Developers are increasingly treating AI image generation as 'Prompt-as-Code,' using structured repositories like freestylefly/awesome-gpt-image-2 to parameterize visual assets for production workflows…
Orelon, an AI video generator, offers cinematic video creation with features such as Seedance 2.5, Kling 3.0, and GPT Image 2, enabling users to generate videos from prompts or reference images with v…
A developer has built a visual canvas tool that lets users branch AI conversations into nodes on an infinite canvas, using React Flow, GPT Image 2, and Gemini 3.5 Flash Lite. The tool aims to overcome…
Microsoft's MAI-Image-2.5-Pro debuted at number one on Artificial Analysis's Image Editing Leaderboard, surpassing Google, OpenAI's GPT Image 2, and Microsoft's own MAI-Image-2.5. The model, launched …
Adobe launched Firefly Image 4, Image 4 Ultra, and Image 5 Preview, alongside partner models GPT Image 2, Gemini 3 with Nano Banana, and Flux 1.1 Pro, in its Firefly AI image generator, which is integ…
Adobe Firefly's AI image generator now offers multiple models—Adobe's Firefly Image 4, Image 4 Ultra, and Image 5 Preview, plus partner models GPT Image 2, Gemini 3 with Nano Banana, and Flux 1.1 Pro—…
In a 25-round AI telephone experiment, the word "chicken" disappeared from descriptions on round 10, and by round 23 the image had transformed into a wild bird egg resembling a guillemot, according to…
OpenAI's GPT Image 2 leads all seven evaluation categories on Arena.ai's new community-voted image editing leaderboard, with an Elo score of 1463 based on more than 165,000 votes and a 242-point margi…
Flux 3, an advanced AI visual intelligence model, enables users to generate realistic images, videos, and creative content through multimodal workflows and simple prompts. The platform offers a premiu…
Alibaba's Qwen team released Qwen-Image-3.0 on July 21, prioritizing utility over aesthetics by enabling single-pass generation of complex layouts like newspapers and infographics from up to 4,500 tok…
ByteDance's Seeddream 5.0 Pro accepts up to 10 reference images and generates infographics and UI mockups, while OpenAI's GPT Image 2 excels at natural language instruction fidelity and text rendering…
A developer outlines a structured workflow for AI image generation that treats prompts as reusable specifications rather than one-off sentences. The approach uses prompt contracts, reference images wi…
A new AI photo editor called Nano Banana & GPT Image 2 model allows users to perform professional-grade image editing using text prompts, with features like one-shot generation, lightning-fast process…
TikTok Shop generated $64.3 billion in global sales in 2025, nearly doubling year-over-year, and sellers can open a store with zero followers. A complete AI ad—virtual model, scripted dialogue, 10-sec…
Meta released Muse Image, a free autoregressive image generation model, competing with OpenAI's GPT Image 2. Both models use step-by-step reasoning to improve text rendering and prompt adherence over …
Meta's Superintelligence Labs released Muse Image, an image generation model that uses tools like code execution and web search to refine results. The model's @-mention feature allows users to generat…
Meta Superintelligence Labs launched Muse Image on July 7, the first image generator that autonomously uses tools like web search and code execution at inference time, with self-refinement emerging fr…
Meta's Muse Image model rose to second place on Arena.ai's Text-to-Image Arena leaderboard with an Elo score of 1280, trailing only OpenAI's GPT Image 2 at 1385. The model, announced by Meta Superinte…
Meta launched Muse Image, its first image model from Meta Superintelligence Labs, and a comparison of its text-to-image prompts against Nano Banana Pro, GPT Image 2, and FLUX 2 Pro shows that while Mu…
XAI's Grok Imagine image generation model, now available on Puter.js, claims to be 15-20x faster than competitors. Puter.js tested both standard and quality tiers against GPT Image 2 and Nano Banana m…