Adds AI featured image generation (FAL.AI) and a dedicated text model setting.<\/p>"},"ratings":[],"assets_icons":{"icon-128x128.png":{"filename":"icon-128x128.png","revision":3577760,"resolution":"128x128","location":"assets","locale":"","width":128,"height":128},"icon-256x256.png":{"filename":"icon-256x256.png","revision":3577760,"resolution":"256x256","location":"assets","locale":"","width":256,"height":256}},"assets_banners":{"banner-1544x500.png":{"filename":"banner-1544x500.png","revision":3577760,"resolution":"1544x500","location":"assets","locale":"","width":1544,"height":500},"banner-772x250.png":{"filename":"banner-772x250.png","revision":3577760,"resolution":"772x250","location":"assets","locale":"","width":772,"height":250}},"assets_blueprints":{},"all_blocks":{"kwik-ai\/description":{"name":"kwik-ai\/description","title":"Description"}},"tagged_versions":["v1.1.0"],"block_files":[],"assets_screenshots":{"screenshot-1.png":{"filename":"screenshot-1.png","revision":3577760,"resolution":"1","location":"assets","locale":"","width":534,"height":2166},"screenshot-2.png":{"filename":"screenshot-2.png","revision":3577760,"resolution":"2","location":"assets","locale":"","width":3374,"height":2606}},"screenshots":{"1":"Kwik AI settings: configure your provider, models, and API keys.","2":"Generating AI tags and a description for a post in the editor."}},"plugin_section":[],"plugin_tags":[2353,1795,226976,194533,609],"plugin_category":[57],"plugin_contributors":[267783,129971],"plugin_business_model":[],"class_list":["post-320915","plugin","type-plugin","status-publish","hentry","plugin_tags-ai","plugin_tags-featured-image","plugin_tags-ollama","plugin_tags-openai","plugin_tags-tags","plugin_category-taxonomy","plugin_contributors-draggable","plugin_contributors-kevinchappell","plugin_committers-draggable"],"banners":{"banner":"https:\/\/ps.w.org\/kwik-ai\/assets\/banner-772x250.png?rev=3577760","banner_2x":"https:\/\/ps.w.org\/kwik-ai\/assets\/banner-1544x500.png?rev=3577760","banner_rtl":false,"banner_2x_rtl":false},"icons":{"svg":false,"icon":"https:\/\/ps.w.org\/kwik-ai\/assets\/icon-128x128.png?rev=3577760","icon_2x":"https:\/\/ps.w.org\/kwik-ai\/assets\/icon-256x256.png?rev=3577760","generated":false},"screenshots":[{"src":"https:\/\/ps.w.org\/kwik-ai\/assets\/screenshot-1.png?rev=3577760","caption":"Kwik AI settings: configure your provider, models, and API keys."},{"src":"https:\/\/ps.w.org\/kwik-ai\/assets\/screenshot-2.png?rev=3577760","caption":"Generating AI tags and a description for a post in the editor."}],"raw_content":"\n
Kwik AI brings AI-powered content automation to your WordPress site. Generate tags, write descriptions, craft excerpts, and create featured images -- all from within the WordPress editor. It supports multiple AI providers: Ollama<\/strong> (local models for full data privacy), OpenRouter<\/strong> (hundreds of cloud models via one API), OpenAI<\/strong> (GPT models), and FAL.AI<\/strong> (AI image generation).<\/p>\n\n Features<\/strong><\/p>\n\n The plugin connects to third-party AI services you configure. Tags, descriptions, excerpts, and images are generated by sending your post content (text, images, or both) to the provider you select.<\/p>\n\n Third-party services<\/strong><\/p>\n\n This plugin can send your post content to whichever provider you configure:<\/p>\n\n For OpenRouter and OpenAI you need an API key. For Ollama or local LLM you only need a running Ollama server (local or remote). FAL.AI requires its own key and is only needed for featured-image generation.<\/p><\/dd>\n Yes, when you generate tags, descriptions, excerpts, or images, the relevant post content is sent to the AI provider you configure. See the third-party services list in the Description for links to each provider's terms and privacy policy.<\/p><\/dd>\n Any vision-capable model: for example Yes. In settings you can set a dedicated Text Model for text-only generation (image prompts, excerpts, URL-based descriptions) when your main model is vision-only.<\/p><\/dd>\n FAL.AI offers many text-to-image models. The plugin includes popular choices out of the box: FLUX.1 (schnell, dev, pro), Stable Diffusion 3.5, Ideogram V2, and Recraft V3. The list is populated from FAL.AI's live catalog and cached for 12 hours, so new models appear automatically. You can also enter a custom model ID.<\/p><\/dd>\n It uses a two-step process. First, the AI reads your entire post and distills it into a visual theme. Second, that theme is turned into a creative image prompt. You can preview and edit the prompt before submitting it to FAL.AI. The image is generated asynchronously via FAL.AI's queue API, then sideloaded into your media library and set as the post's featured image.<\/p><\/dd>\n You can choose from six preset sizes: Square HD (1:1), Square (1:1), Portrait 4:3, Portrait 16:9, Landscape 4:3, and Landscape 16:9. The default is Landscape 16:9.<\/p><\/dd>\n Yes. Paste one or more URLs into the description meta box and Kwik AI will scrape the page content, summarize it, and generate a description based on that summary.<\/p><\/dd>\n Four tones: Technical<\/strong> (precise and factual), Straight<\/strong> (clear and direct), Excerpt<\/strong> (editorial style that teases the central idea), and Pithy<\/strong> (lively and compact). Length ranges from 20 to 80 words.<\/p><\/dd>\n\n<\/dl>\n\n\n\n
\n
\n
gemma3:27b<\/code> or llava:13b<\/code> for Ollama; gpt-4o<\/code> for OpenAI).<\/li>\n\n
Do I need an API key?<\/h3><\/dt>\n
Does this send my content to a third party?<\/h3><\/dt>\n
What models work for image analysis?<\/h3><\/dt>\n
gemma3:27b<\/code> or llava:13b<\/code> on Ollama, openai\/gpt-4o<\/code> on OpenRouter, or gpt-4o<\/code> \/ gpt-4o-mini<\/code> on OpenAI.<\/p><\/dd>\nCan I use a different model for text-only tasks?<\/h3><\/dt>\n
Which image models are available for featured images?<\/h3><\/dt>\n
How does featured image generation work?<\/h3><\/dt>\n
What image sizes can I generate?<\/h3><\/dt>\n
Can I generate descriptions from URLs?<\/h3><\/dt>\n
What excerpt tones are available?<\/h3><\/dt>\n
3.1<\/h4>\n\n
\n
\/chat\/completions<\/code> with a fallback to \/api\/generate<\/code>.<\/li>\nmax_tokens<\/code> by retrying with max_completion_tokens<\/code>.<\/li>\n<\/ul>\n\n3.0<\/h4>\n\n
\n