The Image Generation Model That's Hotter Than Nano Banana Has Leaked, Screenshots Are No Longer Evidence | Includes Prompts

marsbitPublicado em 2026-04-19Última atualização em 2026-04-19

Resumo

A new AI image generation model, widely referred to as "GPT Image 2," has been leaked and is demonstrating significant advancements over predecessors like DALL-E 3 and even Google's Nano Banana Pro. It excels in four key areas: text rendering, prompt adherence, photorealism, and world knowledge. The model can generate highly accurate text in multiple languages, including complex Chinese characters, making it capable of producing convincing fake documents, UI screenshots, and product labels. This capability also raises concerns about the reliability of using screenshots as evidence. The model is currently in A/B testing, with a full release expected around May 2026 when DALL-E services are officially retired. It is accessible for testing on the LM Arena platform. The article includes several prompt templates optimized for the model, such as generating realistic app screenshots, product photos with detailed labels, and street scenes with accurate signage. This advancement is reshaping creative workflows but also accelerating the displacement of some traditional design roles.

Is your impression of text-to-image still stuck on Nano Banana?

But kid, times have changed again.

@johnAGI168 https://x.com/johnAGI168/status/2044781168151724067

@0115hippo https://x.com/0115hippo/status/2044722124611539160

In early April, three anonymous image models, codenamed maskingtape-alpha, packingtape-alpha, and gaffertape-alpha, appeared on the LM Arena evaluation platform. They disappeared a few hours later.

OpenAI has not officially announced this model yet, but based on the metadata returned by the API and user-side testing records, it has already gained a widely accepted name: GPT Image 2.

Screenshots Can No Longer Be Used as Evidence

Over the past few years, one of the most obvious weaknesses of AI image generation models has been text within images. In the DALL-E 3 era, if you asked it to write "Hello" in an image, it might output "Hellp" or even "Hl10", with letters tilting drunkenly. GPT Image 1 improved a lot, handling simple English labels. By GPT Image 1.5, its accuracy in rendering English text was close to 95%, but it still had significant flaws with non-Latin scripts like Chinese, Japanese, and Korean.

But the leaked sample images from GPT Image 2 have changed this impression.

@MrLarus https://x.com/MrLarus/status/2044824800909054181

@akokoi1 https://x.com/akokoi1/status/2044789531615056175

The text in the images is exactly what it should be. Chinese characters are clear, with accurate glyphs and complete strokes. Someone tested generating an ID card-style image, where the name, address, and ID number were all rendered correctly, with neat formatting, looking at first glance like a photo of a real document.

This is good news. The improvement in text rendering means generating infographics, posters, product packaging, and complex charts becomes more reliable.

But there's always another side to the coin. A model that can generate photo-realistic ID-style images and precisely render UI screenshots naturally makes "screenshots can be used as evidence" increasingly questionable.

By comparison, this is also a core difference between the GPT Image series and other models. Midjourney still has no progress in text rendering, and the Stable Diffusion series also has this old problem. According to the leaked Arena test results, GPT Image 2 surpassed Midjourney in four dimensions: text rendering, instruction following, photorealism, and world knowledge. Midjourney's advantages are mainly retained in artistic style and aesthetic control.

Does It Really Know What the World Looks Like?

A tester asked the model to generate a hypothetical GPT-8 product pricing page. The resulting image had a layout that was indeed in the style of the OpenAI website, with button placement and font choices resembling those from a real interface, and the hierarchical logic of the price table was correct.

GPT Image 2 can generate images extremely similar to real software interfaces, including browser windows, mobile app interfaces, and data visualization charts, with a level of fidelity unmatched by the previous generation.

@johnAGI168 https://x.com/johnAGI168/status/2044781168151724067

@levelsio https://x.com/levelsio/status/2040333489476681758

This will lead to some very interesting practical uses. When designers are creating product prototypes, they don't need to open Figma first and draw a bunch of wireframes; they can directly describe the desired interface in text, and the output is a reference image that can be used for team discussions. When creating investor decks, they can show a "product screenshot" without waiting for an engineer to write code. When writing documentation, example interface images for illustration can be generated directly, without having to think about where to find screenshots for a blank page.

@marmaduke091 https://x.com/marmaduke091/status/2040338311873515597

Image Generation Is No Longer Just "Image Generation"

OpenAI has already announced that DALL-E 2 and DALL-E 3 will officially cease service on May 12, 2026. Azure OpenAI's DALL-E 3 was retired early in February.

DALL-E was the first place many people encountered AI image generation, from those blurry early works to today, in just a few short years.

Meanwhile, Google, which had just established its industry position with Nano Banana Pro in early 2026, might feel the pressure. Early test reports indicate that GPT Image 2 simultaneously surpasses Nano Banana Pro in three dimensions: realism, text rendering, and world knowledge. This kind of triple win is not common.

For creators, the feeling is complex. Illustrators, graphic designers, and photographers are not facing this topic for the first time. Since the release of GPT Image 1, the number of freelance graphic design positions has decreased by about 18%. AI has indeed replaced the decision to "hire someone to do this" in certain scenarios, but it is also creating new ways of working, allowing one person to do more.

The evolution speed of image generation models no longer leaves much time for adaptation. It was only a few months from GPT Image 1's launch to version 1.5. And from 1.5 to 2, it's only been about half a year. Each generation solves the core shortcomings of the previous one while opening up new possibilities.

GPT Image 2 is currently still in the A/B testing phase, with some ChatGPT users randomly gaining access. The official release window is widely predicted to be around May, coinciding with the retirement of DALL-E. If you want to experience it early, you can currently try your luck on the LM Arena evaluation platform.

Test Address: https://arena.ai

Based on community feedback and the known strengths of this model, the following prompt templates can maximize your chances of success:

UI/Screenshot Prompt: A photorealistic screenshot of a mobile banking app, clearly showing transaction history with dates, amounts, and merchant names legible. iPhone 16 screen, natural hand holding the phone, coffee shop background.

Product Label Prompt: A photographic product photo of a craft beer bottle, with clear label details showing the brewery name "Oakridge Brewing Co.", alcohol content 6.8%, a mountain logo, and an ingredient list. Studio lighting, white background.

Signage Prompt: A street scene photo of a Tokyo alley at night, showing multiple neon signs in both Japanese and English, including a ramen shop sign reading "Ichiban Ramen — Est. 1987", a karaoke bar sign, and various glowing advertisements. Wet, reflective pavement with light reflections.

Interface/World Knowledge Prompt: A photorealistic YouTube video screenshot showing a video titled "How to Assemble a Computer in 2026" with 2.3 million views, featuring realistic comments, sidebar video recommendations, and channel info. Desktop browser view.

Widescreen Trigger Prompt: A cinematic widescreen photo of an IKEA store exterior at dusk, showing the glowing IKEA sign, a parking lot with realistic cars, and shoppers entering and leaving. Golden hour lighting, 16:9 format.

Unattributed image sources and references: https://miraflow.ai/blog/how-to-use-duct-tape-ai-model-arena-gpt-image-2-guide

This article is from the WeChat public account "APPSO", author: Discovering Tomorrow's Products

Perguntas relacionadas

QWhat is the name of the leaked image generation model mentioned in the article, and what is its significance?

AThe leaked model is referred to as GPT Image 2. Its significance lies in its dramatic improvement in text rendering accuracy, especially for non-Latin scripts like Chinese, and its ability to generate highly realistic images, including convincing UI screenshots and document-style images, which challenges the reliability of screenshots as evidence.

QHow does GPT Image 2's performance compare to other models like Midjourney and Google's Nano Banana Pro?

AAccording to the article, GPT Image 2 outperforms Midjourney in text rendering, prompt following, photorealism, and world knowledge, with Midjourney retaining an advantage mainly in artistic style and aesthetic control. It also reportedly surpasses Google's Nano Banana Pro in realism, text rendering, and world knowledge.

QWhat are some of the potential practical applications of GPT Image 2's capabilities?

APotential applications include generating product prototypes and UI mockups for designers, creating realistic 'screenshots' for investor decks without coding, producing example interface images for documentation, and generating accurate product labels, packaging, and information graphics.

QWhat major change is OpenAI making to its image generation services in relation to this new model?

AOpenAI has announced that DALL-E 2 and DALL-E 3 will officially stop service on May 12, 2026, with Azure's DALL-E 3 having already been retired in February. This suggests a transition to the new GPT Image model series.

QWhere can users currently try to access or test the GPT Image 2 model, and what is a recommended strategy for getting good results?

AThe model is currently in A/B testing, with some ChatGPT users randomly gaining access. Users can also try their luck on the LM Arena评测平台 (arena.ai). The article recommends using specific, detailed prompt templates focused on UI/screenshots, product labels, signage, interface/world knowledge, and widescreen formats to maximize success.

Leituras Relacionadas

Wang Chuan: When the neighbor Lao Wang earned thirty times from investing in memory storage stocks, how can you still avoid anxiety (6) - The trap of homogeneous products

The article, "Wang Chuan: How to Remain Unanxious After Neighbor Lao Wang's Thirty-Fold Gain on Storage Stocks (Part 6) - The Trap of Commoditized Goods," analyzes the cyclical and perilous nature of the data storage industry through historical and current case studies. It begins with the example of Iomega, whose Zip drives led to a stock surge of over 160x in the mid-1990s before collapsing over 97% from its peak due to competition from cheaper CD-R technology. This pattern is characteristic of storage, where products like DRAM are highly commoditized, leading to extreme price volatility. The sector has seen prices crash over 80% multiple times, with companies often facing bankruptcy. The core dynamic is "elastic demand facing heavy-asset, long-cycle, rigid supply." High prices attract new capacity, but the long lead time means supply eventually overshoots, causing sharp price corrections. The current AI-driven boom, exemplified by surging demand for High-Bandwidth Memory (HBM), has led to skyrocketing prices and profit margins for companies like SanDisk and Micron, despite relatively flat production volumes. However, the author warns this high-margin environment is self-defeating. The high profits are already triggering massive new capacity investments (hundreds of billions starting 2026), with supply expected to ramp up by late 2027. When supply catches up, total revenue and profits may fall even as more units are sold. Long-term supply agreements offer little protection, as buyers can find ways to renegotiate if market prices drop, similar to fragile political treaties. Key risks include economic downturns, cuts in AI spending, faster-than-expected capacity expansion (especially from Chinese firms), and innovations in chip/algorithm design that reduce memory needs. A critical trap is that at the cycle's peak, storage stocks often appear cheap with low P/E ratios, luring value investors just before an impending downturn where profits evaporate. The conclusion cautions that for commoditized goods like storage, high margins inevitably destroy themselves, and the current asymmetry favors downside risk over further upside. The neighbor's dream of easy wealth from storage stocks is portrayed as a precarious illusion.

链捕手Há 17m

Wang Chuan: When the neighbor Lao Wang earned thirty times from investing in memory storage stocks, how can you still avoid anxiety (6) - The trap of homogeneous products

链捕手Há 17m

AI PCs Are Here, Going Toe-to-Toe with 120B Models Locally! NVIDIA Redefines the "Personal AI Computer" Foundation with RTX Spark

NVIDIA has redefined the "AI PC" standard with the launch of the RTX Spark super chip at GTC 2026. Boasting 1 petaflop (1000 TOPS) of AI performance, it dwarfs the 45-50 TOPS NPUs in current AI PCs. The SoC features a Blackwell GPU, a 20-core Arm CPU co-designed with MediaTek, and crucially, up to 128GB of unified memory shared between CPU and GPU. This architectural shift enables local execution of 120-billion-parameter large language models with million-token context windows, a massive leap from the 9B-40B models typical on current consumer hardware. Beyond AI, use cases include 12K video editing and high-fps ray-traced gaming. Key to enterprise adoption is a security collaboration with Microsoft. Windows security is upgraded, and NVIDIA's OpenShell sandbox runtime is integrated to safely contain AI agent actions. Major software support comes from Adobe, which announced a deep,底层-level rewrite of Photoshop and Premiere to leverage the unified memory for up to 2x performance gains. Six OEMs, including Dell, HP, Lenovo, and Microsoft Surface, will release RTX Spark-based轻薄本 and compact desktops this fall. However, questions remain about real-world performance,功耗, thermal management in laptops, pricing, and the actual impact of the OpenShell sandbox. The RTX Spark represents a fundamental power shift in the PC industry, moving from an x86 CPU-centric model to a GPU-centric SoC platform, but its ultimate success hinges on the upcoming product rollouts and ecosystem validation.

marsbitHá 30m

AI PCs Are Here, Going Toe-to-Toe with 120B Models Locally! NVIDIA Redefines the "Personal AI Computer" Foundation with RTX Spark

marsbitHá 30m

Jensen Huang: Vera Rubin Full Mass Production, AI Agent a Key Focus, Challenging Intel to Target the Next-Generation AI PC Gateway

NVIDIA CEO Jensen Huang delivered the keynote speech at GTC Taipei 2026, announcing several major product launches and strategic directions. The company's Vera Rubin architecture is now in full-scale production, with OpenAI, Anthropic, and SpaceX among the first customers. NVIDIA highlighted AI Agent as a key future focus, introducing the Vera CPU designed for AI agents and the Vera BlueField-4 STX for secure, chip-level AI storage processing. A significant move involves challenging Intel in the PC market. NVIDIA, in collaboration with MediaTek, is developing the RTX SPARK PC chip (manufactured by TSMC) for Windows systems, set to launch this fall for laptops and desktops. This signals NVIDIA's push into the next-generation AI PC arena, aiming to provide a vertically integrated core computing platform for the entire Windows ecosystem, similar to Apple's approach. Other announcements include the new Nemotron 3 Ultra AI model and the NVIDIA DSX platform, described as a complete "playbook" for building AI factories, allowing performance simulation and validation before physical deployment. In automotive, the DRIVE Hyperion platform was positioned as a global robotaxi platform, with major Chinese automakers like BYD, Geely, Zeekr, Xiaomi, and Pony.ai already adopting or developing autonomous driving solutions based on it. The Alpamayo 2 super open inference model for robotaxis was also introduced. For robotics, NVIDIA unveiled the Isaac GR00T humanoid robot reference platform for academic research and a large open-source agent tools and skills suite for Physical AI. The company plans to collaborate with global humanoid robot manufacturers, including China's Unitree, whose H2 Plus robot served as the reference hardware for the GR00T platform demonstration.

marsbitHá 58m

Jensen Huang: Vera Rubin Full Mass Production, AI Agent a Key Focus, Challenging Intel to Target the Next-Generation AI PC Gateway

marsbitHá 58m

Interview with Macro Master Raoul Pal: The Economic Singularity is Approaching, Don’t Get Off the Ride in the Next Four Years

Interview with macro expert Raoul Pal discusses the approaching "economic singularity," where AI-driven growth outpaces traditional economic systems. He explains the unprecedented scale of the AI race between the US and China, arguing capital will continue flooding this sector as neither side can afford to stop. Pal sees this as a catalyst for cryptocurrency, as AI agents will operate on-chain, creating an "infinite TAM" for crypto networks. He views the recent crypto downturn as a normal bull market correction, advocating for a long-term "buy and hold" strategy over trying to time the market. Key investments include Layer 1 smart contract platforms like Ethereum, Solana, and Sui, which he believes will capture most value due to their foundational role. He also sees potential in privacy coins like Zcash and a future resurgence for high-end NFTs as digital trophy assets. Pal emphasizes that while AI stocks are hot, crypto offers superior asymmetric returns. He outlines a bullish case for 2026-2027 based on institutional adoption, pro-regulation, increased global liquidity, and crypto's current undervaluation relative to assets like the Nasdaq. His core advice: accumulate crypto assets during dips and hold for the long term, as the shift towards a digital, AI-agent-driven economy is inevitable.

链捕手Há 1h

Interview with Macro Master Raoul Pal: The Economic Singularity is Approaching, Don’t Get Off the Ride in the Next Four Years

链捕手Há 1h

Running MoE on Mobile Phones? Meta Proposes MobileMoE, Speeding Up iPhone 16 Pro by 3.8x

Meta's MobileMoE, a mobile-optimized Mixture-of-Experts (MoE) language model architecture, enables efficient on-device large language model (LLM) inference for the first time on commercial smartphones. Designed for decoder-only Transformers, it replaces dense feed-forward layers with MoE layers. Key design choices include 8 experts with granularity g=8, top-4 routing, and a shared expert. The model undergoes a four-stage training process: pre-training, intermediate training, supervised fine-tuning, and quantization-aware training. Results show MobileMoE models, with similar memory footprint, achieve equal or higher average accuracy across 14 foundational benchmarks while using only 1/2 to 1/4 of the FLOPs compared to dense baselines. After INT4 quantization, they remain competitive. Notably, on an iPhone 16 Pro, MobileMoE-S demonstrates significant speedups: up to 3.8x faster in the prompt phase and 2.2-3.4x faster in per-token generation compared to a dense counterpart, with lower peak memory usage. While MobileMoE establishes a new Pareto frontier for on-device LLMs in accuracy-compute trade-offs, particularly excelling in code and math tasks, it currently lags behind models like Qwen3.5 2B in advanced instruction following and knowledge reasoning. Future work includes improving post-training techniques, exploring NPU deployment, and managing the runtime memory sensitivity of MoE models to varying inputs.

marsbitHá 1h

Running MoE on Mobile Phones? Meta Proposes MobileMoE, Speeding Up iPhone 16 Pro by 3.8x

marsbitHá 1h

Trading

Spot

Futuros

Artigos em Destaque

Como comprar BANANA

Bem-vindo à HTX.com!Tornámos a compra de Banana Gun (BANANA) simples e conveniente.Segue o nosso guia passo a passo para iniciar a tua jornada no mundo das criptos.Passo 1: cria a tua conta HTXUtiliza o teu e-mail ou número de telefone para te inscreveres numa conta gratuita na HTX.Desfruta de um processo de inscrição sem complicações e desbloqueia todas as funcionalidades.Obter a minha contaPasso 2: vai para Comprar Cripto e escolhe o teu método de pagamentoCartão de crédito/débito: usa o teu visa ou mastercard para comprar Banana Gun (BANANA) instantaneamente.Saldo: usa os fundos da tua conta HTX para transacionar sem problemas.Terceiros: adicionamos métodos de pagamento populares, como Google Pay e Apple Pay, para aumentar a conveniência.P2P: transaciona diretamente com outros utilizadores na HTX.Mercado de balcão (OTC): oferecemos serviços personalizados e taxas de câmbio competitivas para os traders.Passo 3: armazena teu Banana Gun (BANANA)Depois de comprar o teu Banana Gun (BANANA), armazena-o na tua conta HTX.Alternativamente, podes enviá-lo para outro lugar através de transferência blockchain ou usá-lo para transacionar outras criptomoedas.Passo 4: transaciona Banana Gun (BANANA)Transaciona facilmente Banana Gun (BANANA) no mercado à vista da HTX.Acede simplesmente à tua conta, seleciona o teu par de trading, executa as tuas transações e monitoriza em tempo real.Oferecemos uma experiência de fácil utilização tanto para principiantes como para traders experientes.

135 Visualizações TotaisPublicado em {updateTime}Atualizado em 2025.03.21

Discussões

Bem-vindo à Comunidade HTX. Aqui, pode manter-se informado sobre os mais recentes desenvolvimentos da plataforma e obter acesso a análises profissionais de mercado. As opiniões dos utilizadores sobre o preço de BANANA (BANANA) são apresentadas abaixo.