Click any tag below to further narrow down your results
Links
This article highlights 13 popular trends using Google's Nano Banana image generation model throughout 2025. It showcases various creative prompts, from photo edits to complex infographics, demonstrating the model's versatility and user creativity.
This article details the capabilities and limitations of Gemini's image generation and editing tools. While it offers high precision and control for creating images and infographics, users should be aware of its challenges with detail accuracy, text generation, and potential misinformation. It emphasizes the importance of verifying generated content and highlights safety features for image outputs.
Figma launched Vectorize, an AI tool that converts raster images into editable vector graphics. This feature allows designers to easily refine and scale their designs without losing the original character of their sketches or textures. It integrates with existing Figma tools for a smoother workflow.
Alibaba's Qwen has introduced an AI model that separates images into editable layers, similar to Photoshop. Users can easily modify each layer—resize, reposition, or change colors—without impacting other parts of the image. The model supports splitting images into 3 or 8 layers and allows for further breakdown of layers.
Adobe unveiled Firefly 5, its latest image-generation model, which supports higher resolutions and improved human rendering. The model features prompt-based editing, allowing creators to make specific changes to generated images without starting over. Adobe is also expanding its offerings with third-party models and custom model options for creators.
OpenAI has released GPT Image 1.5, an AI model designed for image editing and generation. It improves text rendering and retains important image details during edits, making it more efficient for both developers and casual users. The model is accessible through ChatGPT, with lower API costs compared to its predecessor.
Figma has improved its Crop tool, making image editing faster and more intuitive. Users can now double-click to enter crop mode, and the tool automatically maintains aspect ratios. New features like preset ratios and a dedicated Crop toolbar streamline the editing process.
Qwen-Image-Layered is a model that breaks down images into multiple editable RGBA layers, allowing for precise manipulation of individual components. Users can perform tasks like recoloring, resizing, and repositioning without altering other layers. The model supports variable-layer decomposition and can recursively decompose layers.
Figma has launched three new AI tools for image editing: Erase object, Isolate object, and Expand image. These features allow designers to manipulate images directly within Figma, streamlining the editing process and enhancing workflow efficiency. The tools are integrated into a new image editing toolbar for easier access.
Pixelmator Pro, a leading image editing app for Mac, is now available on iPad, replacing the older Pixelmator Photo. The app features a touch-optimized interface and advanced editing tools, including machine learning capabilities. However, it's only compatible with newer iPad models and requires iPadOS 26 or later.
Magic Hour AI offers a platform with over 100 free tools for creating videos and images using AI. Users can access various features like video upscaling, image editing, and voice generation without needing a credit card to start. The service targets creators looking for easy and quick content generation.
Google launched Nano Banana Pro, an advanced image editing tool built on its Gemini 3 Pro AI model. The tool enhances capabilities for creating infographics and maintaining character consistency in images. It follows the success of the original Nano Banana, which gained popularity for transforming photos into 3D figurines.
Google has launched Nano Banana Pro, an advanced image generation and editing model that enhances visual content creation. It offers improved accuracy and context in visuals, supports multilingual text, and integrates real-time information for various applications. This tool is aimed at casual creators, professionals, and developers.
Remake Face AI offers an online tool for seamless face swapping in photos and videos, allowing users to create fun and creative transformations. With features like celebrity swaps, artistic filters, and gender transformations, the platform prioritizes privacy and provides high-resolution outputs for easy sharing. New users can register to receive free credits to start their image remaking journey.
Stability AI has launched its Image Services on Amazon Bedrock, offering professional-grade image editing tools as managed API services. These tools enable granular control for creative workflows, allowing enterprises to integrate sophisticated editing capabilities into their applications while leveraging AWS's secure and scalable infrastructure.
A novel photograph relighting method allows users to control various light sources with physical accuracy, integrating traditional and neural rendering techniques. By employing a self-supervised training approach, the system reconstructs scene illumination from real-world images, facilitating in-the-wild relighting applications akin to those in 3D computer graphics tools.
Qwen-Image, a 20B MMDiT image foundation model, offers advanced capabilities in complex text rendering and image editing, outperforming existing models in various benchmarks. Its strengths include high-fidelity text generation in both English and Chinese, consistent image editing, and versatility in artistic styles, making it a powerful tool for content creators. The model aims to lower barriers in visual content creation and foster community engagement in generative AI development.
Google Nano Banana, also known as Gemini 2.5 Flash Image, is a new image generation and editing model from Google that allows users to edit images using natural language prompts. The article outlines five techniques for image editing, including object removal, photo colorization, text addition to billboards, maintaining character consistency, and creating branding assets, demonstrating the model's capabilities and ease of use in various scenarios.
An online WebGL2 photo editor allows users to edit images locally in their browser without uploading to a server, ensuring 100% privacy. It offers various features including cropping, perspective correction, color adjustments, filters, and more, while supporting different file formats depending on the browser and platform used. Users can submit feature requests in the issues section for future enhancements.
The Nano Banana is a new image editing tool designed to provide users with a simple and efficient way to enhance their photos. It offers a variety of features that allow for quick adjustments and creative edits, making it suitable for both casual users and more serious photographers. The tool aims to streamline the editing process while still delivering professional-quality results.
Qwen-Image Edit, developed by Alibaba's Qwen Team, offers advanced AI-powered text-to-image editing capabilities that rival Adobe Photoshop. The model's dual-encoding mechanism allows for both semantic and appearance edits, enabling users to modify images with text inputs quickly and accurately. With support for bilingual text editing, it caters to a variety of creative and professional applications.
Figma is enhancing its platform by integrating Google's generative AI models, including Gemini 2.5 Flash and Imagen 4, to significantly speed up image generation and editing, achieving a 50% reduction in latency. The integration maintains enterprise governance with opt-out controls for AI content training and ensures image quality with built-in watermarking for provenance. This move aims to streamline design processes while adhering to organizational standards and expectations.
Gemini app users can now upload and edit images with new AI-powered features, allowing modifications such as changing backgrounds and replacing objects. This intuitive editing capability enhances user interaction by integrating text and images, while also ensuring all generated images include a digital watermark for authenticity. The rollout of these features will expand to users in over 45 languages and most countries in the coming weeks.
Goodfire has introduced Paint With Ember, a tool that enables users to generate and edit images by manipulating neural activations of AI models directly on a canvas. The tool utilizes insights from diffusion models, particularly the Stable Diffusion XL-Turbo, to provide a more intuitive interface for creative expression, while also open-sourcing the underlying SAE model for broader use and exploration.
Learn how to use Google's AI image editing model, Nano Banana, integrated into Google Gemini and Imogen, to effortlessly edit, blend, and enhance images. The article provides a step-by-step guide, showcases various use cases, and discusses the limitations of the model while highlighting its impressive capabilities for creative projects.
Flow-GRPO-Fast is a newly introduced accelerated variant of the Flow-GRPO model that enhances training efficiency by reducing the number of denoising steps required per trajectory. Recent updates include support for various models and reward mechanisms, as well as improvements in training parameters to optimize performance on tasks such as image editing and generation. The article outlines detailed instructions for setup, training, and model implementation across multiple environments.
Adobe has introduced new AI-powered image editing features in Photoshop that enhance user experience by automating complex tasks and improving efficiency. These updates aim to streamline workflows for both amateur and professional photographers. The features leverage advanced machine learning to deliver more intuitive tools for image manipulation.
Google has unveiled a new AI image model that enhances photo editing capabilities, allowing users to make smarter adjustments to their images. This innovative technology aims to simplify the editing process while improving the quality of the final output. The model reflects Google's ongoing commitment to integrating AI into creative tools, making sophisticated editing accessible to a wider audience.
Google DeepMind's new image editing model, Nano Banana, available in the Gemini app, allows users to creatively transform images with unprecedented control. Users can blend photos, change parts of images, and create unique characters or scenes, as showcased through various imaginative prompts. This update enhances the possibilities for personalized image creation and storytelling.
Adobe has integrated Google's Gemini 2.5 Flash Image into its Firefly and Adobe Express platforms, allowing creators enhanced capabilities in visual generation. To celebrate this launch, Adobe is offering unlimited generations for Firefly and Creative Cloud subscribers until September 1, while new users on the free plan can access up to 20 generations. Despite the advancements in image quality and editing control, Google acknowledges that the model has limitations, including potential inaccuracies in generated content.
Google has introduced the "nano banana" model, a significant advancement in AI image editing, now available in the Gemini app. This model enhances consistency in edits, allowing for creative modifications of images while retaining recognizable features of the original source. Users can experiment with styles and attire changes without losing the essence of the initial image.
Reve has launched a new image editing platform that emphasizes creative intent over technical proficiency, integrating various tools into one seamless user experience. The platform features advanced image creation and editing capabilities, a drag-and-drop editor, a creative assistant, and an API for third-party integration, all built on a revolutionary intermediate representation for visual information. This new architecture enhances precision, bridges language and vision, and allows users greater control over their creative processes.
OmniTools is a self-hosted web application that provides a range of online tools for tasks such as image and video editing, PDF manipulation, and data calculations, all processed client-side for privacy. With a lightweight Docker image and a focus on user contributions, it aims to simplify everyday tasks while expanding its toolset.
Figma has introduced new AI tools that enhance its image editing capabilities, allowing users to generate images and select models more efficiently. These tools aim to streamline the design process and improve user experience by integrating advanced AI functionalities directly into the platform.