Turn three named new-item stills into a launch board you can post, then turn the rest of the set into a matching pack. This store new item launch studio writes a new-item still set and launch poster from the facts you already have. Use it for cafe launches, retail restocks, and chain-store new-item boards.
编程
Crowdfunding Gallery Stills
试用Turn a written campaign and reward-tier plan into one gallery still per named slot. This crowdfunding gallery studio lays out each named reward-tier still and campaign scene as its own still. Use it for Indiegogo gallery stills, Kickstarter gallery frames, reward-tier tiles, and campaign gallery sets.
它能做什么
Turn a written campaign and reward-tier plan into one gallery still per named slot. This crowdfunding gallery studio lays out each named reward-tier still and campaign scene as its own still. Use it for Indiegogo gallery stills, Kickstarter gallery frames, reward-tier tiles, and campaign gallery sets.
技能文档
Crowdfunding Gallery Stills
Turn a written campaign and reward-tier plan into one gallery still per named slot. Use this Skill when a crowdfunding page needs gallery stills or reward-tier tiles that follow the plan already on file, not a six-slot product listing gallery.
Use ecommerce-listing-image-set when the seller wants a hero, lifestyle,
and detail gallery for one SKU. Use amazon-a-plus-module-pack when the
work is Amazon A+ selling-point modules. Keep a later
kickstarter-reward-tile package for a single perk tile when that
package is installed. Do not look up public posts or live campaign pages
for missing perks or prices.
Collect the written plan
Hard inputs are the exact campaign or product name and the already-written reward-tier or gallery plan that will appear on the stills. Do not invent a perk, price, stretch goal, backer count, or ship date to finish a slot. Reuse platform (Indiegogo, Kickstarter, or another gallery), language, palette, and must-keeps already in the conversation.
Ask only for facts that change a still:
- exact campaign or product name;
- each named gallery or reward-tier slot in the writer's words, with any price they already approved;
- destination gallery and language; and
- an optional product or brand still if the set should match that look.
A photo is a visual reference, not a source for missing perks. Uploading makes media available to Beatra and does not inspect it. When the host cannot view a file, keep the writer's declared role for it.
Default to one still per named gallery or reward-tier slot. If the writer wants a standard set and has not numbered the slots, plan up to four stills from the facts already given: campaign hero, product still, reward-tier tile, and use scene. Leave a slot whose fact is missing on the plan. A single-tile request stays one still.
Keep the same product look, palette, and lighting across the set so the stills read as one campaign gallery.
Plan the free gallery
Write a labeled gallery plan before any paid image. For each slot record the campaign name, reward or scene line, language, visual role, canvas, and any optional reference role. That plan is the free visible result. Planning is not approval.
Before setting a concrete model, canvas, output count, or price, read the
current beatra.models.list card for text_to_image. Keep model as
auto and count at 1 per still. A writer who wants another
candidate adds a distinct slot and approves that new work.
Use beatra.images.edit only after the writer accepts a still and asks
for a local correction, with that accepted image as images[0].
Read crowdfunding gallery workflow when writing the payload or recovering a task.
Confirm once, create by slot
Planning is free. Before the first billable call, show one current production card and wait:
- Work — one crowdfunding gallery still per named slot, a generate
call (
beatra.images.generate). - Credits — the live
text_to_imageprice just read. Do not reuse a remembered number. - Count — one paid call per still. Do not batch several slots into
one
count. - Identity — one new opaque
client_request_idper still. A changed prompt, perk line, file, model, or canvas mints a new ID. - If we stop here — the labeled gallery plan remains usable.
- If the balance is insufficient — relay the official message and its
top-up URL exactly (
https://console.beatra.ai/wallet?intent=buy). Translate the prose; keep the URL. Do not retry until the writer says they have topped up. Do not recommend ¥198.
Submit once through bundled scripts/mcp_client.py. Poll
beatra.tasks.get. Deliver actual bytes plus
billing.net_charged_credits. Do not promise the prepaid estimate is
the final charge.
After approval, submit each still once. Keep no more than two generation tasks in flight on one connection.
Review, deliver, and recover
Review printed claims against the confirmed gallery plan. Report only the text the host can actually see. Treat generated small type as a review item, not as a live campaign perk.
Deliver the stills in slot order, the gallery plan, observed dimensions
and formats, task IDs, resolved models, and returned
billing.net_charged_credits. A focused correction is new paid work
with its own card and ID.
After a returned task_id, poll that task. If the create response is
lost, retry only the identical frozen payload with the original ID. If
the task ID is missing, use beatra.tasks.list and verify candidates
with beatra.tasks.get before another submit. Use beatra.tasks.cancel
only when the writer asks.
Execution
Invoke every remote Beatra operation only through this package's bundled
scripts/mcp_client.py. Put the MCP tool name after call and send one
JSON object on standard input.
python3 scripts/mcp_client.py call beatra.models.list
{"capability": "text_to_image"}
printf '%s' '{"prompt":"Create the approved crowdfunding gallery still for the named slot. Show only the confirmed campaign name and written reward or scene line. Keep the shared gallery look.","model":"auto","count":1,"canvas":{"type":"preset","tier":"2K","aspect":"16:9"},"client_request_id":"opaque-gallery-01"}' | python3 scripts/mcp_client.py call beatra.images.generate
Do not configure or call a host Beatra Connector, and do not use REST/OpenAPI as a fallback.
References by task
- For gallery lists, payloads, confirmation, polling, recovery, and review, read crowdfunding gallery workflow.
- For authorization and the non-billable registration step, read installation and authentication and installation registration.
- For shared task, billing, and connection details, read tasks and results, billing, errors, and recovery, and Bundled MCP Client diagnostics.
- For update guarantees and controls, read automatic updates and safety. For removal, read uninstall and disconnect.
Runtime and safe automatic updates
The bundled client silently checks for a newer release at most once every 24 hours per installation. When a newer version is available, it installs automatically without separate confirmation. It downloads only from the fixed official Beatra discovery and immutable CDN paths for this package, channel, and locale, verifies discovery data, archive, manifest, and every packaged file, and replaces only package-owned files.
Update checks, downloads, verification, replacement, rollback, and recovery fail open: the current installation remains usable and the original command continues. An update failure never authorizes retrying a paid image request. The setting persists for this installation. See automatic updates and safety.
python3 scripts/mcp_client.py update --auto off
python3 scripts/mcp_client.py update --auto on
python3 scripts/mcp_client.py update --check
相关技能
Turn a topic description, a product photo, or brand references into a scroll-stopping event poster, promotional banner, or social media graphic. This AI poster maker and design generator creates photo-rich posters with strong visual hierarchy, category-matched styling, and text-safe zones for event, music, movie, product launch, and sale campaigns. Use it as an AI flyer maker for sale flyers, an event poster design tool, a movie poster generator, a music festival poster creator, a banner design AI for product launch posters, or a graphic design poster studio. Start from a campaign topic, transform a product or scene photo with style references, or refine an accepted draft toward a print-ready or share-ready result.
Turn contractor-supplied project names, unit names, and handover dates into three handover sign stills, then turn the rest of that project into a matching set. This project handover sign studio lays out each named completion board from the inscriptions you already have. Use it for project completion signs, handover sign boards, and matching completion-sign packs.
Turn a confirmed new-drop script and authorized stills into one drop talking clip per still. This product drop video studio writes a speakable launch talking clip and new-drop announcement for each photo, then animates a 2 to 15s talking teaser. Use it for creator drop videos and talking teasers that stay one photo, one clip.
从需求收集到样图交付的营销宣传册设计流程，版式确认后才进入样机生成阶段。
67 次安装
Turn a script, scene, or ad brief into a structured AI storyboard plan with a practical shot list and one to four storyboard key-frame images. Plan shot types, camera angles and movement, action, timing, dialogue, and sound for short films, ads, animation, social video, motion comics, and creative pitches.