Unofficial's FLUX 3 edit locally. On small edits like adding a vase of tulips, we measured that they left 95% or more of the image essentially untouched. GPT Image 2.5 (Sunburst) re-renders most of the entire image on every edit, leaving only about a fifth of the image unchanged, so small shifts in colour and detail compound over turns. Nano Banana 2.1 sits in between: its edits stay local, but the rest of the image shifts slightly and gradually darkens.

Artificial Analysis

52,850 Aufrufe • vor 1 Tag

I just put Kling 2.6 head-to-head with the newly released Runway Gen-4.5 (image to video) Kling 2.6 videos and images made with Nano Banana Pro inside Leonardo.Ai I included 9 examples with full prompts 🧵👇 Which model surprised you the most? I’m reading the comments

I just put Kling 2.6 head-to-head with the newly released Runway Gen-4.5 (image to video) Kling 2.6 videos and images made with Nano Banana Pro inside Leonardo.Ai I included 9 examples with full prompts 🧵👇 Which model surprised you the most? I’m reading the comments

MayorkingAI

25,337 Aufrufe • vor 8 Monaten

here's how to do this in 2 minutes: - upload 0% interest image to gemini - ask it to generate a 1:1 prompt - generate the image with nano banana pro - lipsync with veo / infinitetalk (open-source) - voice change with minimax audio congrats you just got yourself 0% interest.

here's how to do this in 2 minutes: - upload 0% interest image to gemini - ask it to generate a 1:1 prompt - generate the image with nano banana pro - lipsync with veo / infinitetalk (open-source) - voice change with minimax audio congrats you just got yourself 0% interest.

0x ROAS

15,926 Aufrufe • vor 8 Monaten

All these demo videos make HEAD SWAPPING with Nano Banana look so easy, but then you give it a try and you're like... uh... what? Why didn't that work? Here's what I've found. Nano Banana reads your image, almost literally, so if you write on the image, it reads the text. This is how Higgsfield AI 🧩 has capitalized on the tech: "Write on the image" and give it direction, right? Totally true, but you don't need Higgi to write on your image. Nano Banana will understand your direction regardless of where you write on your image. On one hand, Higgi is really smart, because they're hranessing the tech in a unique way, but the whole "Higgsfield's Banana Placement" is a bit of a misnomer. It's more of a "Banana Placement" and Higgi is just giving you a sort of basic Photoshop-type tool to work with (again, pretty smart), but the real tech is the Banana. 🍌 This is how I head swapped heads in Runway, but Nano Banana maintains the aesthetic qualities of your image almost perfectly, whereas Runway Reference spits out a very Gen-4 looking image. I like using Nano in Freepik (now Magnific), mainly because it's fast and I can get 4 gens at a time, and you need to gen a dozen times of so before you get a winner (most of the time). I was pumped when I saw Freepik introduce the @ reference feature, just like Runway has, but it doesn't seem to work for head swapping. My guess is because that's not really how Nano Banana tech works... ideally. Marco is the person I saw using this "A" and "B" method, back when Nano was on LM Arena, and man-oh-man, it just works... like a charm. You need experiment with how much of the face you blot out, and the angle and facial expression of your new head if you want the blend to be perfect. All of the results in this video are 100% Nano Banana. I did not do any Photoshop work to the images after the fact. I really hope this helps. Let me know if you have any questions. I'm happy to help. And I'll keep posting videos like this if you guys find them useful. Let me know! And if you want more serious, one-on-one AI consultation you can throw something on the books here:

All these demo videos make HEAD SWAPPING with Nano Banana look so easy, but then you give it a try and you're like... uh... what? Why didn't that work? Here's what I've found. Nano Banana reads your image, almost literally, so if you write on the image, it reads the text. This is how Higgsfield AI 🧩 has capitalized on the tech: "Write on the image" and give it direction, right? Totally true, but you don't need Higgi to write on your image. Nano Banana will understand your direction regardless of where you write on your image. On one hand, Higgi is really smart, because they're hranessing the tech in a unique way, but the whole "Higgsfield's Banana Placement" is a bit of a misnomer. It's more of a "Banana Placement" and Higgi is just giving you a sort of basic Photoshop-type tool to work with (again, pretty smart), but the real tech is the Banana. 🍌 This is how I head swapped heads in Runway, but Nano Banana maintains the aesthetic qualities of your image almost perfectly, whereas Runway Reference spits out a very Gen-4 looking image. I like using Nano in Freepik (now Magnific), mainly because it's fast and I can get 4 gens at a time, and you need to gen a dozen times of so before you get a winner (most of the time). I was pumped when I saw Freepik introduce the @ reference feature, just like Runway has, but it doesn't seem to work for head swapping. My guess is because that's not really how Nano Banana tech works... ideally. Marco is the person I saw using this "A" and "B" method, back when Nano was on LM Arena, and man-oh-man, it just works... like a charm. You need experiment with how much of the face you blot out, and the angle and facial expression of your new head if you want the blend to be perfect. All of the results in this video are 100% Nano Banana. I did not do any Photoshop work to the images after the fact. I really hope this helps. Let me know if you have any questions. I'm happy to help. And I'll keep posting videos like this if you guys find them useful. Let me know! And if you want more serious, one-on-one AI consultation you can throw something on the books here:

Jordan Daniel Chesney

62,235 Aufrufe • vor 1 Jahr

An anonymous image model appeared on Arena on Aug 12, 2025 and quickly became the most-voted model in Arena's history. The codename: Nano Banana. It was later revealed to be built on Google Gemini and publicly released on Aug 26, 2025. We sat down with Lead Engineer Yue to break down why it stood out. Watch the full video on YouTube, link in thread 👇

An anonymous image model appeared on Arena on Aug 12, 2025 and quickly became the most-voted model in Arena's history. The codename: Nano Banana. It was later revealed to be built on Google Gemini and publicly released on Aug 26, 2025. We sat down with Lead Engineer Yue to break down why it stood out. Watch the full video on YouTube, link in thread 👇

Arena.ai

44,172 Aufrufe • vor 7 Monaten

Ideogram CEO Mohammad Norouzi says image models need taste: "We think taste is extremely important and we really want our models to have taste, and it's very hard to explain it." "One element of taste is going outside of the normal a little bit and not conforming to the average opinion, which is a little against being on top of the leaderboard." "Ultimately, we work with all the arenas... but we care about our own internal evaluation." "AI is not very good at doing the actual taste evaluation yet, so we work with designers... to really push on the taste." Mohammad Norouzi with Yoko and Justine Moore

Ideogram CEO Mohammad Norouzi says image models need taste: "We think taste is extremely important and we really want our models to have taste, and it's very hard to explain it." "One element of taste is going outside of the normal a little bit and not conforming to the average opinion, which is a little against being on top of the leaderboard." "Ultimately, we work with all the arenas... but we care about our own internal evaluation." "AI is not very good at doing the actual taste evaluation yet, so we work with designers... to really push on the taste." Mohammad Norouzi with Yoko and Justine Moore

a16z

19,520 Aufrufe • vor 3 Monaten

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 Aufrufe • vor 5 Monaten

Claude Design is incredible It allows ANYONE to design BEAUTIFUL apps and websites But here's the thing, when combined with ChatGPT's new image model it's 10x better In this video I cover how to use Claude Design and ChatGPT Image 2 together to design BEAUTIFUL apps:

Claude Design is incredible It allows ANYONE to design BEAUTIFUL apps and websites But here's the thing, when combined with ChatGPT's new image model it's 10x better In this video I cover how to use Claude Design and ChatGPT Image 2 together to design BEAUTIFUL apps:

Alex Finn

210,832 Aufrufe • vor 5 Monaten

You know that super annoying overlay texture pattern you get on AI images, particularly with Nano Banana Pro and GPT 2.0? Here's how to get rid of it. Toss your image into Magnific as a reference, select the Nano Banana Pro model, and prompt: Recreate this image exactly, detail for detail and restore fidelity, making it high resolution, and crisp, and clear. Exactly maintain the original colors. Credit to David LaChance, Jr. for figuring this out. Hope this helps.

You know that super annoying overlay texture pattern you get on AI images, particularly with Nano Banana Pro and GPT 2.0? Here's how to get rid of it. Toss your image into Magnific as a reference, select the Nano Banana Pro model, and prompt: Recreate this image exactly, detail for detail and restore fidelity, making it high resolution, and crisp, and clear. Exactly maintain the original colors. Credit to David LaChance, Jr. for figuring this out. Hope this helps.

Jordan Daniel Chesney

31,785 Aufrufe • vor 4 Monaten

Another use case with Nano Banana Pro (Video is fully narrated so don't forget to turn on the sound 🔊) Image to 3D Model For 3D Printing 1 - Generate an image of a vinyl toy character. I generated a character called Peelbert. 2 - Generate multiple outfits for Peelbert while retaining consistency. Nano Banana Pro's consistency and understanding of outfit changes is superb. 3 - Use Hunyuan 3.0 to do image to 3D model 4 - Save as STL and 3D Print. Nano Banana Pro to the real world 👍

Another use case with Nano Banana Pro (Video is fully narrated so don't forget to turn on the sound 🔊) Image to 3D Model For 3D Printing 1 - Generate an image of a vinyl toy character. I generated a character called Peelbert. 2 - Generate multiple outfits for Peelbert while retaining consistency. Nano Banana Pro's consistency and understanding of outfit changes is superb. 3 - Use Hunyuan 3.0 to do image to 3D model 4 - Save as STL and 3D Print. Nano Banana Pro to the real world 👍

Travis Davids

44,133 Aufrufe • vor 10 Monaten

The AI containment debate may already be over. david friedberg argument is that powerful AI is no longer controlled by a handful of American companies running enormous data centers. Open weight models are becoming capable and efficient enough to download, modify, and run on consumer hardware, making the technology nearly impossible to contain once released. The recent launch cycle shows how quickly this is happening. DeepSeek released a faster and cheaper model, Alibaba published downloadable weights for Qwen Image 2.1, and PrismML compressed a 27 billion parameter Qwen model into just 5.9 gigabytes. PrismML says its compressed model retained 98.2% of the original model’s benchmark performance while becoming small enough to run on a laptop or consumer GPU. At the same time, closed model companies continued releasing more capable and affordable systems. Anthropic’s Opus 5.5 reportedly matched its more expensive flagship while costing approximately 40% less to run than its predecessor. Stanford found that the cost of running a model with GPT 3.5 level performance fell more than 280 fold in roughly 18 months. It also found that the performance gap between leading open-weight and closed models narrowed from 8% to 1.7% on some benchmarks in one year. That is the real meaning of Friedberg’s argument. Governments can regulate large data centers, chip exports, and commercial AI providers but they cannot easily remove models that have already spread across the internet and onto personal computers. The debate must therefore shift from whether powerful AI should exist to how it should be used and who becomes responsible when it causes harm.

The AI containment debate may already be over. david friedberg argument is that powerful AI is no longer controlled by a handful of American companies running enormous data centers. Open weight models are becoming capable and efficient enough to download, modify, and run on consumer hardware, making the technology nearly impossible to contain once released. The recent launch cycle shows how quickly this is happening. DeepSeek released a faster and cheaper model, Alibaba published downloadable weights for Qwen Image 2.1, and PrismML compressed a 27 billion parameter Qwen model into just 5.9 gigabytes. PrismML says its compressed model retained 98.2% of the original model’s benchmark performance while becoming small enough to run on a laptop or consumer GPU. At the same time, closed model companies continued releasing more capable and affordable systems. Anthropic’s Opus 5.5 reportedly matched its more expensive flagship while costing approximately 40% less to run than its predecessor. Stanford found that the cost of running a model with GPT 3.5 level performance fell more than 280 fold in roughly 18 months. It also found that the performance gap between leading open-weight and closed models narrowed from 8% to 1.7% on some benchmarks in one year. That is the real meaning of Friedberg’s argument. Governments can regulate large data centers, chip exports, and commercial AI providers but they cannot easily remove models that have already spread across the internet and onto personal computers. The debate must therefore shift from whether powerful AI should exist to how it should be used and who becomes responsible when it causes harm.

Milk Road AI

37,497 Aufrufe • vor 14 Tagen

Just released my new /lesson-generator skill. Use it with your agent to learn anything: - generate lessons/courses on any topic - include nano-banana images with my /image-generator skill - present the course as an HTML artifact And it's also available to use in our academy.

Just released my new /lesson-generator skill. Use it with your agent to learn anything: - generate lessons/courses on any topic - include nano-banana images with my /image-generator skill - present the course as an HTML artifact And it's also available to use in our academy.

elvis

58,698 Aufrufe • vor 4 Monaten

Announcing the Open Model Series: a new series on open source AI models, with merve of Hugging Face. Hugging Face is the open model hub: it hosts model weights, datasets, evals, & demo apps, and maintains the open-source libraries (like transformers) used to run and train them. I think of it like GitHub, but for AI models. You can download open models and run them on your own machines. In this series we'll cover what open source and open weight models are, how they work, how to run them yourself, and why they're important. By the way - this video is edited entirely with Claude! I can make a tutorial on how I did it. If there's a question you want answered about open models, leave it in the comments. We will read them all. Episode 1 is out soon.

Announcing the Open Model Series: a new series on open source AI models, with merve of Hugging Face. Hugging Face is the open model hub: it hosts model weights, datasets, evals, & demo apps, and maintains the open-source libraries (like transformers) used to run and train them. I think of it like GitHub, but for AI models. You can download open models and run them on your own machines. In this series we'll cover what open source and open weight models are, how they work, how to run them yourself, and why they're important. By the way - this video is edited entirely with Claude! I can make a tutorial on how I did it. If there's a question you want answered about open models, leave it in the comments. We will read them all. Episode 1 is out soon.

Harper Carroll

30,392 Aufrufe • vor 2 Monaten

A conversation with some of the research folks behind nano-banana 🍌 (aka Gemini 2.5 Flash Image) on how we got here, what it took to build this model, and where we go next! So much fun to hang with: Kaushik Shivakumar Robert Riachi Mostafa Dehghani Nicole Brichtova

A conversation with some of the research folks behind nano-banana 🍌 (aka Gemini 2.5 Flash Image) on how we got here, what it took to build this model, and where we go next! So much fun to hang with: Kaushik Shivakumar Robert Riachi Mostafa Dehghani Nicole Brichtova

Logan Kilpatrick

229,508 Aufrufe • vor 1 Jahr

The open-source & open-weight frontier is 7 months behind the closed-model frontier. Let’s talk about it. Check out last week’s episode for the reasons why you might want to consider open-source & open-weight models. Welcome to the fourth episode of the Open Model Series with merve, Hugging Face AI/ML engineer & open-sourceress! We have been discussing open-source & open-weight AI: what it is, how it works, and how you can run them on your own compute. Please leave all your questions about open-source & open-weight AI in the comments! This is a super important topic that is novel to most people, and it can be challenging to grasp - so rest assured your questions are shared with many others!

The open-source & open-weight frontier is 7 months behind the closed-model frontier. Let’s talk about it. Check out last week’s episode for the reasons why you might want to consider open-source & open-weight models. Welcome to the fourth episode of the Open Model Series with merve, Hugging Face AI/ML engineer & open-sourceress! We have been discussing open-source & open-weight AI: what it is, how it works, and how you can run them on your own compute. Please leave all your questions about open-source & open-weight AI in the comments! This is a super important topic that is novel to most people, and it can be challenging to grasp - so rest assured your questions are shared with many others!

Harper Carroll

17,279 Aufrufe • vor 1 Monat

It's official: Qwen3.8-27B just scored 52 on the Artificial Analysis Intelligence Index. We now have an open-weight model that matches GPT-5.6 Luna (max) AND can run locally... even in your browser with custom WebGPU kernels! What a time to be alive! 🤯

It's official: Qwen3.8-27B just scored 52 on the Artificial Analysis Intelligence Index. We now have an open-weight model that matches GPT-5.6 Luna (max) AND can run locally... even in your browser with custom WebGPU kernels! What a time to be alive! 🤯

Xenova

188,212 Aufrufe • vor 1 Monat

GPT-Image-2 was just released... It's the best image model (By a wide margin) Heres how to use GPT-Image-2 in ChatGPT, OpenAI Playground and of Course - Codex. TIMESTAMPS 00:00 Intro 01:27 Initial Tests of GPT-Image-2 02:24 It can GENERATE working BARCODES? 03:40 11 Edits one Prompt 06:40 Creating Cartoons 07:40 Overlay Explanations 08:50 How to Get Started 10:51 IPhone Mockup Images (Amazing) 15:43 Using GPT-Image in OpenAI Playground 16:11 Generate images in 4k 17:44 The FIRST limitation... Its bad at counting 18:26 Using GPT-Image in Codex (Agentic Image Gen)

GPT-Image-2 was just released... It's the best image model (By a wide margin) Heres how to use GPT-Image-2 in ChatGPT, OpenAI Playground and of Course - Codex. TIMESTAMPS 00:00 Intro 01:27 Initial Tests of GPT-Image-2 02:24 It can GENERATE working BARCODES? 03:40 11 Edits one Prompt 06:40 Creating Cartoons 07:40 Overlay Explanations 08:50 How to Get Started 10:51 IPhone Mockup Images (Amazing) 15:43 Using GPT-Image in OpenAI Playground 16:11 Generate images in 4k 17:44 The FIRST limitation... Its bad at counting 18:26 Using GPT-Image in Codex (Agentic Image Gen)

Riley Brown

35,856 Aufrufe • vor 5 Monaten

Woow Nvidia has just released a 2.6B open-source world model 🔥 You can turn a single image, text prompt and trajectory into controllable worlds... And on a single GPU! - Code available on GitHub - Paper as well on arxiv You can use it for many things like embodied AI and robotics research, simulations, etc. Because it can run on a single GPU (like an RTX 5090 or H100) it makes world models accessible to basically everyone!

Woow Nvidia has just released a 2.6B open-source world model 🔥 You can turn a single image, text prompt and trajectory into controllable worlds... And on a single GPU! - Code available on GitHub - Paper as well on arxiv You can use it for many things like embodied AI and robotics research, simulations, etc. Because it can run on a single GPU (like an RTX 5090 or H100) it makes world models accessible to basically everyone!

Paul Couvert

174,447 Aufrufe • vor 4 Monaten