46 posts on this topic
Gemini Omni 1.2 Flash, Google's next-generation multimodal video generation and editing model, is shifting the balance in AI-powered media production with native video length extended to 15 seconds, chat-based editing capabilities and aggressive pricing that drops to $0.07 per second.
The latest comprehensive analyses of Steam data show that generative AI usage in new games released on the platform has jumped from 1.7 percent to 49.9 percent. Used by developers mostly for visual design, translation and store page assets, the technology is also fueling debates about mass production in the indie game ecosystem.
At a time when the digital advertising world is filling up with automatically generated content criticized as 'AI slop', Prada worked with legendary Disney animator John Pomeroy to create an enchanting holiday campaign drawn by hand frame by frame.
Google has added a persistent brand identity feature to Gemini for small businesses and marketing teams. Powered by the Nano Banana 2.1 image engine, the new system removes the need to upload a style guide in every chat session and produces designs fully aligned with the corporate look.
Runway, a pioneer in AI video and media generation, has launched Runway App Studio, a platform that lets users build shareable creative apps with one click using natural language prompts or by converting existing agent workflows.
Google announced Nano Banana 2.1, a model based on Gemini 3.6 Flash. With costs cut in half, improved text rendering and 4K support, it sets a new standard in AI image generation.
Ready-made codes to paste into Gemini for a biometric ID photo, a LinkedIn portrait and a simple identity photo. Just replace the square brackets with your own description.
Realistic photo prompts to paste into ChatGPT. In each code, subject, lighting, lens and framing stand apart. That way the result feels like a shot someone took, not a poster.
Ready-made codes for generating portraits, products and outdoor scenes with Nano Banana. In each example, material, lighting and framing are written separately. That way the result doesn't end up looking like a flat filter.
Ready-made codes for repairing a yellowed, scratched or black-and-white photo in Gemini. The goal isn't to turn the face into someone else but to make the existing photo legible.
Gemini prompts for testing a brand mark. First a text-free symbol, then one color. Don't ask for made-up letters. Draw the wordmark later in a vector tool.
Separate Gemini prompts for profile, cover and vertical story. Each prompt has a single subject and room to breathe. Add text later instead of baking it into the image.
Alongside ChatGPT Images 2.5, OpenAI announced the Sketch feature, which turns simple doodles into professional images, and two new API models for developers. Here are all the details.
If you are looking for ready-made prompts and templates to get the most out of Google Gemini's image generation, you are in the right place. In this guide, I list the best photo prompts and prompt examples you can copy and paste.
Escaping the artificial look and capturing the feel of 'a real photo' is not always easy in AI image generation. In this guide, I go step by step through how to produce ultra-realistic photos with Google Gemini and the Imagen 3 engine.
A detailed guide to creating the most lifelike human portraits with advanced image generation models like Flux AI and Midjourney v6, covering skin texture, pores, optical lens properties and professional lighting setups.
A prompt guide with the key keywords for producing professional product photos at zero cost for e-commerce sellers, digital advertisers and designers using Midjourney v6 and Flux AI.
A prompt guide to camera lenses, lighting angles and color grading for creating film scenes, cinematic portraits and epic fantasy landscapes with Midjourney v6 and Flux AI.
A prompt guide with the key keywords for producing realistic, flawless 3D interior designs for architects, interior designers and decor enthusiasts using Midjourney v6 and Flux AI.
A prompt guide with the key keywords for producing clean, professional logos that can be made transparent for startups, mobile apps and corporate identities using Midjourney v6.
Writing the right prompt is essential to get the most out of ChatGPT's image generation capabilities. Learn how to use lighting, lens, composition and atmosphere details.
Freepik’s rebrand as Magnific is not just a name change; it is a bigger strategy in which the stock image, design tool and generative AI markets come together under one roof.
Drafted AI, a nine-month-old startup, cuts the home design process from minutes to seconds with AI-based automatic floor plan generation and 2D-to-3D conversion. The platform generated 50,000 layouts in 24 hours, raised $1.65 million and also targets professional architects with DXF/IFC export support. In this post we take a detailed look at the model, the workflow, its market position and its impact on the industry.
OpenAI introduced ChatGPT Images 2.0 and its API counterpart gpt-image-2. The model stands out for instruction fidelity, sharper small text and interface details, photorealistic textures, wide aspect ratio support and a ‘thinking model’ mode that researches and plans. In this post we summarize what the new features mean, who gets access to which feature and where the model still struggles.
Claude Design, Anthropic's new AI design platform, debuted as a research preview. Built on Opus 4.7's advanced visual reasoning, the tool tries to bring prototypes, mockups, presentations and team workflows under a single AI roof. We took a close look at what sets apart the platform, which is rolling out gradually to Pro, Max, Team and Enterprise subscribers.
Getting light, composition and camera language right in Gemini-based image generation: prompt structure, technical terms and re-generation strategies for near-realistic results, all in one guide.
ByteDance has integrated its next-generation AI video model Dreamina Seedance 2.0 into the popular video editing app CapCut. With realistic lighting, motion and audio synchronization, a new era begins in video production.
Luma AI has announced its new image generation model, Uni-1. Unlike diffusion models, Uni-1 works with a 'step-by-step thinking' architecture and outperforms ChatGPT and Gemini at understanding complex instructions and staying consistent.
Google's eagerly awaited next-generation image generation model, Nano Banana 2, is now officially available. A detailed look at this groundbreaking Gemini 3.1 Flash Image based model, its 4K support, character consistency and more.
Google added ready-made video templates to the Gemini platform. Running on Veo 3.1, the system lets users produce videos in different aesthetic styles without needing complex prompts. Daily generation limits per subscription plan and Lyria 3 music generation limits have also been clarified.
46 articles about AI Art, often together with AI, Google, Gemini. The newest one is "Google Introduces Gemini Omni 1.2 Flash: 15-Second AI Videos and a 30 Percent Price Cut".