Google DeepMind explains in a new post how to use the improved image generation in Gemini to its full potential. Product Manager Naina Raisinghani shared specific prompting strategies to achieve better results with the updated model. The company recommends including six key elements in prompts: subject, composition, action, location, style, and editing instructions. Users should …
Google has released an updated AI model, Gemini 2.5 Flash Image, designed to provide users with more control over image generation and editing. The model, which was anonymously tested on the crowdsourced evaluation platform LMArena under the codename “nano-banana,” is now integrated into the consumer-facing Gemini app and available to developers through the Gemini API, …
Alibaba’s Qwen Team has released a new open-source AI model named Qwen-Image Edit that allows users to modify images using simple text instructions. The tool is capable of performing a wide range of complex editing tasks that challenge established software like Adobe Photoshop. According to an article by Carl Franzen for VentureBeat, users can upload …
Not long ago, generating an image with AI was mostly a technological novelty. It was a nice party trick with limited practical use. As of 2025, that has changed. AI image generation has evolved into a practical tool for marketing professionals. From unique visuals for social media campaigns to website assets and conceptual product shots: …
Google has released its Imagen 4 family of text-to-image models, making them generally available in the Gemini API and Google AI Studio. According to a post on the Google Developers blog, the release includes the new Imagen 4 Fast model, which is optimized for speed and high-volume tasks. This model is priced at $0.02 per …
Alibaba’s Qwen Team has released a new open source AI image generator called Qwen-Image. According to its developers, the model specializes in creating images with accurately rendered text in both English and Chinese, a common challenge for many AI systems. Writing for VentureBeat, journalist Carl Franzen notes this capability allows for creating content like posters, …
Krea AI has released an open-source version of its image generation model, designed to produce visuals with a distinct aesthetic and avoid the common look of AI-generated content. In their post authors Sangwu Lee and Erwann Millon detailed the philosophy and process behind their new model, FLUX.1 Krea. The model was developed in collaboration with …
Adobe is rolling out new generative AI features for Photoshop, including a tool called “Harmonize” that automatically blends added objects into images. According to a report by The Verge, the Harmonize feature adjusts an object’s color, lighting, and shadows to convincingly match the main photograph. The update also includes an AI tool for upscaling low-resolution …
AMD and Stability AI have launched a new version of the Stable Diffusion 3.0 Medium image generator. According to an article by Anton Shilov in Tom’s Hardware, this model runs locally on laptops equipped with AMD’s latest Ryzen AI processors. It allows users to create high-resolution images from text prompts offline, without an internet connection. …
The French artificial intelligence company Mistral has announced a significant update for its chatbot, Le Chat, introducing a range of new features aimed at enhancing productivity for both individual and enterprise users. The update brings Le Chat closer in capability to competing services from companies like OpenAI and Google. A key new feature is the …