=== AI Featured Image === Contributors: amr267, freemius Donate link: https://buymeacoffee.com/unclegold Tags: image generator, featured image, auto featured image, ai, mcp Requires at least: 5.8 Tested up to: 7.1 Stable tag: 2.0.1 Requires PHP: 7.4 License: GPLv2 or later License URI: https://www.gnu.org/licenses/gpl-2.0.html AI featured images in one click, in bulk, in your content, or by asking Claude through MCP. Free with OpenAI, Stability AI and Grok; Pro adds more. == Description == **AI Featured Image Generator** creates AI-powered featured images right from the WordPress editor. Click "Generate Featured Image" on any post and the plugin builds a unique image from your post title, chosen style, and optional custom prompt, using OpenAI, Stability AI, or Grok/xAI on the free plan, or Google Gemini and Meta Muse on Pro. Every image gets alt text automatically and an SEO-friendly filename based on your post title. Generate one at a time in the editor, in bulk, straight from the Posts list, inline in your content with the AI Image Generator block, or by asking an AI assistant such as Claude Desktop or Cursor through MCP. Everything is managed from one settings hub. = Video Walkthrough = https://www.youtube.com/watch?v=n5jwt4UN2Hk = Free Features = * **3 free AI providers**: OpenAI, Stability AI, and Grok/xAI (Google Gemini and Meta Muse available on Pro) * **OpenAI models**: GPT Image 2 (default): excels at text rendering in multiple languages, visual reasoning, multi-object scenes, transparent backgrounds, mask-based editing, and up to 4K output * **Stability AI**: Stable Image Core with 16 native style presets (Photographic, Cinematic, Anime, Digital Art, Comic Book, Fantasy Art, and more) * **Grok/xAI**: Grok Imagine Image: fast and affordable at $0.02 per image * **21 style presets**: Common (None, Realistic, Artistic, Cartoon, Minimalist), Creative (Sketch, Watercolor, 3D Render, Pixel Art, Cyberpunk, Fantasy, Anime, Technicolor), and Trending (Toy Figure, Miniature World, Claymation, Cinematic, Lo-Fi Cozy, Vintage Instant Photo, Magazine Collage, Paper Cut) * **Custom prompts**: plus one-click **Generate Prompt from Content**, which crafts an AI-optimized prompt from your post title and body (OpenAI and Grok free; Gemini on Pro) * **7 image sizes with GPT Image 2 and 2.5**: square, portrait, landscape, widescreen 16:9, vertical 9:16, ultra-wide 3:1, and tall banner 1:3 * **All aspect ratios**: 9 for Stability AI and 9 for Grok, plus 2K resolution on Grok * **Output control (OpenAI)**: WebP/PNG/JPEG format, compression slider (1–100), and Low/Medium/High generation quality (Extra High and Max on GPT Image 2.5, Pro) * **Text control**: allow or block text, captions, and words in generated images * **Auto alt text**: from the post title, the prompt, or a custom template with `{title}`, `{prompt}`, `{style}`, and `{site_name}` placeholders. with an option to preserve manual edits on regeneration * **Bulk Generate**: unlimited images for Posts and Pages that have no featured image yet, as many at once as you like * **Generate from Post List**: an "AI Featured Image" column on the Posts/Pages list with a one-click Generate/Regenerate link, so there is no need to open the editor * **Inline images**: the AI Image Generator block adds AI images anywhere in your Gutenberg content, with its own settings tab * **AI assistants (MCP)**: connect Claude Desktop, Cursor, Claude Code or VS Code and ask them in plain words, starting with "On ," to make featured images, make any image for the Media Library, find posts and images, audit your images (missing alt text, size, format, blur, cut-off edges) and fix alt text, titles and captions. A 3-step setup on the AI Assistants tab, 20 assistant images on the free plan * **Multisite compatible** = Pro Features 🚀 = * **Google Gemini**: Nano Banana 2.1 (Google's newest, fast and about half the price of Nano Banana 2), Nano Banana Pro (Gemini 3 Pro) and Nano Banana 2 (Gemini 3.1 Flash, deprecated by Google but still available): up to 4K resolution and 10 aspect ratios * **Meta Muse (beta)**: Muse Image 1.0, Meta's reasoning image model at $0.01 per image, with 9 aspect ratios and native WebP, PNG or JPEG output * **Unlimited AI assistant images (MCP)**: plus Pro tools for assistants: set a featured image from the Media Library, insert an image into a post, upscale, remove background, rename images, convert JPG or PNG to WebP, and manage the Brand Kit (read it, change colours, tone and logo placement, preview it, stamp the logo onto existing featured images and undo that, or set it up from what the site already says about itself) * **GPT Image 2.5 (OpenAI)**: GPT Image 2.5 Flare (fast, recommended) and GPT Image 2.5 Sunburst (best detail), with Extra High and Max generation quality and a one-click "Retry with Sunburst" button in the post editor * **Image upscaling (Stability AI)**: Conservative (faithful 4x), Creative (AI-enhanced 4K), or Fast (quick 4x), right from the post editor * **Background removal (Stability AI)**: one click isolates the subject and saves a transparent PNG as your featured image * **Advanced Stability AI models**: Stable Image Ultra, SD 3.5 Large / Large Turbo / Medium / Flash, SD 3 Large / Large Turbo / Medium, and SDXL 1.0 * **Negative prompts (Stability AI)**: exclude unwanted elements, e.g. "blurry, watermark, text, low quality" * **Grok Imagine Image 2.0**: higher quality at $0.04 per image * **More output formats**: PNG/JPEG/WebP for Stability AI, and automatic WebP conversion for Gemini and Grok images * **More Bulk Generate**: any post type, filters for date range and thumbnail status, overwrite existing images, and the Brand Kit * **Custom post types**: enable generation for any public post type * **Custom styles**: create named styles with your own prompt descriptions, available in every style dropdown * **Brand Kit**: save your brand colors, a style description, tone, and avoid-rules, plus an optional reference image (used by Google Gemini) and a logo watermark (corners or centre, with size, opacity, margin and offset controls plus a live preview), applied automatically to every image you generate, with a per-image "Use Brand Kit" toggle to skip it Want to unlock Google Gemini, Meta Muse, image upscaling, background removal, the Brand Kit, unlimited AI assistant images and more? Upgrade to Pro here. = Requirements = * WordPress 5.8 or higher * PHP 7.4 or higher * An API key for at least one provider: * [OpenAI](https://platform.openai.com/api-keys) (free plan) * [Stability AI](https://platform.stability.ai/account/keys) (free plan) * [Grok/xAI](https://console.x.ai/) (free plan) * [Google Gemini](https://aistudio.google.com/app/apikey) (Pro only) * [Meta Muse](https://dev.meta.ai/) (Pro only) * For AI assistants (MCP): WordPress 6.9 or higher and the free [MCP Adapter](https://wordpress.org/plugins/mcp-adapter/) plugin, installed in one click from the AI Assistants tab == External Services == This plugin connects to your chosen AI provider's API to generate images. For every provider: * Your post title and content (or your custom prompt, and for Stability AI any negative prompt) are sent to the provider's API when you generate an image * Your API key for that provider authenticates each request * Requests are only sent when you trigger generation: from the post editor, the Posts list, Bulk Generate, or the AI Image Generator block * "Generate Prompt from Content" sends your post title and body to the provider's text API: gpt-6-luna (OpenAI), grok-4.3 (Grok), Gemini 3.6 Flash (Gemini, Pro), or Muse Spark 1.3 (Meta Muse, Pro) **OpenAI (Free & Pro)**: image generation and prompt generation. [Terms of Service](https://openai.com/policies/terms-of-use) | [Privacy Policy](https://openai.com/policies/privacy-policy) | [API Documentation](https://platform.openai.com/docs) **Stability AI (Free & Pro)**: image generation; for Pro users, upscaling and background removal also send your existing featured image file to Stability AI for processing. [Terms of Service](https://stability.ai/terms-of-service) | [Privacy Policy](https://stability.ai/privacy-policy) | [API Documentation](https://platform.stability.ai/docs/api-reference) **Grok / xAI (Free & Pro)**: image generation and prompt generation. [Terms of Service](https://x.ai/legal/terms-of-service) | [Privacy Policy](https://x.ai/legal/privacy-policy) | [API Documentation](https://docs.x.ai/docs) **Google Gemini (Pro only)**: image generation and prompt generation. [Terms of Service](https://ai.google.dev/gemini-api/terms) | [Privacy Policy](https://policies.google.com/privacy) | [API Documentation](https://ai.google.dev/gemini-api/docs) **Meta Muse (Pro only)**: image generation (Muse Image 1.0) and prompt generation (Muse Spark 1.3) through the Meta Model API. [Terms of Service](https://dev.meta.ai/legal/terms-of-service) | [Acceptable Use Policy](https://dev.meta.ai/legal/acceptable-use-policy) | [Data Handling](https://dev.meta.ai/help/policies-and-privacy/data-handling) | [API Documentation](https://dev.meta.ai/docs/image-generation) **AI assistants (MCP)**: no new third party. Your own assistant app (Claude Desktop, Cursor, Claude Code, VS Code) connects to your site with a WordPress Application Password and calls the same providers above with your keys. Images are only generated when you ask the assistant. **Data usage:** generated images are stored in your WordPress media library. No personal data is stored by the providers beyond what's necessary for API processing. You are responsible for ensuring your content complies with the selected provider's usage policies. == Installation == 1. Upload the `ai-featured-image-generator` folder to the `/wp-content/plugins/` directory 2. Activate the plugin through the 'Plugins' menu in WordPress 3. Go to AI Image in the admin menu to configure your API key and other settings 4. The AI Image Generator block is available in the Gutenberg block inserter for adding inline images == Frequently Asked Questions == = Do I need an API key? = Yes, for at least one provider. All free-plan providers have free tiers or pay-as-you-go pricing: [OpenAI](https://platform.openai.com/api-keys), [Stability AI](https://platform.stability.ai/account/keys), [Grok/xAI](https://console.x.ai/), [Google Gemini](https://aistudio.google.com/app/apikey) (Pro only), or [Meta Muse](https://dev.meta.ai/) (Pro only). = How much does it cost? = The plugin is free; you pay your provider per image: * **OpenAI**: varies by model and generation quality (Low is the cheapest); see [OpenAI pricing](https://openai.com/api/pricing/) * **Stability AI**: Stable Image Core is roughly ~$0.003/image; other models vary; see [Stability AI pricing](https://platform.stability.ai/pricing) * **Grok/xAI**: $0.02/image (Grok Imagine Image) or $0.04/image (Grok Imagine Image 2.0) * **Google Gemini (Pro)**: Nano Banana 2.1, Gemini 3.1 Flash and 3 Pro vary by resolution * **Meta Muse (Pro)**: $0.01/image = Can I switch between providers? = Yes. Select your provider and enter its API key in the plugin settings. The page shows only the options relevant to your selection. Free users can switch between OpenAI, Stability AI, and Grok/xAI; Pro adds Google Gemini and Meta Muse. = Is there a limit to how many images I can generate? = Only your API plan's quota with your chosen provider. The plugin generates one image per request. The free plan has one lifetime cap: 20 images requested by AI assistants (MCP). Pro removes it. Everything else, including Bulk Generate, has no plugin limit. = What AI models are available? = **OpenAI (Free & Pro):** GPT Image 2 (default, with strong text rendering and visual reasoning). Pro adds GPT Image 2.5 Flare (up to 50% faster than GPT Image 2 with sharper detail) and GPT Image 2.5 Sunburst (the most detailed), both with Extra High and Max generation quality. **Stability AI:** Stable Image Core (free): fast, high quality, best value. Pro adds Stable Image Ultra (best quality), SD 3.5 Large / Large Turbo / Medium / Flash, SD 3 Large / Large Turbo / Medium, and SDXL 1.0 (legacy). **Grok / xAI:** Grok Imagine Image (free, $0.02/image) and Grok Imagine Image 2.0 (Pro, $0.04/image). **Google Gemini (Pro only):** Nano Banana 2.1 (1K/2K/4K, the default), Gemini 3.1 Flash Image (1K/2K/4K, deprecated by Google) and Gemini 3 Pro Image (best quality, 1K/2K/4K). All support 10 aspect ratios. **Meta Muse (Pro only, beta):** Muse Image 1.0, Meta's in-house reasoning image model. New and not yet widely tested, so please report anything odd. 9 aspect ratios, up to 1600px, $0.01 per image. = What styles are available? = 21 built-in styles that work with all providers: None, Realistic, Artistic, Cartoon, Minimalist, Sketch, Watercolor, 3D Render, Pixel Art, Cyberpunk, Fantasy, Anime, and Technicolor, plus the Trending group: Toy Figure, Miniature World, Claymation, Cinematic, Lo-Fi Cozy, Vintage Instant Photo, Magazine Collage, and Paper Cut. With Stability AI you also get a **Stability Presets** group of 16 native API-level presets: Photographic, Cinematic, Anime, Digital Art, Comic Book, Fantasy Art, 3D Model, Analog Film, Enhance, Isometric, Line Art, Low Poly, Neon Punk, Origami, Pixel Art, and Tile Texture. Pro users can also create unlimited custom styles (see below). = Can I create my own custom styles? (Pro) = Yes. Go to **AI Images → Settings → Brand & Styles → Custom Styles**, click "Add Style", and enter a name plus a prompt description (e.g. "in a dreamy impressionist style"). Custom styles appear in all style dropdowns and work exactly like built-in styles. = What is the Brand Kit? (Pro) = One global set of brand rules that keeps every AI image on-brand. Go to **AI Images → Settings → Brand & Styles** and save up to 3 brand colors, a style description, a tone, and avoid-rules; optionally add a reference image (used by Google Gemini to match your visual style) and a logo watermark with position (four corners or centre), size, opacity, margin and horizontal/vertical offset controls, with a live preview you can drag to place the logo. The kit is applied automatically wherever you generate: post editor, Bulk Generate, the Posts list, and the AI Image Generator block. The post editor, Bulk Generate, and the block each have a "Use Brand Kit" checkbox you can uncheck for a one-off image; the Posts list always applies the kit. = What image sizes and aspect ratios are supported? = * **OpenAI**: 7 sizes with GPT Image 2 and 2.5: 1024x1024 (1:1), 1024x1536 (portrait), 1536x1024 (landscape), 1792x1024 (16:9), 1024x1792 (9:16), 1920x640 (3:1), and 640x1920 (1:3) * **Stability AI**: 9 ratios (1:1, 16:9, 21:9, 2:3, 3:2, 4:5, 5:4, 9:16, 9:21) * **Grok**: 9 ratios (1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 2:1, 1:2) * **Gemini (Pro)**: 10 ratios (1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9): 1K/2K/4K on Nano Banana 2.1, Gemini 3.1 Flash and 3 Pro * **Meta Muse (Pro)**: 9 ratios (1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 2:1, 1:2) = Can I upscale my featured image? (Pro) = Yes, with a Stability AI API key. Once a featured image is set, a "Stability AI Tools" panel appears in the post editor with three modes: **Conservative** (faithful 4x), **Creative** (AI-enhanced 4K), and **Fast** (quick 4x). Conservative and Creative process asynchronously and may take up to ~3 minutes; the result automatically becomes your new featured image. = Can I remove the background from my featured image? (Pro) = Yes, from the same "Stability AI Tools" panel. Click "Remove Background" and Stability AI isolates the subject and saves a transparent PNG as your featured image, which suits product shots and portraits. = What is a negative prompt? (Stability AI, Pro) = Text that tells Stability AI what **not** to include, e.g. "blurry, watermark, text, low quality". Set defaults in **AI Images → Settings → Featured Images** (and the Inline Images tab). Negative prompts have no effect with OpenAI, Gemini, or Grok. = What output formats are supported? = * **OpenAI**: WebP (recommended), PNG, or JPEG * **Stability AI**: PNG free; Pro adds JPEG and WebP * **Grok**: JPEG free; Pro adds WebP (converted after generation) * **Gemini (Pro)**: PNG default, or WebP (converted after generation) * **Meta Muse (Pro)**: WebP (default), PNG, or JPEG, returned directly by the API Because the Gemini and Grok APIs return PNG/JPEG, the plugin converts to WebP using your server's image library (ImageMagick or GD). = Why was my image saved as PNG or JPEG instead of WebP? = WebP conversion for Gemini and Grok needs a WebP-capable image library on your server (GD with WebP, or ImageMagick with the WebP delegate). If it's missing, the plugin safely falls back to the provider's native format and shows a notice with the reason. Generation never fails. Ask your host to enable WebP if needed. OpenAI WebP is unaffected because the API returns it directly. = How does quality control work? = * **OpenAI**: Output Compression slider (1–100, default 90) plus a Low/Medium/High generation quality tier (Extra High and Max on GPT Image 2.5, Pro) * **Stability AI**: quality is inherent to the model you choose * **Grok**: 1K or 2K resolution * **Gemini (Pro)**: 1K/2K/4K on Nano Banana 2.1, 3.1 Flash and 3 Pro * **Inline images (all providers)**: Automatic Quality Optimization picks quality and resolution based on the image's display size in your content = Can I generate images inside the Gutenberg editor? = Yes. Add the "AI Image Generator" block from the Media category, enter a prompt, and generate images anywhere in your content. The block supports the same providers, styles, and aspect ratios as featured images; configure defaults in the Inline Images settings tab. = How does auto alt text work? = Every AI image (featured, inline, or bulk) automatically gets alt text in the media library. Configure it under **AI Images → Settings → General → Alt Text**: choose the post title (default), the generation prompt, or a custom template with `{title}`, `{prompt}`, `{style}`, and `{site_name}` placeholders. e.g. `{title} - {style} style - {site_name}`. By default, manually edited alt text is preserved on regeneration; enable "Overwrite on Regeneration" to always refresh it. = How does "Generate Prompt from Content" work? = Click **"Generate Prompt from Content"** in the post editor and AI writes an image prompt from your post title and body. It's saved to the post and pre-filled in the Custom Prompt field so you can review or edit before generating. The same option exists in Bulk Generate, creating a unique prompt per post. Text model per provider: gpt-6-luna (OpenAI), grok-4.3 (Grok), Gemini 3.6 Flash (Gemini, Pro), Muse Spark 1.3 (Meta Muse, Pro). Stability AI has no text API, so the button shows a notice when it's the active provider. = Can I generate images from Claude, Cursor or another AI assistant? (MCP) = Yes. Go to **AI Images → Settings → AI Assistants** and follow the 3 steps: install the free MCP Adapter plugin (one click), create a key (one click), and connect your app with the ready-made config. Claude Desktop, Cursor, Claude Code and VS Code are covered with step-by-step instructions, and the tab ticks step 3 by itself the first time your assistant calls the site, which costs nothing. Then start each request with "On" and your site name, for example "On My Site, make a featured image for my latest post". That one rule works in every app and keeps several sites apart. The assistant can only do what your WordPress user can do, and only the plugin's image tools are exposed. Free sites get 20 assistant images plus finding, auditing and alt text; Pro is unlimited and adds the tools below. On a Free site the Pro tools still show up, but answer with an upgrade link instead of running. Needs WordPress 6.9 or newer. claude.ai in the browser and ChatGPT cannot connect yet because they need an OAuth sign-in that the MCP Adapter does not provide. = What can the assistant do on my site? (MCP) = Free: * **Make images**: a featured image for a post (with a prompt, style, shape, provider or model of your choice) or any image for the Media Library. 20 images in total. * **Find**: posts, pages and any other post type by title, author, category, tag, date, or whether they have a featured image; read a post to write a better prompt; find images in the Media Library by name. * **Image audits**: count and list images by format, shape, pixel size, file size, upload date, missing alt text, blur or cut-off edges, across posts of any type or the whole Media Library; measure one image for sharpness and cut-off edges; look at a preview to judge the picture itself. * **Image text**: change an image's title, alt text, caption or description. Pro adds unlimited images and: * **Image tools**: rename an image (every post keeps pointing at the right file), convert JPG or PNG to WebP (every post switches to the lighter copy), upscale, or remove the background. * **Place images**: set a Media Library image as a featured image, or insert it into a post. * **Brand**: read and change the Brand Kit (colours, tone, description, avoid list, reference image), pick and place the logo, preview the kit, stamp the logo onto the featured images posts already have (no AI call) and undo it, find posts whose image predates the current kit, and set the kit up from the site name, tagline, theme colours and logo. Examples: "On My Site, add featured images to every post in Recipes that is missing one", "On My Site, which pages have JPG images with no alt text?", "On My Site, look at the featured image on post 123 and tell me if anything is cut off", "On My Site, set my brand colours to navy and gold, then show me a test image", "On My Site, look at my site and suggest a brand kit", "On My Site, which posts still have images from before my brand kit changed?", "On My Site, add my logo to every featured image in Recipes". = Does it work with custom post types? (Pro) = Yes. Go to **AI Images → Settings → General → Availability**, check the post types you want, and save. The generator panel then appears in the editor for those post types. Free users are limited to Posts and Pages. == Screenshots == 1. General tab: pick your AI provider and model, see the price per image, and test your API key. 2. The AI Featured Image panel in the block editor: custom prompt, style, and the cost shown before you generate. 3. AI Assistants (MCP): connect Claude Desktop, Cursor, Claude Code or VS Code in three steps, then ask in plain words. 4. What your AI assistant can do (MCP): a usage meter for the free images and the Free and Pro lists. 5. Bulk Generate: filter and load posts, with the Pro filters shown as locked. 6. Bulk Generate: select posts and make images for all of them at once. 7. AI Image Generator block: type a prompt, pick a style and shape, and see the cost before generating. 8. Featured Images tab: default shape, resolution, format, style and text options. 9. Inline Images tab: default style, shape and format for the AI Image Generator block. 10. Brand Kit (Pro): upload your logo and set its position, size, opacity, margin and offsets with a live preview. 11. Brand Kit preview in the free version: the same image without and with your Brand Kit. 12. The AI Featured Image column in the Posts list, with thumbnails and one-click Regenerate. == Changelog == = 2.0.1 = * **Upgrade link fix**: "Upgrade to Pro" now opens the hosted checkout when the in-admin pricing page is not available (for example before the opt-in screen is completed), instead of "Sorry, you are not allowed to access this page". The link is shown to administrators only, since only they can activate a licence. = 2.0.0 = * **AI assistants (MCP)**: connect Claude Desktop, Cursor, Claude Code or VS Code to your site and ask them to generate featured images. New AI Assistants tab with a 3-step setup, one-click MCP Adapter install, one-click key creation, ready-made configs and example requests. Free sites get 20 assistant images; Pro is unlimited. * **Assistant tools for everyone**: find posts of any type by author, category, tag or date, find posts missing a featured image, read a post, and fix an image's alt text, title, caption or description. * **Pro assistant tools**: set a featured image from the Media Library, insert an image into a post, upscale, remove background, rename images and convert them to WebP. * **Brand management from your assistant (Pro)**: read and change the Brand Kit (colours, tone, description, avoid list, reference image), pick and place the logo, preview the kit, stamp the logo onto the featured images posts already have (no AI call) and undo it, find posts whose image predates the current kit, and set the kit up from the site name, tagline, theme colours and logo. * **Image audits from your assistant**: count and list images by format, shape, pixel size, file size, upload date, missing alt text, blur or cut-off edges, across posts of any type or the whole Media Library; measure one image for sharpness and cut-off edges; and show the assistant a preview so it can judge the picture itself. * **Nano Banana 2.1 (Pro)**: Google's new Gemini image model is the default for new Gemini setups, at about half the price of Nano Banana 2. Nano Banana 2 stays available and is marked deprecated by Google; saved choices are kept. * **OpenAI text model**: Generate Prompt from Content now uses gpt-6-luna, since OpenAI retires gpt-4o-mini on January 14, 2027. * **Meta Muse (Pro, beta)**: new provider with Muse Image 1.0 at $0.01 per image, 9 aspect ratios, native WebP/PNG/JPEG output, and Muse Spark 1.3 for "Generate Prompt from Content". * **Brand Kit logo placement (Pro)**: new Centre position plus horizontal and vertical offsets, sliders with number boxes, and a live preview you can drag. The logo always stays inside the image. * **More for the free plan**: Bulk Generate has no image or batch limit and works on Posts and Pages, every aspect ratio of Stability AI and Grok is free, and so is Grok's 2K resolution. * **Clearer costs**: every Generate button (post editor, Posts list, block) now says which model it uses and, where the price is fixed, about how much each image costs, and shows progress while it works. * **Easier first setup**: a 3-step guide on the General tab, Save right under your API key, and a "Make your first image" button once you are set. * **Posts list keeps your prompt**: Generate in the Posts list now uses the custom prompt you saved in the editor instead of replacing it. * **Bulk Generate menu item**: open Bulk Generate straight from the AI Images menu. * **What's new notice**: after updating from 1.x, administrators see a short one-time note of what changed, with a button to set up their AI assistant. * **Internal**: one provider registry replaces the provider lists that were copied across the plugin. * **Fixes**: various bug fixes and improvements. = 1.9.10 = * Updated Freemius SDK to the latest version = 1.9.9 = * **Gemini models updated (Pro)**: Nano Banana 2 and Nano Banana Pro now use Google's stable Gemini 3.1 Flash Image and Gemini 3 Pro Image models. Google is retiring the preview models and Gemini 2.5 Flash Image, so sites using them switch automatically. * **Grok Imagine Image 2.0 (Pro)**: Replaces Grok Imagine Image Pro, which xAI is retiring. Higher quality at $0.04 per image. Sites using the old model switch automatically. * **Updated prompt models**: "Generate Prompt from Content" now uses Grok 4.3 and Gemini 3.6 Flash, replacing retired models. = 1.9.8 = * **GPT Image 2.5 (Pro)**: Two new OpenAI models, GPT Image 2.5 Flare (fast, recommended) and GPT Image 2.5 Sunburst (best detail), with all 7 GPT Image 2 sizes and transparent backgrounds. * **Extra High and Max quality (Pro)**: Two new generation quality tiers for GPT Image 2.5. * **Retry with Sunburst (Pro)**: After generating an image in the post editor, one click makes a new version with GPT Image 2.5 Sunburst using the same prompt and style. * **Trending styles**: 8 new free styles in their own Trending group: Toy Figure, Miniature World, Claymation, Cinematic, Lo-Fi Cozy, Vintage Instant Photo, Magazine Collage, and Paper Cut. * **Removed deprecated models**: GPT Image 1, GPT Image 1 Mini, and GPT Image 1.5, which OpenAI shuts down on October 23 and December 1, 2026. Sites using them switch to GPT Image 2 automatically. * **Fix**: The settings page now updates model-specific options (sizes, background, quality) as soon as you change the AI model. * Bug fixes and post editor improvements = 1.9.7 = * Bug fixes = 1.9.6 = * Bug fixes = 1.9.5 = * Bug fixes = 1.9.4 = * Bug fixes = 1.9.3 = * Bug fixes = 1.9.2 = * **Brand Kit (Pro)**: Save your brand colors, style description, tone, and avoid-rules once, plus add an optional reference image (used by Google Gemini) and a logo watermark with customizable position, size, opacity, and margin. Automatically applies to featured, bulk, Posts-list, and inline images. * **Per-image opt-out**: A "Use Brand Kit" toggle in the post editor, Bulk Generate, and AI Image Generator block for skipping the kit on specific images. * **Layout enhancement** * Other bug fixes, including Gemini debug logging that previously wrote to the PHP error log on every request. = 1.8.3 = * **WebP for Gemini & Grok (Pro)**: featured and inline images from Gemini and Grok are now converted to lightweight WebP after generation (Imagick or GD). WebP becomes the recommended default for Pro; free users keep the native format * **Consistent output formats**: Gemini and Grok get their own Output Format selector on the Featured and Inline Images tabs * **Safe fallback**: if a server can't produce WebP, generation never fails. The image is saved in the provider's native format and you're notified with the reason = 1.8.2 = * **Inline Images now free**: the AI Image Generator block and its settings tab are available to all users (OpenAI, Stability AI, Grok; Gemini remains Pro) * **Plugin renamed** to "AI Featured Image Generator with Output Control" * **Compatibility notice** when the official WordPress "AI" plugin is active with image generation enabled = 1.8.1 = * **Generate from Post List**: a new "AI Featured Image" column on the Posts/Pages list with a one-click Generate/Regenerate link, so there is no need to open the editor * Auto-builds the prompt from post title and content, respects all global settings, confirms before overwriting an existing image, and doesn't count against the free bulk limit * Per-post 5-second rate limit prevents accidental double-clicks = 1.8.0 = * **New model (OpenAI)**: GPT Image 2, now the default for new installs: text rendering, visual reasoning, multi-object scenes, up to 4K, transparent backgrounds, quality tiers, moderation control, and 4 additional sizes * **New provider: Stability AI** (free): Stable Image Core with 16 native style presets; Pro adds Ultra, SD 3.5/SD 3 variants, SDXL 1.0, negative prompts, output formats, and 9 aspect ratios * **New provider: Grok/xAI** (free): Grok Imagine Image at $0.02/image; Pro adds the Pro model, 9 aspect ratios, and 2K resolution * **New Pro tools**: image upscaling (Conservative/Creative/Fast) and one-click background removal via Stability AI * Automatic Quality Optimization for inline images, Stability key validation with credit balance, improved API error messages, and assorted fixes = 1.5.4 = * Auto Alt Text for all AI-generated images with title/prompt/custom-template sources; free bulk limit raised from 20 to 50 images = 1.5.0 = * Custom Styles (Pro), Bulk Generate for free users (5 posts/batch, 50 lifetime), unified settings hub with AJAX tabs, API key Test Connection, new models (ChatGPT Image Latest, Gemini 3.1 Flash Preview), and a full admin UI overhaul = 1.4.x = * Inline image generation in Gutenberg with a dedicated Inline Images settings tab, PNG output fixes, and WordPress 6.9.1 compatibility = 1.3.x = * Google Gemini provider (Pro), custom post types (Pro), gpt-image-1.5 model, redesigned card-based settings UI, top-level admin menu, and Freemius integration = 1.2.x = * Output format selection (WebP/PNG/JPEG), image quality control, model selection (GPT Image 1 vs Mini), and Classic Editor compatibility fixes = 1.0.0 – 1.1.0 = * Initial releases: core featured-image generation, style presets, Pages support, and UI improvements == Upgrade Notice == = 2.0.1 = Fixes the "Upgrade to Pro" link opening a "not allowed" page on some sites. = 2.0.0 = New: AI assistants via MCP. Connect Claude Desktop, Cursor, Claude Code or VS Code from the new AI Assistants tab and ask them, in plain words, to make featured images (20 free, unlimited on Pro). Free assistants can also find posts, audit your images and fix alt text; Pro adds tools to manage the Brand Kit, stamp your logo onto existing images, rename images and convert them to WebP. The free plan now has unlimited Bulk Generate for Posts and Pages, every aspect ratio, and Grok 2K. New for Pro: Meta Muse provider at $0.01 per image, and a Centre logo position with offsets and a live preview in the Brand Kit. Needs WordPress 6.9+ for the assistant features; everything else works as before. = 1.9.8 = New for Pro: OpenAI GPT Image 2.5 Flare (fast) and Sunburst (best detail), Extra High and Max generation quality, and a one-click "Retry with Sunburst" button in the post editor. New for everyone: 8 Trending styles. GPT Image 1, 1 Mini, and 1.5 are removed (deprecated by OpenAI); sites using them switch to GPT Image 2 automatically. = 1.9.2 = New: Brand Kit (Pro)! Save your brand colors, a style description, tone, and avoid-rules once, add an optional reference image (used by Google Gemini) and a logo watermark with position, size, opacity, and margin controls, and every image you generate follows them automatically: in the post editor, Bulk Generate, the Posts list, and the AI Image Generator block. A "Use Brand Kit" toggle in the post editor, Bulk Generate, and the block skips it whenever you need a one-off image. Also fixes Gemini debug logging that wrote to the PHP error log on every request. = 1.8.1 = New: Generate AI featured images directly from the Posts/Pages admin list! A new "AI Featured Image" column shows the current thumbnail and a one-click Generate Image / Regenerate Image link, with no need to open each post. Auto-builds the prompt from title + content, respects all your provider settings, and does not count against the free bulk-generation limit. = 1.8.0 = Major update! New OpenAI GPT Image 2 model (now default) with text rendering, visual reasoning, 4K output, 7 aspect ratios, transparent backgrounds, generation quality tiers, and moderation control. Two new free providers: Stability AI (16 style presets) and Grok/xAI ($0.02/image). Pro users gain image upscaling, background removal, negative prompts, advanced Stability AI models, Grok Pro, extended aspect ratios, and automatic quality optimization for inline images.