What's New

You can now extract text from uploaded documents and images. The tool processes files and converts them into editable text, supporting multiple pages.

A new AI model for generating images has been added, replacing the previous version. This update provides access to the latest image generation technology.

We've added a new AI-powered tool that can analyze both uploaded videos and YouTube links. You can now ask questions about the content of a video to get insights directly from the AI.

An info button has been added to help you learn more about specific content. When you click it, a modal window will appear with additional details, such as the prompt used to generate the content.

The Image Generation tool has been updated to version 2.3, adding the powerful Nano Banana AI model and support for new providers like Black Forest Lab and Alibaba for enhanced image creation options. Users can now more easily copy prompts directly from generated images, improving workflow efficiency.

We've significantly upgraded our image generation tool by integrating several new AI models, including Flux Pro, Ideogram, and Imagen 4. This update supports advanced features like editing, remixing, inpainting, and generating from image references for more creative and precise results. Users can now access a wider variety of high-quality image creation options directly in the app.

We've updated the Image Virtual Try-On tool with improvements to its processing and support for additional languages, providing a smoother experience for virtual fashion try-ons.

We've upgraded the video generation tool with new AI models and advanced modes for more creative and dynamic video creation. Improved file handling in chats and fixed quantity and cost calculations for better user experience.

We've integrated several new AI services into our content creation tools, including Google, ByteDance, Ideogram, Qwen, Flux Kontext, Wan, and RunwayML. This expands your options for generating and editing images with AI.

The Ask AI tool has been upgraded to include the latest GPT-5 model.

You can now attach files like images and audio directly to your AI commands for more interactive chats. Features include easy uploads in the command input, previews of attached items, and support for multiple file types.

The Lipsync tool has been updated to version 1.5 with improvements to cost handling and display for better transparency in your projects.

You can now view PDF files directly in the app with a built-in viewer. If your browser doesn't support it, you'll see a clear message about the limitation.

We've introduced a new Image to Video tool, allowing you to transform your images into dynamic videos using advanced AI models. This feature supports multiple generation options and integrates seamlessly into your content creation workflow.

You can now edit the content of previous messages in chats.

We've introduced new AI-powered video effects, including support for models like Kling and Pixverse 4.5. This allows users to create more advanced and creative video content with enhanced generation options.

We've added a new file pool input tool to make handling files in your content creation easier. You can now drag and drop files into pools, reverse their order, delete items, and access common actions directly from the interface. This improves organization and workflow for editing and uploading content.

The Chat AI tool has been significantly upgraded with support for advanced AI models like Google Gemini Flash/Pro, Anthropic Claude, and others, enabling more powerful conversations. Users can now upload and reference files in chats, view citations and sources for responses, and benefit from improved streaming for faster interactions. Cost tracking per token and web search integration have also been added to enhance usability and transparency.

We've added a document editor to help you create and edit content more easily, including support for previewing text and saving your work.

We've improved the context menu in the item list to make copying, pasting, and managing content easier. Now you can paste images, videos, audio, files, and text directly, rename items, and copy content seamlessly—even in messages without a specific tool. This update provides more intuitive options for handling your media and text items.

We've introduced a new Speech-to-Text tool that lets you transcribe audio files into editable text using AI, supporting formats like M4A and WebM. It includes cost estimates based on audio length to help you plan usage. This feature streamlines content creation by converting spoken audio directly into text for your projects.

We've introduced built-in audio and video recording tools, making it easier to capture and share multimedia directly in your messages and content. Enjoy playback options, timers, and seamless integration for a smoother experience.

We've added a new Text-to-Video tool to help you generate videos from text descriptions easily.

We've introduced a new AI-powered video generation tool to help you create dynamic content easily. It integrates multiple advanced models including Kling, Runway, Google Veo, Luma, Pika, and Minimax for high-quality video outputs directly in the app.

We've integrated Kling 2 into the text-to-video feature for enhanced AI-generated videos from text prompts. A new Cartoonify tool is now available, allowing you to easily transform images into cartoon-style artwork.

We've added a new tool to generate audio from text, making it easier to create voiceovers and sound elements for your content.

We've added a new Voice Recorder tool to the app, enabling you to capture audio directly in your browser for content creation or AI interactions. Recordings are now displayed seamlessly, with improved output generation for better usability.

We've introduced a new Lipsync tool that lets you create videos from text with realistic lip-syncing for voices. This makes it easier to produce engaging video content directly in the app.

You can now use the new Lipsync tool to synchronize audio with video, making it easier to create engaging content like talking head videos or animated clips.

You can now generate custom sound effects for your videos directly in the app using AI audio tools. This feature enhances your content creation by allowing easy addition of audio elements.

We've introduced a new tool that lets you upscale videos to improve their quality. Simply upload your video files and process them directly in the app.

You can now handle multiple file parameters more seamlessly in tools, improving the workflow for uploading and processing images or other files. This update ensures smoother tool switching and job creation without losing your inputs.

We've improved the chat editor to make interacting with AI more intuitive and efficient. You can now directly use AI responses as output, preview costs before generating content, and easily copy or download text and code files. The interface features smoother animations, better readability with larger fonts, and overall performance enhancements.

We've introduced a new tool that lets you generate custom sound effects to enhance your content creation and projects.

We've added a powerful AI web search tool to the chat interface, enabling real-time web searches with summarized answers, cited sources, and related questions for deeper exploration. It supports multiple models from Perplexity, OpenAI, and more, with improved display of results including tables and thinking animations during processing.

The document editor now supports easier linking and image insertion. You can now add links directly in the editor and drag and drop images into your documents.

Users can now provide geographic coordinates in the AI web search and ask AI tools for more accurate location-based interactions and queries.

We've improved how items like files and media are managed in parameters for better workflow in the image, audio, video, chat, and document editors. You can now more easily drop and use items across tools and actions, with seamless integration and previews. This update fixes issues with item transfers and ensures reliable handling during job processing.

We've enhanced the chat functionality to better integrate with search items, making it easier to start new conversations and manage your chats. Conversations now generate meaningful names automatically, and you can copy chat items for reuse.

We've introduced a new Audio Viewer tool to help you preview, record, and edit audio content more easily. It includes live preview mode, on-demand recording, and improved zooming and playback controls for a smoother experience.

We've introduced a new Audio Editor tool, allowing you to easily edit and playback audio files directly in the app. It features waveform visualization, simple play/pause controls with the spacebar, and an intuitive navigation bar for better usability.

You can now preview videos directly in your browser while working with content. Videos in the item list support play and pause controls for easier management.

We've introduced a new text editor tool for creating and editing content seamlessly. It features a floating menu for quick formatting, support for inserting and dragging images, draggable sections for easy reorganization, and history to track changes. You can now load, save, and manage your text items with improved drag-and-drop functionality.

You can now easily duplicate existing items in your projects without starting from scratch.

You can now export your documents to HTML, Markdown, and plain text formats for easier sharing and integration. Outputs are also available in these formats to enhance your workflow.

You can now create new files directly in the code editor. It automatically detects the programming language from the file extension for improved editing experience.

We've added a new 'Use in another tool' option, replacing the previous 'Continue editing' button. This makes it easier to move your work between different tools in the application.

You can now preview and export your code in multiple formats, including website views, PDF documents, and images without borders. This makes it easier to share and review your created content directly from the app.

The code editor has been upgraded with live previews, resizable split views, word wrapping, and the ability to rename files for a smoother editing experience.

You can now export your code snippets to image, website, and PDF formats directly from the editor, making it easier to share or save your work.

You can now save and load your work sessions. This includes all your chat messages and tool states, so you can easily return to your work later.

We've introduced an auto-start button in the AI Command feature, allowing you to quickly initiate AI interactions without manual setup each time.

We've resolved several issues in the image editing tools to improve reliability and usability. Fixes include correcting inpainting failures, proper image loading and positioning in the editor, better handling of erase and background removal operations, and smoother transitions when switching tools or clearing content.

We've added a new Virtual Try-On tool to the app, allowing you to virtually try on clothing using advanced AI models. This feature enhances your creative editing experience with realistic outfit simulations. Start experimenting with it in the tools section today.

We've enhanced the color input feature, making it easier to select and update colors when editing your content.

You can now drag and drop items between lists for easier reorganization in the web app.

We've launched updates to our image generation and editing tools, including bigger thumbnails, new options like sketch inputs and structure prompts, and an improved cutout tool for easier content creation. AI commands have been expanded with features like depth and canny for reimagining images, variations, and better background removal. The home page now includes more details on tools, and select features are available for free.

We've integrated new AI-powered models for image upscaling, including ESRGAN, Clarity Upscaler, and creative options. This allows for higher resolution and more detailed image enhancements directly in the editor. Enjoy improved quality when enlarging your images without losing clarity.

Running AI Commands will now consume credits from your account. If you don't have enough credits, an alert will notify you to add more before proceeding.

We've switched back to our flexible credit-based pricing system for using AI tools and features. You can now purchase credits directly to cover costs for chats, edits, and more, with clear displays of your balance in the navigation. This update ensures better control over your spending without currency complications.

We've improved how credits are managed. Credits now roll over for one month, and your free credits are automatically updated each month.

You can now view your available credit balance and expiration details directly from your user menu. This makes it easier to track your usage and manage your account.

You can now generate multiple images at once in various tools. This feature is available for inpainting, outpainting, and other image editing functions.

The grid view has been enhanced for better image display and usability. You can now double-click images to center them, access quick action buttons directly in the grid and other editors, and enjoy highlighted items for easier navigation. Image issues after generation runs have been fixed, and the interface includes a cleaner separated menu bar.

The Reimagine tool will be removed from the application soon. We recommend switching to the Variation tool as a replacement for similar functionality.

We've added Flux Canny and Depth capabilities to enhance image variation and editing tools, offering more advanced AI-driven options for creating and modifying images. This update also improves support for image sizes and multiple style generations.

We've introduced an improved background removal feature for images, inspired by professional tools, allowing you to precisely edit paths and refine edges for cleaner results.

We've introduced a new Cutout tool that uses advanced AI to easily remove backgrounds and segment objects from your images. This feature enhances your content editing capabilities, allowing for precise extractions and refinements. Enjoy improved performance and options for manual or automatic processing.

We've added the new OmniGen tool to the app, powered by advanced AI models for creative content generation. This versatile feature enhances your ability to edit and create with AI assistance.

We've added an Image Variation tool that lets you generate multiple AI-powered variations of your images. You can specify the quantity of variations to create for more creative options.

We've added Flux Ultra, an upgraded AI model that generates images directly in native 4K resolution without needing upscaling, offering better quality, speed, and accuracy than Flux Pro. This upgrade provides faster generation times and more efficient results for your creative projects. Try it now for superior AI-powered image creation.

You can now use Flux Fill to intelligently edit and fill in missing or selected parts of your images using AI-powered inpainting. This tool makes it easy to remove unwanted elements or extend your artwork seamlessly. Check out example workflows on OpenArt for inspiration.

We've enhanced the image inpainting tool using the advanced Flux Alpha model for more precise and natural edits to your images.

We've integrated Recraft, a powerful AI tool for generating and editing images, into the app. This allows you to create custom visuals seamlessly alongside your other content tools.

You can now provide context for AI commands, which helps the AI generate more accurate and relevant responses. This improvement ensures the AI has a better understanding of your task.

We've enhanced image editing tools with better SVG preview support, improved compression, and sharper resized images for higher quality outputs. Fixed issues with tool inputs, error messaging for rate limits, and the premium upgrade process to make your experience smoother. Voice features now prompt for account creation when needed.

We've added a new ICO generator tool to the platform, making it easy for you to create and edit icon files right in your browser.

You can now speak to the AI using voice input. Tap the new microphone button in the text area to record and automatically transcribe your voice into text for chatting or commands.

We've updated the manual crop tool to provide more accurate sizing and better support for aspect ratios, making it easier to crop images precisely. Crop areas now maintain proportions across multiple images in your queue, and interactions like switching tools or transforming images are smoother without unexpected resets. Key fixes also prevent invalid selections and improve overall usability.

You can now cancel ongoing runs directly from the interface using a new cancel button.

We've rolled out a suite of new AI-powered features to enhance your image editing experience. Now you can generate images, smartly remove objects, expand images with outpainting, crop and edit with precision, and work with HEIF files seamlessly. Stability controls for sketches, structures, and styles provide more creative control.

We've introduced a new Outpainting editor in the image tools, allowing you to extend and manipulate areas beyond the original image boundaries for more creative editing.

We've introduced a new AI-powered tool to automatically retouch and enhance faces in your images, helping you improve photo quality with ease.

We've introduced AI-powered tools for sketching, structuring, and styling images to enhance your content creation experience. These features let you easily generate and edit images with more creative control. They're now available directly from the home page.

You can now easily remove backgrounds from images using our new AI-powered tool, perfect for quick photo edits and content creation.

We've added a Voice UI to make interacting with the app more intuitive. You can now use voice buttons and commands for AI input, with an updated tools menu and navigation layout.

We've expanded image generation capabilities by adding support for advanced AI models like DALL-E 3 and Flux, along with updated pricing and improved handling for various image sizes. This allows users to create higher-quality images more flexibly in the app.

New upscaling options have been added, including different modes like fast, AI, and ControlNet. You can now compare images at the same size and choose between conservative or creative enhancement styles. The service also includes usage restrictions for very large upscales.

We've enhanced the image compression process on your device to better honor quality settings, resulting in smoother images without jagged edges during content creation and editing.

We've integrated advanced AI-powered image segmentation into the editing tools, allowing users to easily remove objects, watermarks, people, and backgrounds with higher quality and efficiency. New features include face restoration, upscaling, anime-style segmentation, and paint-by-example options for creative edits.

We've introduced a powerful new image editor that lets you easily enhance your photos with AI assistance. Features include removing objects, watermarks, or backgrounds, face restoration, upscaling, and more specialized tools like anime segmentation and paint by example. Start editing your images directly in the app for quicker, more creative results.

We've introduced AI-powered image inpainting, allowing you to select and fill in parts of images with generated content for easier editing.

We've introduced a Layer panel in the editor, allowing you to easily add, manage, and toggle visibility for multiple layers in your content creations. This makes it simpler to build complex designs with layered outputs directly in the tool.

Image editing tools have been improved for a more intuitive experience, making it easier to modify and create visuals with AI assistance.

Users can now cancel long-running processing tasks to stop unnecessary operations and save resources.

The color picker has been redesigned to be more compact and intuitive, with refined styling for easier RGB value selection in your editing tools.

We've improved how the app handles various image formats, making it easier to work with different types of images in your projects. This update ensures consistent support across tools and better reliability when uploading or processing images.

You can now upload, preview, and work with HEIF images directly in the app, enhancing compatibility with high-efficiency image formats.

We've enhanced the SVG compression feature to produce smaller files more efficiently while maintaining quality. This update streamlines workflows for compressing SVGs directly or as part of image processing in our tools.

We've expanded support for various image formats in our editing tools, including HEIC, AVIF, animated GIFs and WebPs, and SVGs. You can now convert and work with these formats seamlessly in the browser and across the app. This improves compatibility for uploading and editing a wider range of images.

We've added a variety of powerful new tools to help you edit and enhance images directly in the app. These include advanced features like face restoration, colorizing old photos, denoising, deblurring, and low-light enhancement, along with basics like cropping, rotating, and flipping. Enjoy more creative control over your images!

A new image crop tool has been added, which now provides a suggested crop area that you can manually adjust. The tool includes options to lock the aspect ratio and navigate between images more easily.

The AI command feature has been improved to better understand your requests and navigate to the right tools. It now supports more AI models and provides more accurate results.

You can now use AI to generate images directly within the application. The process for creating new images has been streamlined for a smoother experience.

SVG files now display size information when created or compressed. This helps you better understand the dimensions of your generated vector images.

The image display has been updated to be more intuitive. Switching between tools now works more smoothly.

The editor now includes a side navigation panel for managing your files. You can easily compare input and output images, and tools will automatically switch to the appropriate view when you select files.

We've optimized AI commands for better performance, enabling faster responses and smoother interactions. Free users can now access basic AI features, tools have enhanced descriptions and categories for easier discovery, and multi-language support along with voice recording have been added for a more inclusive experience.

Users can now maintain their files across multiple editing sessions without losing them, allowing for continuous workflow. File uploads have been improved, and files are preserved even when switching tools or sections.

We've added support for uploading TIFF files with previews and size display. Fixed resizing issues for AVIF images directly in your browser. Also resolved a bug where credits weren't being applied properly.

We've introduced a drag-and-drop interface for easily uploading files directly into the app. This enhances usability when working with files in AI chats and various tools, including displaying stored files on the home page and seamless integration after sign-up.

We've introduced improved session management for tools, making it easier to handle files, track processing status, and manage credits directly in your workflow. You can now see upload/download progress, compression details, and receive alerts for insufficient credits. File handling and job queuing have been streamlined for a smoother experience.

You can now view and manage multiple outputs for your tasks. This includes the ability to download outputs, view a count of all outputs, and filter them by type.

The background removal feature has been updated to use a new AI service. This provides more reliable and higher quality results for your images.

This update includes several improvements to the user interface and tools. You can now upload images more easily and see previews for them. Various fixes have been applied to make the tools more stable and inputs clearer.

You can now see the number of files directly in the interface, making it easier to manage your content and projects.