Generate editorial images at publishing volume
Use case: Generate article heroes and social cards at publishing volume
Every published article needs at least a hero image, and most editorial teams need a second cropped version for social cards — yet stock photography is generic, licensed photo libraries get expensive at scale, and a design queue that hand-crafts two images per article becomes the bottleneck on publishing day. Webanto's editorial imagery use case generates both directly from the article's headline and summary, using Qwen-Image — an open-licence image model Webanto self-hosts on dedicated GPU hardware — called through POST /api/v1/images. Because output is billed per image and scales with resolution, a newsroom or content team publishing dozens of pieces a week can generate a hero and a social crop for every article without waiting on a designer or paying per-download stock licensing fees, while keeping final publish approval in human hands.
What to expect
Every article gets a distinct, headline-relevant hero image instead of a generic or repeated stock photo pulled from the same handful of libraries every other site uses.
No per-download stock licensing fees and no waiting on a design queue — generation can happen the moment a draft is ready for review, not after it clears a separate design backlog.
Social card variants generated alongside the hero in the same workflow, keeping visual style consistent between the article page and its social distribution.
Usage-based cost that tracks publishing volume directly, so a quiet week costs little and a high-output week doesn't require negotiating a new stock subscription tier.
How to set this up
- 1
Create a Webanto API key under Settings > API and store it server-side as WEBANTO_API_KEY — image generation should be called from your CMS backend or publishing pipeline, not the browser.
- 2
Define two prompt templates keyed off the article's headline and dek: one tuned for a wide hero crop (roughly 16:9), one for a square or vertical social card, both referencing a fixed house style so articles don't look inconsistent day to day.
- 3
Hook the generation call into your publishing workflow — for example a step that fires when an article moves from draft to ready-for-review — calling POST https://api.webanto.com/api/v1/images with model set to qwen-image and the appropriate prompt and size for each crop — 1664x928 for a 16:9 hero, 1328x1328 or 928x1664 for social cards.
- 4
Work out the monthly credit budget: a 1664x928 hero (about 1.5 megapixels) runs 7 credits and a 1328x1328 social card runs 8, so 40 articles a month at two images each is roughly 40 x 15 = 600 credits, comfortably inside the Starter plan's 10,000/mo allowance.
- 5
Route generated images to an editor review step before publish, checking the image actually matches the article's subject and doesn't contain garbled on-image text, which image models still get wrong at times.
- 6
Store the approved image and its prompt together in your CMS so a rejected generation can be regenerated with a refined prompt rather than starting from a blank slate.
- 7
Track credit spend against publishing cadence over the first month and adjust plan tier or prompt resolution if a high-output week runs close to the monthly allowance.
Products that power this use case
Frequently asked questions
Will every article look visually similar if they're all generated by the same model?
Only if the prompts are similar. Style consistency — colour palette, illustration versus photographic look — should come from a fixed style clause you reuse across prompts; subject variety should come from feeding in the article's actual headline and key subject each time. Teams that copy-paste one generic prompt across every article get repetitive results — the model isn't the limiting factor, the prompt is.
Can the model put readable text or a headline directly into the image?
Qwen-Image renders short, legible text far better than most image models, but long headlines still come out wrong at times. For anything that must be exact, overlay the headline as a text layer on top of the generated image using your CMS or design tool rather than asking the model to render it.
What if the article is about a real, named person or a specific news event?
This is a genuine limitation worth flagging: generating a recognisable likeness of a real public figure, or an image that could be mistaken for a real photograph of a breaking news event, carries both a misinformation risk and a legal risk around depicting real people. For hard news and anything naming a real individual, use a real photo, wire-service image, or an abstract, non-likeness illustrative image — not a photorealistic generated stand-in.
How does the cost compare to a stock photo subscription?
It depends on volume and your current subscription tier, but the mechanism is different: stock subscriptions are a fixed monthly fee regardless of usage, while generation is billed per image at roughly 5-6 credits (a credit is $0.01 at overage), so cost tracks your actual publishing output rather than a flat licence fee. High-volume publishers with irregular output tend to see the largest relative saving.
Do we still need a photographer or illustrator on staff?
For routine daily content, generated imagery covers a large share of what a stock subscription used to. For flagship investigative pieces, interviews, or anything where an actual photograph of a real subject is the point of the image, you still need real photography or licensed press imagery — generation complements editorial visuals, it doesn't fully replace them.
Other use cases
Let shoppers search your catalogue with a photo
Shoppers who spot a product in the wild, on someone else's feed, or on a competitor's site rarely know the right keywords to find it in your catalogue. Visual search closes that gap: a shopper uploads
Find near-duplicate images in a large media library
Large media libraries accumulate redundancy fast — the same product shot re-exported at a different crop, a stock photo uploaded twice under different filenames, a banner re-saved at a lower compressi
Reverse image search against your own image library
Reverse image search answers a narrower question than catalogue browsing: given one photo someone just handed you — a screenshot, a competitor's product shot, a customer's snapshot of a damaged item —
Related resources
AI Overviews
GlossaryAI Overviews are AI-generated summary answers that appear at the top of Google search results, synthesising information from multiple ranking pages and citing them as sources.
Data Synchronization
ServiceWebanto for Travel: itinerary nurturing and destination loyalty
IndustryTour operators, OTAs, destination marketing organisations, and travel agencies sell high-consideration, high-emotion purchases where the decision cycle can be 3-9 months and the post-trip glow is the best time to secure the next booking. Most still send the same 'book now for summer' blast to everyone regardless of whether the recipient just returned from a safari or is dreaming of a family beach holiday in 18 months. Webanto connects booking, itinerary, and CRM data so pre-trip, on-trip, and post-trip sequences reference the exact destinations, dates, and traveller profile — while respecting the strict consent and data-protection rules of every source market.
Pillar Page
GlossaryA pillar page is a long-form, comprehensive page on a broad topic that links out to and is linked from a network of shorter, related 'cluster' pages, used to signal topical authority to search engines.
Incorporating AI into Your Website Design: Pros and Cons
BlogAI in web design: a game-changer or a risk? Weigh in! 🤖⚖️
How to Leverage AI-Driven Tools for Smarter Marketing Campaigns
BlogBoost your marketing with AI-driven tools! 🚀 Discover smarter strategies today! 🤖
Ready to try it?
Start a 14-day free trial on any paid plan. Cancel before it ends and you won't be charged.

