Create a coordinated REDnote (Xiaohongshu) OOTD lookbook from outfit photos or a styling idea. Build a vertical 3:4 fashion carousel with a cover, full-look outfit image, styling-detail image, and lifestyle scene, then shape a ready-to-publish fashion recommendation post with title ideas, caption angles, and tags. Use this AI outfit image maker for Xiaohongshu outfit posts, OOTD photos, fashion lookbooks, clothing recommendation visuals, creator style diaries, and brand collaboration campaigns. Optionally it reads Xiaohongshu itself — the notes already running for the topic, one page of a note's top comments, and an account's own recent notes — so Xiaohongshu research, competitor note analysis and comment analysis rest on the platform instead of on guesswork.
Design & media
REDnote OOTD Lookbook Maker
Try itCreate a coordinated REDnote (Xiaohongshu) OOTD lookbook from outfit photos or a styling idea. Build a vertical 3:4 fashion carousel with a cover, full-look outfit image, styling-detail image, and lifestyle scene, then shape a ready-to-publish fashion recommendation post with title ideas, caption angles, and tags. Use this AI outfit image maker for Xiaohongshu outfit posts, OOTD photos, fashion lookbooks, clothing recommendation visuals, creator style diaries, and brand collaboration campaigns.
What it does
Create a coordinated REDnote (Xiaohongshu) OOTD lookbook from outfit photos or a styling idea. Build a vertical 3:4 fashion carousel with a cover, full-look outfit image, styling-detail image, and lifestyle scene, then shape a ready-to-publish fashion recommendation post with title ideas, caption angles, and tags. Use this AI outfit image maker for Xiaohongshu outfit posts, OOTD photos, fashion lookbooks, clothing recommendation visuals, creator style diaries, and brand collaboration campaigns.
The skill document
REDnote OOTD Lookbook Maker
Create an ordered REDnote (Xiaohongshu) OOTD lookbook that gives one outfit a complete visual story: a cover, full-look image, styling detail, and lifestyle scene. Pair the visual sequence with a practical post angle, title ideas, caption beats, and tags in the user's voice.
Scope and routing
Use this Skill for a coordinated outfit-led carousel, a fashion diary, a clothing recommendation post, or brand collaboration campaign where the creator wants multiple images to feel like one story. A typical request starts with an outfit photo, mirror selfie, flat lay, garment image, or a clear styling concept.
For one isolated REDnote cover, route to rednote-cover-maker. For a
market-specific on-model ecommerce visual from a confirmed wearable SKU, route
to product-on-model-locale-studio. Keep the user's stated garment details,
accessories, occasion, and visual references central whenever this Skill owns
the lookbook.
Inputs and defaults
Reuse the conversation's outfit, occasion, target audience, style vocabulary, and references. A source outfit photo or a concrete styling idea is the minimum hard input. Ask only for a missing choice that materially changes the visual story: the outfit, the intended occasion, or the style direction.
With an outfit photo, use it as the first ordered reference for every outfit-preserving image. With a styling idea, create an original lookbook from the user's described garments, palette, occasion, and mood.
Default to a four-slide vertical 3:4 lookbook at 2K, delivered as one
coordinated sequence when the live model card accepts count: 4 and
output_relationship: "sequence":
- Cover — a clear outfit introduction with clean title space.
- Full look — a readable head-to-toe view that makes the silhouette and layering easy to understand.
- Detail — the material, accessory, color relationship, or styling move that makes the outfit memorable.
- Lifestyle scene — an occasion-led final image that carries the look's mood.
Keep model: "auto" and model-managed controls unless the user asks for a
model, compatibility, or price decision. Read beatra.models.list for the
selected image_to_image, text_to_image, or image_edit capability before
fixing a model, canvas, control, count, output relationship, or current price.
When the live card does not accept the coordinated four-image sequence, present
its compatible routes and their maximum charge before the user selects any
different paid plan.
Golden path
- Build one lookbook card: outfit must-keeps, occasion, audience, story angle, palette, light, setting, title-safe placement, and each slide's role.
- Choose the route:
beatra.images.transformfor a source outfit photo;beatra.images.generatefor a styling idea;beatra.images.editfor a focused revision to an accepted slide. - Draft the four prompts as one visual family. Keep source and later reference roles explicit, and create the post angle, title ideas, caption beats, and tags before paid execution.
- Read the live model card, then show one confirmation containing the ordered four-slide sequence, all slide roles, the complete prompt, ordered references, canvas, count, output relationship, model behaviour, current maximum charge, and call count.
- After approval, assign the coordinated sequence one stable opaque
client_request_id, submit it once through the bundled client, and retain the returned task ID. - Poll the original task, review accessible outputs against the lookbook card, and deliver the images in post order with the caption plan and actual returned image and billing facts.
Read lookbook planning to shape the visual story and lookbook workflow for exact route, prompt, confirmation, polling, and recovery details.
Decisions that require confirmation
Planning, post writing, and prompt drafting are free. Before any image generation or revision, obtain one clear confirmation of the frozen lookbook card, every paid image request, source and reference order, canvas, model, controls, count, current price, maximum charge, and total call count.
Every changed outfit, source or reference order, prompt, slide role, canvas,
model, count, output relationship, or control is a new paid request with a new
confirmation and a new client_request_id. A focused revision to an accepted
slide is also fresh paid work.
Execute and deliver
Use only this package's bundled scripts/mcp_client.py for every remote
operation. Send one JSON object on standard input after call .
Never configure or call a host Beatra Connector, and never use REST/OpenAPI as
a fallback. Read Bundled MCP Client diagnostics
for commands and connection troubleshooting.
For source-photo routes, upload the local file and put its returned artifact at
images[0] in the transform request. Later images may guide composition,
palette, setting, or styling in the stated order. For a concept-only route,
use beatra.images.generate with the selected vertical canvas. For a focused
revision, use the accepted slide as images[0] with beatra.images.edit.
Register the package through beatra.installations.register on first use. A
returned task_id belongs to the original approved work: poll it only with
beatra.tasks.get. When a create response is genuinely unknown, retain the
same frozen payload and client_request_id; if the task ID is missing, use
beatra.tasks.list and verify a candidate with beatra.tasks.get before any
replay. Use beatra.tasks.cancel only at the user's request. If cancellation
returns 409, keep polling the original task and report cancellation only after
its terminal status is canceled.
Review accessible images against the approved outfit must-keeps, slide role,
3:4 composition, visual continuity, and title-safe placement. Deliver only
facts returned by the completed tasks: artifact links, dimensions, format,
resolved model, task IDs, and billing.net_charged_credits. Present the
ordered lookbook, cover and slide roles, title ideas, caption beats, tag set,
and any visible drift that matters to the user's next revision.
References by task
- For the lookbook card, four-slide defaults, source-reference roles, and post angle: lookbook planning.
- For precise transform, concept, edit, confirmation, task tracking, recovery, and review: lookbook workflow.
- For first use or expired credentials: installation and authentication.
- For the non-billable installation registration: installation registration.
- For task fields and polling: tasks and results.
- For balance, validation, and structured errors: billing, errors, and recovery.
- For client commands and diagnostics: Bundled MCP Client diagnostics.
- For removal: uninstall and disconnect.
Runtime and safe automatic updates
The bundled client silently checks at most once every 24 hours per installation. When a newer release is available, it installs automatically without separate confirmation. It uses only the fixed official Beatra discovery address and immutable CDN path for this package, channel, and locale. Before replacement, it verifies discovery data, manifest, archive, and every packaged file using the expected identity, size, and SHA-256 values, then replaces only package-owned files in the installed Skill directory.
Checks, downloads, verification, replacement, rollback, and recovery fail open: the current installation stays usable and the original command continues. The setting persists for this installation. Read automatic updates and safety for the official sources, integrity checks, replacement boundary, failure behaviour, and controls.
python3 scripts/mcp_client.py update --auto off
python3 scripts/mcp_client.py update --auto on
python3 scripts/mcp_client.py update --check
Related skills
Turn a photo, a topic idea, or an accepted draft into a scroll-stopping REDnote (Xiaohongshu) cover and post image. This AI cover generator creates vertical 3:4 Xiaohongshu note covers with clean backgrounds, bold focal composition, and text-safe areas for beauty, food, fashion, travel, and knowledge content. Generate high-click Xiaohongshu note covers, OOTD post images, food photography covers, product recommendation visuals, and lifestyle note illustrations from one photo or a topic description. Start from a real photo, compose from multiple references, or refine an accepted cover toward a publish-ready result.
Create a Xiaohongshu or REDnote carousel from a post outline, product details, photo set, or style reference. Build an ordered 3:4 image sequence with a hook cover and supporting slides, clear focal imagery, matched visual direction, and headline-safe areas for product recommendations, tutorials, food notes, OOTD, travel guides, knowledge posts, and Xiaohongshu content images for one connected post story.
Create a Xiaohongshu or REDnote carousel from a post outline, product details, photo set, or style reference. Build an ordered 3:4 image sequence with a hook cover and supporting slides, clear focal imagery, matched visual direction, and headline-safe areas for product recommendations, tutorials, food notes, OOTD, travel guides, knowledge posts, and Xiaohongshu content images for one connected post story. Optionally it reads Xiaohongshu itself — the notes already running for the topic, one page of a note's top comments, and an account's own recent notes — so Xiaohongshu research, competitor note analysis and comment analysis rest on the platform instead of on guesswork.
Create a Xiaohongshu food post or REDnote food post from a dish photo, restaurant visit theme, or dining-atmosphere reference. This REDnote food image maker plans restaurant review images and AI food photography as a vertical 3:4 food-note sequence: a cover, dish close-up, table or restaurant atmosphere image, and a final detail image for a food recommendation post. Shape title ideas, caption angles, and tags for a restaurant review post, cafe-hopping post, new-menu launch post, restaurant visit images, food diary images, and restaurant social media images.
Create Xiaohongshu beauty and skincare content from product facts, routine steps, skin concerns, and audience context. This AI beauty note maker produces a 3:4 post concept, review structure, usage-scene copy, title options, cover wording, relevant hashtags, and a natural comment starter for makeup, skincare, haircare, body care, routines, comparisons, and product recommendations.