guides/design/book-cover-design/SKILL.md
Book cover design with genre-specific conventions, typography rules, and AI image generation. Covers fiction and non-fiction genres, sizing, thumbnail testing, and iteration workflows. Use for: self-publishing, ebook covers, print covers, audiobook covers, cover mockups. Triggers: book cover, cover design, ebook cover, book art, novel cover, self publishing cover, kindle cover, audiobook cover, book jacket, cover illustration, fiction cover, nonfiction cover
npx skillsauth add inference-sh/agent-skills book-cover-designInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Create genre-appropriate book covers with AI image generation via inference.sh CLI.
Requires inference.sh CLI (
belt). Install instructions
belt login
# Generate a thriller cover concept
belt app run falai/flux-dev-lora --input '{
"prompt": "dark moody book cover art, lone figure standing at end of a rain-soaked alley, dramatic chiaroscuro lighting, noir atmosphere, cinematic, high contrast shadows",
"width": 832,
"height": 1248
}'
Readers judge books by covers. Matching genre expectations is critical — a romance reader will skip a cover that looks like sci-fi, regardless of content.
| Genre | Palette | Imagery | Typography | Mood | |-------|---------|---------|------------|------| | Thriller/Mystery | Dark (black, navy, blood red) | Lone figure, urban scenes, shadows | Bold sans-serif, all caps | Tense, ominous | | Romance | Warm (pink, red, gold, soft purple) | Couples, flowers, scenic backdrops | Script/cursive, elegant serif | Passionate, dreamy | | Sci-Fi | Cool (blue, teal, purple, silver) | Space, tech, geometric shapes | Clean sans-serif, futuristic | Vast, technological | | Fantasy | Rich saturated (emerald, crimson, gold) | Swords, magic, landscapes, creatures | Decorative serif, ornamental | Epic, magical | | Literary Fiction | Muted, sophisticated | Abstract, minimal, symbolic | Elegant serif, understated | Thoughtful, artistic | | Horror | Dark with high contrast pops | Faces, shadows, isolation, decay | Distressed, bold, dripping | Dread, unease | | Historical | Sepia, muted period-accurate | Period clothing, architecture, artifacts | Classical serif | Nostalgic, authentic |
| Category | Style | Imagery | Typography | |----------|-------|---------|------------| | Business/Self-help | Clean, bold, 2-3 colors | Minimal or none, icon optional | Large bold sans-serif title | | Memoir | Personal, warm | Author photo or atmospheric scene | Mix of serif and sans | | Science/Academic | Professional, structured | Diagrams, abstract visuals | Clean serif, structured layout | | Cookbook | Appetizing, bright | Hero food photograph | Warm, inviting fonts | | Travel | Vibrant, aspirational | Destination photography | Adventure-style fonts |
| Format | Dimensions | Common For | |--------|-----------|------------| | Mass market paperback | 4.25 x 6.87" | Genre fiction | | Trade paperback | 5.5 x 8.5" | Most fiction/non-fiction | | Standard | 6 x 9" | Non-fiction, textbooks | | Large format | 7 x 10" | Coffee table, art books |
| Platform | Cover Size | Aspect Ratio | |----------|-----------|--------------| | Amazon Kindle | 2560 x 1600 px (min 1000 x 625) | 1.6:1 | | Apple Books | 1400 x 1873 px minimum | ~3:4 | | General ebook | 2500 x 3750 px | 2:3 |
Approximate: page count / 400 = spine width in inches (varies by paper stock).
┌─────────────────────────┐
│ TITLE ZONE │ ← Top 1/3: Title must be readable here
│ (largest text) │ This is what shows in thumbnails
│ │
│ │
│ MAIN IMAGE │ ← Middle: Core visual/illustration
│ ZONE │ The emotional hook
│ │
│ │
│ SUBTITLE / │ ← Bottom area: Author name, subtitle
│ AUTHOR ZONE │ Smaller text, less critical at thumbnail
└─────────────────────────┘
Your cover will be seen at 80x120px on Amazon, 60x90px in search results, and ~40x60px on mobile grids.
At thumbnail size, readers must be able to identify:
Test: shrink your cover to 80px wide. If you can't read the title or identify the genre, redesign.
belt app run falai/flux-dev-lora --input '{
"prompt": "dark cinematic book cover scene, silhouette of a person standing before a foggy bridge at night, single streetlamp casting long shadows, noir atmosphere, high contrast, desaturated blue tint, dramatic tension",
"width": 832,
"height": 1248
}'
belt app run bytedance/seedream-4-5 --input '{
"prompt": "romantic soft-focus scene, couple silhouetted against golden sunset on a beach, warm pink and gold tones, bokeh lights, dreamy atmosphere, soft pastel sky, intimate mood",
"size": "2K"
}'
belt app run falai/flux-dev-lora --input '{
"prompt": "science fiction book cover art, massive space station orbiting a ringed planet, deep blue and teal color palette, stars and nebula background, hard sci-fi aesthetic, cinematic scale, clean geometric architecture",
"width": 832,
"height": 1248
}'
belt app run xai/grok-imagine-image-pro --input '{
"prompt": "epic fantasy book cover illustration, ancient stone castle on a cliff overlooking a misty valley, magical aurora in the sky, rich emerald and gold colors, detailed environment, sense of wonder and adventure",
"aspect_ratio": "2:3"
}'
belt app run falai/flux-dev-lora --input '{
"prompt": "minimal abstract book cover background, clean gradient from deep navy to white, subtle geometric pattern, professional and modern, negative space, corporate aesthetic",
"width": 832,
"height": 1248
}'
AI cannot render text reliably. Generate the cover art/background with AI, then add typography in a design tool.
# 1. Generate 5+ concepts across different models
belt app run falai/flux-dev-lora --input '{"prompt": "...", "width": 832, "height": 1248}' --no-wait
belt app run bytedance/seedream-4-5 --input '{"prompt": "..."}' --no-wait
belt app run xai/grok-imagine-image-pro --input '{"prompt": "...", "aspect_ratio": "2:3"}' --no-wait
# 2. Refine best concept with image-to-image editing
belt app run bytedance/seededit-3-0-i2i --input '{
"prompt": "make the sky more dramatic with storm clouds, increase contrast",
"image": "path/to/best-concept.png"
}'
# 3. Upscale for print quality
belt app run falai/topaz-image-upscaler --input '{
"image": "path/to/final-cover.png",
"scale": 4
}'
| Mistake | Problem | Fix | |---------|---------|-----| | Wrong genre signals | Readers skip it | Study bestsellers in your genre | | Title too small | Invisible at thumbnail | Title should fill top 1/3 | | Too much detail | Muddy at small sizes | Simplify, use negative space | | AI-generated text | Garbled letters | Add text in design tool | | Centered everything | Static, boring | Use asymmetry intentionally | | Following trends blindly | Dates quickly | Classic genre conventions endure |
npx skills add inference-sh/skills@ai-image-generation
npx skills add inference-sh/skills@prompt-engineering
npx skills add inference-sh/skills@image-upscaling
Browse all apps: belt app list
development
Render videos from React/Remotion component code via inference.sh. Pass TSX code, get MP4. Supports all Remotion APIs: useCurrentFrame, useVideoConfig, spring, interpolate, AbsoluteFill, Sequence. Configurable resolution, FPS, duration, codec. Use for: programmatic video generation, animated graphics, motion design, data-driven videos, React animations to video. Triggers: remotion, render video from code, tsx to video, react video, programmatic video, remotion render, code to video, animated video, motion graphics code, react animation video
tools
Generate videos with Pruna P-Video and WAN models via inference.sh CLI. Models: P-Video, WAN-T2V, WAN-I2V. Capabilities: text-to-video, image-to-video, audio support, 720p/1080p, fast inference. Pruna optimizes models for speed without quality loss. Triggers: pruna video, p-video, pruna ai video, fast video generation, optimized video, wan t2v, wan i2v, economic video generation, cheap video generation, pruna text to video, pruna image to video
documentation
Still-to-video conversion guide: model selection, motion prompting, and camera movement. Covers Wan 2.5 i2v, Seedance, Fabric, Grok Video with when to use each. Use for: animating images, creating video from stills, adding motion, product animations. Triggers: image to video, i2v, animate image, still to video, add motion to image, image animation, photo to video, animate still, wan i2v, image2video, bring image to life, animate photo, motion from image
tools
Generate videos with Google Veo models via inference.sh CLI. Models: Veo 3.1, Veo 3.1 Fast, Veo 3, Veo 3 Fast, Veo 2. Capabilities: text-to-video, cinematic output, high quality video generation. Triggers: veo, google veo, veo 3, veo 2, veo 3.1, vertex ai video, google video generation, google video ai, veo model, veo video