Generate OG Share Image
Social preview art + ready-to-paste meta tags
Generate OG Share Image
Social preview art + ready-to-paste meta tags
Showcase
Description
Paste a webpage URL to generate a link preview image (OG image/social preview card) for display when shared on WeChat, Twitter/X, LinkedIn, or Slack. You’ll also get ready-to-paste og / twitter meta tags. The title, subtitle, and data are extracted from the page itself—nothing is made up. Branding is represented with text only; no fake logos are drawn. The design direction is selected automatically based on the page type: editorial layouts for personal blogs, branded gradients for product homepages, high-contrast minimalism for developer tools, and information cards when real data is available. 2026.10 update: · Upgraded to GPT Image 2.5 for more accurate text rendering in images; · All images are now generated in 16:9, with text and brand names placed in the central safe area so they won’t be cropped when center-cropped to 1200×630; crop guidance is included with delivery; · Meta tag width and height now match the actual published dimensions instead of conflicting with the image; · Design directions are no longer limited to seven rigid options and are combined flexibly based on the page content; · Less common pages such as login and privacy policy pages no longer require confirmation—the site-wide default image is generated directly; · Repeated rules have been streamlined. One image is generated by default, reducing unnecessary generations and credit usage.
Recommended by
Dancang
Why we love this skill
Extracts real page information, matches a proven OG layout, and delivers a 1200×630 image with paste-ready Open Graph and Twitter meta tags—without fabricated logos or data.
Related Skills
View all
ImageLanding Page & OG Pro v2.0
Built a product but stuck on the landing page? Generic templates look obviously AI-made, while designing one yourself can eat up an entire weekend. Landing Page & OG Pro turns a one-line product idea into a polished landing page you can preview and publish directly, plus a matching link-sharing image. Just explain what your product is and who it’s for. You can also paste existing copy or a URL. It chooses the best fit from 32 designer-crafted visual systems, carries over the system’s fonts, colors, and decorative details, and lays out your content as a scrolling landing page with everything you need: hero section, pain points, how it works, what you’ll get, and a call-to-action button. You’ll get: - A web page you can open and preview directly—not a pile of code pasted into the chat. It also displays properly on mobile. - A cohesive visual design: the fonts, colors, spacing, and decorative details come from one established design system rather than being pieced together. - A matching OG sharing image: when you share the link on WeChat, X, or Slack, the preview card and page use the same style, with text kept inside the safe area so it won’t be cropped. - Clean, credible copy: it only uses the information you provide and reasonable value statements. It doesn’t invent testimonials, user counts, or data. - Want to change the style, revise the copy, adjust the colors, or switch to your brand colors? Just say so. It avoids the usual blue-and-purple tech look by default; if your brand is already blue or purple, it follows your brand. What’s new in v2.0: - The result is a true scrolling landing page, not a paged slideshow. - Once there’s enough information, it generates the page directly instead of first asking about the setting and mood or creating three preview images. It’s faster and uses fewer credits. - Added a matching OG sharing image with the same title as the landing page. - It no longer invents testimonials, user counts, or data. Ideal for indie developers, product launches, waitlist pages, personal portfolios, event sign-up pages, and Newsletter subscription pages.
ImageSong-Style Covers-SagaSu
Generate Song Dynasty-inspired cover images for articles, blogs, and social media, with aspect ratios for multiple platforms and direct delivery as high-quality PNGs. 🆕 **Updated October 2026** • Upgraded to GPT Image 2.5 for direct image generation, with more accurate Chinese title rendering and finer textures for xuan paper, gilded gold, and distant mountains • Removed the intermediate process of writing SVG code, rendering it in a browser, and converting a screenshot to PNG—each generation now produces a finished image directly • Removed the second confirmation step for a “preview / full version”; provide a title and the cover is generated directly • Significantly reduced intermediate steps and generated code, making image generation faster and using fewer credits • Added **Premium Mode**: request more detailed visuals for key art and posters • SVG source files are still available on request, suitable for precise pixel dimensions or consistent series templates ✨ **Core Features** • Follows three core principles of Song Dynasty aesthetics: negative space takes center stage, less is more precise, and artistic conception matters more than form • A celadon blue × gilded gold color system, with gilded gold used only for outlining—not glowing effects • Six motifs: ripples on water, echo walls, mountain ridgelines, brushstrokes and ink marks, architectural eaves, and lunar-phase arcs • Automatically selects motifs based on the mood of the topic, using Southern Song corner composition with 70–80% negative space 📱 **Use Cases** • WeChat Official Account covers and Zhihu/Twitter headers (16:9) • Square images (1:1) and vertical images for Xiaohongshu and Instagram • Personal blog, podcast, and brand campaign covers 🎯 **How to Use** Just provide a title. A subtitle, motif, byline, and platform are optional. You’ll receive a finished cover directly.
ImageCharacter Portraits—sagasu
Turn 1–8 characters into a single star-studded group portrait: anthropomorphized AI models, virtual idols, game characters, famous IP characters, and brand mascots are all supported. Each character gets their own colors, outfit, props, and pose, arranged at different depths and interacting with one another instead of standing in a row. Each person also gets a text card with their name, tags, and a line of dialogue. 🆕 Updated October 2026 · Upgraded to GPT Image 2.5: Flare is used by default for fast image generation; say “premium / poster / key visual / high resolution” to automatically switch to Sunburst for more accurate Chinese cards and a finish closer to an official promotional image · Generate directly when there’s enough information: the “show the complete plan first and wait for confirmation” step has been removed. When information is missing, all necessary questions are asked at once instead of asking about each character individually · Better at getting the references right: AI models and famous IP characters use widely recognized public personas and designs by default, such as DeepSeek’s blue, chubby fish · Less crowding: for 5–8 people, cards are automatically simplified to “name + one line of dialogue” · Uses fewer credits: the outdated multi-model fallback and retry chain has been removed, reducing wasted generations and back-and-forth conversation so the same image costs fewer credits Examples: “Turn Claude, GPT, Gemini, and DeepSeek into a group portrait using their public personas, landscape format” or “Draw portraits of my 4 original characters, vertical phone wallpaper”
Information
- Version
- v4
- Last updated
- Runtime credits
- Usage-based
- Models
- Auto
