Skip to content
social-media-carousel logo

Social Media Carousel

social-media-carousel

Multi-slide carousel design for Instagram, LinkedIn, and Twitter/X with layout rules and hooks. Covers slide structure, text hierarchy, swipe psychology, and platform-specific specs. Use for: carousel posts, Instagram carousels, LinkedIn carousels, slide posts, educational content. Triggers: carousel, instagram carousel, linkedin carousel, slide post, carousel design, swipe post, multi-image post, carousel template, educational carousel, carousel content, instagram slides, linkedin slides

inference-sh/skills1Kinstalls760stars

SKILL.md

Full skill instructions

Install the belt CLI skill: npx skills add belt-sh/​cli

Social Media Carousel

Design high-engagement carousel posts via inference.sh CLI.

Quick Start

Requires inference.sh CLI (belt). Install instructions

belt login

# Generate a carousel slide
belt app run infsh/​html-to-image --input '{
  "html": "<div style=\"width:1080px;height:1080px;background:#0f172a;display:flex;align-items:center;justify-content:center;padding:80px;font-family:system-ui;color:white;text-align:center\"><div><p style=\"font-size:24px;color:#818cf8;text-transform:uppercase;letter-spacing:3px\">5 Rules for</​p><h1 style=\"font-size:64px;margin:16px 0;font-weight:900;line-height:1.1\">Writing Headlines That Convert</​h1><p style=\"font-size:22px;opacity:0.5;margin-top:24px\">Swipe →</​p></​div></​div>"
}'

Platform Specs

PlatformDimensionsSlidesAspect Ratios
Instagram1080 x 1080 pxUp to 201:1 (default), 4:5, 16:9
LinkedIn1080 x 1080 px or 1080 x 1350Up to 201:1, 4:5
Twitter/​X1080 x 1080 pxUp to 41:1, 16:9
Facebook1080 x 1080 pxUp to 101:1, 4:5

Use 1080 x 1350 (4:5) on Instagram and LinkedIn — takes up more screen real estate in the feed than square.

Carousel Structure

The 7-Slide Framework

SlidePurposeContent
1HookBold claim, question, or promise — stops the scroll
2ContextWhy this matters, set up the problem
3-6ValueOne point per slide, numbered
7CTAFollow, save, share, comment, visit link

Slide 1: The Hook

The most important slide. If this fails, nobody swipes.

Hook TypeExample
Bold claim"90% of landing pages make this mistake"
Question"Why do your ads get clicks but no conversions?"
Number + promise"7 Python tricks I wish I learned sooner"
Contrarian"Stop writing blog posts (do this instead)"
Before/​afterShow transformation
# Hook slide
belt app run infsh/​html-to-image --input '{
  "html": "<div style=\"width:1080px;height:1350px;background:linear-gradient(180deg,#1e1b4b,#312e81);display:flex;align-items:center;justify-content:center;padding:80px;font-family:system-ui;color:white;text-align:center\"><div><h1 style=\"font-size:72px;font-weight:900;line-height:1.15;margin:0\">90% of Landing Pages Make This Mistake</​h1><p style=\"font-size:28px;opacity:0.6;margin-top:32px\">Swipe to find out →</​p></​div></​div>"
}'

Slides 2-6: Content Slides

One point per slide. Never cram multiple ideas.

# Content slide template
belt app run infsh/​html-to-image --input '{
  "html": "<div style=\"width:1080px;height:1350px;background:#1e1b4b;padding:80px;font-family:system-ui;color:white;display:flex;flex-direction:column;justify-content:center\"><div><p style=\"font-size:120px;font-weight:900;color:#818cf8;margin:0;line-height:1\">01</​p><h2 style=\"font-size:48px;margin:24px 0 16px;font-weight:800;line-height:1.2\">Your headline is too vague</​h2><p style=\"font-size:26px;opacity:0.8;line-height:1.6\">\"Welcome to our platform\" tells the visitor nothing. Lead with the outcome: \"Ship docs in minutes, not days.\"</​p></​div></​div>"
}'

Slide 7: CTA Slide

# CTA slide
belt app run infsh/​html-to-image --input '{
  "html": "<div style=\"width:1080px;height:1350px;background:linear-gradient(180deg,#312e81,#1e1b4b);display:flex;align-items:center;justify-content:center;padding:80px;font-family:system-ui;color:white;text-align:center\"><div><h2 style=\"font-size:56px;font-weight:900;margin:0;line-height:1.2\">Found this useful?</​h2><p style=\"font-size:32px;opacity:0.8;margin-top:24px;line-height:1.5\">Save this post for later 🔖<br>Follow for more tips</​p><p style=\"font-size:24px;opacity:0.4;margin-top:40px\">@yourusername</​p></​div></​div>"
}'

Design Rules

Text Hierarchy

ElementSize (at 1080px)Weight
Slide number96-120pxBlack (900)
Heading48-64pxBold (700-800)
Body text24-28pxRegular (400)
Caption/​tag18-22pxMedium (500)

Readability

RuleValue
Max words per slide30-40
Max lines of body text4-5
Line height1.5-1.6
FontSans-serif (Inter, Montserrat, Poppins)
Text contrast4.5:1 minimum (WCAG AA)

Visual Consistency

ElementKeep Consistent Across All Slides
Background color/​gradientSame palette, slight variations OK
Font familySame font throughout
Text alignmentSame position (left or center)
Margins/​paddingSame spacing
Accent colorSame highlight color
Numbering styleSame format (01, 02 or 1., 2.)

Carousel Types

Educational / Tips

Slide 1: "5 CSS tricks you need to know"
Slide 2: Trick 1 with code example
Slide 3: Trick 2 with code example
...
Slide 6: Trick 5 with code example
Slide 7: "Follow for more dev tips"

Storytelling / Case Study

Slide 1: "How we grew from 0 to $1M ARR"
Slide 2: The beginning (context)
Slide 3: The challenge
Slide 4: What we tried (failed)
Slide 5: What worked
Slide 6: The result (numbers)
Slide 7: Key takeaway + CTA

Before / After

Slide 1: "I redesigned this landing page"
Slide 2: Before screenshot
Slide 3: Problem 1 annotated
Slide 4: After screenshot
Slide 5: Improvement 1 explained
Slide 6: Results (conversion lift)
Slide 7: "Want a review? DM me"

Listicle / Tools

Slide 1: "10 tools every designer needs in 2025"
Slides 2-6: 2 tools per slide with logo + one-liner
Slide 7: "Save this for later 🔖"

Swipe Psychology

PrincipleApplication
Curiosity gapHook promises value that requires swiping
Numbered progress"3/​7" creates completion drive
Visual continuityConsistent design signals "there's more"
Increasing valueBest tip last — rewards completing
Swipe cueArrow or "Swipe →" on slide 1

Batch Generation

# Generate all slides for a carousel
for i in 1 2 3 4 5 6 7; do
  belt app run infsh/​html-to-image --input "{
    \"html\": \"<div style='width:1080px;height:1350px;background:#1e1b4b;display:flex;align-items:center;justify-content:center;padding:80px;font-family:system-ui;color:white'><div style='text-align:center'><p style='font-size:28px;opacity:0.5'>Slide $i of 7</​p></​div></​div>\"
  }" --no-wait
done

AI-Generated Carousel Visuals

# Generate illustrations for each slide
belt app run falai/​flux-dev-lora --input '{
  "prompt": "minimal flat illustration, person at desk with laptop, clean modern style, simple shapes, limited color palette purple and blue tones, white background, icon style",
  "width": 1080,
  "height": 1080
}'

Common Mistakes

MistakeProblemFix
Weak hook (slide 1)Nobody swipesBold claim, question, or number + promise
Too much text per slideOverwhelming, stops readingMax 30-40 words per slide
No visual consistencyLooks like different postsSame colors, fonts, margins throughout
No swipe indicatorPeople don't realize there's moreAdd "Swipe →" or arrow on slide 1
No CTA on last slideMissed engagement opportunityAsk to save, follow, share, or comment
Inconsistent numberingFeels disorganizedSame number format on every content slide
Cramming 2+ ideas per slideHard to digestOne point per slide, always
Square format on InstagramWastes feed real estateUse 1080x1350 (4:5) for more visibility

Related Skills

npx skills add inference-sh/​skills@ai-image-generation
npx skills add inference-sh/​skills@content-repurposing
npx skills add inference-sh/​skills@linkedin-content

Browse all apps: belt app list

More skills from inference-sh

ai-voice-cloning logo
inference-sh/skills

ai-voice-cloning

AI voice generation, text-to-speech, and voice synthesis via inference.sh CLI. Models: Inworld TTS-2 (100+ languages, emotion/non-verbal steering), Inworld TTS 1.5 (ultra-low latency), ElevenLabs (22+ premium voices, 32 languages), Kokoro TTS, DIA, Chatterbox, Higgs, VibeVoice for natural speech. Capabilities: multiple voices, emotions, accents, long-form narration, conversation, voice transformation, delivery mode control, character voices. Use for: voiceovers, audiobooks, podcasts, video narration, accessibility, gaming NPCs, avatar audio, UGC. Triggers: voice cloning, tts, text to speech, ai voice, voice generation, voice synthesis, voice over, narration, speech synthesis, ai narrator, elevenlabs, eleven labs, natural voice, realistic speech, voice ai, voice changer, inworld, inworld tts, character voice, npc voice

760 1K
View
ai-product-photography logo
inference-sh/skills

ai-product-photography

Generate professional AI product photography and commercial images. Models: FLUX, Imagen 3, Grok, Seedream for product shots, lifestyle images, mockups. Capabilities: studio lighting, lifestyle scenes, packaging, e-commerce photos. Use for: e-commerce, Amazon listings, Shopify, marketing, advertising, mockups. Triggers: product photography, product shot, commercial photography, e-commerce images, amazon product photo, shopify images, product mockup, studio product shot, lifestyle product image, advertising photo, packshot, product render, product image ai

760 1K
View
ai-music-generation logo
inference-sh/skills

ai-music-generation

Generate AI music and songs with ElevenLabs, Diffrythm, Tencent Song Generation via inference.sh CLI. Models: ElevenLabs Music (up to 10 min, commercial license), Diffrythm (fast song generation), Tencent Song Generation (full songs with vocals). Capabilities: text-to-music, song generation, instrumental, lyrics to song, soundtrack creation. Use for: background music, social media content, game soundtracks, podcasts, royalty-free music. Triggers: music generation, ai music, generate song, ai composer, text to music, song generator, create music with ai, suno alternative, udio alternative, ai song, ai soundtrack, generate soundtrack, ai jingle, music ai, beat generator, elevenlabs music, eleven labs music

760 1K
View
speech-to-text logo
inference-sh/skills

speech-to-text

Transcribe audio to text with ElevenLabs Scribe and Whisper models via inference.sh CLI. Models: ElevenLabs Scribe v2 (98%+ accuracy, diarization), Fast Whisper Large V3, Whisper V3 Large. Capabilities: transcription, translation, multi-language, timestamps, speaker diarization, audio event tagging. Use for: meeting transcription, subtitles, podcast transcripts, voice notes. Triggers: speech to text, transcription, whisper, audio to text, transcribe audio, voice to text, stt, automatic transcription, subtitles generation, transcribe meeting, audio transcription, whisper ai, elevenlabs stt, scribe, eleven labs transcribe

760 1K
View
javascript-sdk logo
inference-sh/skills

javascript-sdk

JavaScript/TypeScript SDK for inference.sh - run AI apps, build agents, integrate with all models. Package: @inferencesh/sdk (npm install). Full TypeScript support, streaming, file uploads. Build agents with template or ad-hoc patterns, tool builder API, skills, human approval. Use for: JavaScript integration, TypeScript, Node.js, React, Next.js, frontend apps. Triggers: javascript sdk, typescript sdk, npm install, node.js api, js client, react ai, next.js ai, frontend sdk, @inferencesh/sdk, typescript agent, browser sdk, js integration

760 1K
View
image-upscaling logo
inference-sh/skills

image-upscaling

Upscale and enhance images with Real-ESRGAN, Thera, Topaz, FLUX Upscaler via inference.sh CLI. Models: Real-ESRGAN, Thera (any size), FLUX Dev Upscaler, Topaz Image Upscaler. Use for: enhance low-res images, upscale AI art, restore old photos, increase resolution. Triggers: upscale image, image upscaler, enhance image, increase resolution, real esrgan, ai upscale, super resolution, image enhancement, upscaling, enlarge image, higher resolution, 4k upscale, hd upscale

760 1K
View
seo-content-brief logo
inference-sh/skills

seo-content-brief

SEO content brief creation with keyword research, search intent analysis, and content structure. Covers SERP analysis, heading hierarchy, word count targets, and internal linking strategy. Use for: content briefs, SEO writing, blog strategy, content planning, keyword targeting. Triggers: seo content brief, content brief, seo brief, keyword research, search intent, content strategy, blog brief, seo writing, content planning, keyword targeting, serp analysis, content outline, seo article, blog seo

760 1K
View
python-sdk logo
inference-sh/skills

python-sdk

Python SDK for inference.sh - run AI apps, build agents, and integrate with all models. Package: inferencesh (pip install inferencesh). Supports sync/async, streaming, file uploads. Build agents with template or ad-hoc patterns, tool builder API, skills, and human approval. Use for: Python integration, AI apps, agent development, RAG pipelines, automation. Triggers: python sdk, inferencesh, pip install, python api, python client, async inference, python agent, tool builder python, programmatic ai, python integration, sdk python

760 1K
View
data-visualization logo
inference-sh/skills

data-visualization

Data visualization with chart selection, color theory, and annotation best practices. Covers chart types (bar, line, scatter, heatmap), axes rules, and storytelling with data. Use for: charts, graphs, dashboards, reports, presentations, infographics, data stories. Triggers: data visualization, chart, graph, data chart, bar chart, line chart, scatter plot, data viz, visualization, dashboard chart, infographic data, data presentation, chart design, plot, heatmap, pie chart alternative

760 1K
View
customer-persona logo
inference-sh/skills

customer-persona

Research-backed customer persona creation with market data and avatar generation. Covers demographics, psychographics, jobs-to-be-done, journey mapping, and anti-personas. Use for: marketing strategy, product development, UX research, sales enablement, content strategy. Triggers: customer persona, buyer persona, user persona, target audience, ideal customer, customer profile, audience research, user research, icp, ideal customer profile, target market, customer avatar, audience persona

760 999
View
nano-banana-2 logo
inference-sh/skills

nano-banana-2

Generate images with Google Gemini 3.1 Flash Image Preview (Nano Banana 2) via inference.sh CLI. Capabilities: text-to-image, image editing, multi-image input (up to 14 images), Google Search grounding. Triggers: nano banana 2, nanobanana 2, gemini 3.1 flash image, gemini 3 1 flash image preview, google image generation

760 999
View
video-prompting-guide logo
inference-sh/skills

video-prompting-guide

Best practices and techniques for writing effective AI video generation prompts. Covers: Veo, Seedance, Wan, Grok, Kling, Runway, Pika, Sora prompting strategies. Learn: shot types, camera movements, lighting, pacing, style keywords, negative prompts. Use for: improving video quality, getting consistent results, professional video prompts. Triggers: video prompt, how to prompt video, veo prompts, video generation tips, better ai video, video prompt engineering, video prompt guide, video prompt template, ai video tips, video prompt best practices, video prompt examples, cinematography prompts

760 996
View

Popular AI tools

Kaiber logo
Video

Kaiber

Generate, edit, and beat-sync AI video with leading models in one workspace.

Paid
View
Vimcal logo
Productivity

Vimcal

The world's fastest calendar for remote work

Free
View

Transform Your Design with AI Designer by ImgCreator.ai

Freemium
View
Akool AI logo
Content & writing

Akool AI

Revolutionizing Video Production with AI-Powered Creativity

Paid
View

Extend an image past the frame and let AI fill the new aspect ratio.

Freemium
View
StarByFace logo
Security

StarByFace

Discover your celebrity doppelgänger with StarByFace!

Free
View
C

ChainClarity explains 700+ crypto whitepapers in plain English, with layered summaries, comparisons, research tools, alerts, and a $4.99 Pro plan.

Freemium
View
Opus Clip logo
Coding & apps

Opus Clip

Opus.ai: Revolutionize Your Web Experience

Free
View