guides/design/logo-design-guide/SKILL.md
Logo design principles and AI image generation best practices for creating logos. Covers logo types, prompting techniques, scalability rules, and iteration workflows. Use for: brand identity, startup logos, app icons, favicons, logo concepts. Triggers: logo design, create logo, brand logo, logo generation, ai logo, logo maker, icon design, brand mark, logo concept, startup logo, app icon logo
npx skillsauth add inference-sh-6/skills logo-design-guideInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security scan pending...
This skill is queued for security scanning. Results will appear when the scan completes.
Install the belt CLI skill:
npx skills add belt-sh/cli
Design effective logos with AI image generation via inference.sh CLI.
Requires inference.sh CLI (
belt). Install instructions
belt login
# Generate a logo concept
belt app run falai/flux-dev-lora --input '{
"prompt": "flat vector logo of a mountain peak with a sunrise, minimal geometric style, single color, clean lines, white background",
"width": 1024,
"height": 1024
}'
| Type | Description | When to Use | Example | |------|-------------|-------------|---------| | Wordmark | Company name styled as logo | Strong brand name, short (< 10 chars) | Google, Coca-Cola | | Lettermark | Initials only | Long company name, formal | IBM, HBO, CNN | | Pictorial | Recognizable icon/symbol | Universal brand, works without text | Apple, Twitter bird | | Abstract | Geometric/non-literal shape | Tech companies, conceptual brands | Nike swoosh, Pepsi | | Mascot | Character illustration | Friendly brands, food/sports | KFC Colonel, Pringles | | Combination | Icon + wordmark together | New brands needing both recognition and name | Burger King, Adidas |
AI image generators cannot reliably render text. Letters will be distorted, misspelled, or garbled.
Strategy:
flat vector logo, simple minimal icon, single color silhouette,
geometric logo mark, clean lines, negative space design,
line art logo, flat design icon, minimalist symbol
❌ photorealistic logo (contradiction — logos aren't photos)
❌ 3D rendered logo (too complex, won't scale down)
❌ gradient logo (inconsistent results, hard to reproduce)
❌ logo with text "Company Name" (text rendering fails)
flat vector logo of [subject], [style], [color constraint], [background], [additional detail]
# Abstract geometric
belt app run falai/flux-dev-lora --input '{
"prompt": "flat vector abstract logo, interlocking hexagonal shapes forming a letter S, minimal geometric style, single navy blue color, white background, clean sharp edges"
}'
# Pictorial nature
belt app run falai/flux-dev-lora --input '{
"prompt": "flat vector logo of a fox head in profile, geometric faceted style, orange and white, minimal clean lines, white background, negative space design"
}'
# Mascot style
belt app run bytedance/seedream-4-5 --input '{
"prompt": "friendly cartoon owl mascot logo, simple flat illustration, wearing graduation cap, purple and gold colors, white background, clean vector style"
}'
# Tech abstract
belt app run xai/grok-imagine-image-pro --input '{
"prompt": "minimal abstract logo mark, interconnected nodes forming a brain shape, line art style, single teal color, white background, tech startup aesthetic"
}'
A logo must work at every size:
| Context | Size | What Must Work | |---------|------|----------------| | Favicon | 16x16 px | Silhouette recognizable | | App icon | 1024x1024 px | Full detail visible | | Social avatar | 400x400 px | Clear at a glance | | Business card | ~1 inch | Clean print reproduction | | Billboard | 10+ feet | No pixelation, simple enough |
# Step 1: Generate 5-10 broad concepts
for i in {1..5}; do
belt app run falai/flux-dev-lora --input '{
"prompt": "flat vector logo of a lighthouse, minimal geometric, single color, white background"
}' --no-wait
done
# Step 2: Refine the best concept with variations
belt app run falai/flux-dev-lora --input '{
"prompt": "flat vector logo of a geometric lighthouse with light beam rays, minimal line art, navy blue, white background, negative space design"
}'
# Step 3: Generate at high resolution for final
belt app run bytedance/seedream-4-5 --input '{
"prompt": "flat vector logo of a geometric lighthouse with radiating light beams, minimal clean design, navy blue single color, pure white background",
"size": "2K"
}'
# Step 4: Upscale for production use
belt app run falai/topaz-image-upscaler --input '{
"image": "path/to/best-logo.png",
"scale": 4
}'
| Mistake | Problem | Fix | |---------|---------|-----| | Too much detail | Loses clarity at small sizes | Simplify to essential shapes | | Relies on color | Fails in B&W contexts | Design in black first | | Text in AI generation | Garbled/misspelled letters | Generate icon only, add text manually | | Trendy effects (glows, shadows) | Dates quickly, reproduction issues | Stick to flat, timeless design | | Too many colors | Hard to reproduce, expensive printing | Max 2-3 colors | | Asymmetric without purpose | Looks unfinished | Use intentional asymmetry or stay balanced |
| Format | Use Case | |--------|----------| | SVG | Scalable vector, web, editing | | PNG (transparent) | Digital use, presentations | | PNG (white bg) | Documents, email signatures | | ICO / Favicon | Website favicon (16, 32, 48px) | | High-res PNG (4096px+) | Print, billboards |
Note: AI generates raster images (PNG). For true vector SVG, use the AI output as a reference and trace in a vector tool, or use AI-to-SVG conversion tools.
npx skills add inference-sh/skills@ai-image-generation
npx skills add inference-sh/skills@prompt-engineering
Browse all apps: belt app store
data-ai
Generate multi-person talking head podcast videos from scratch using AI — character creation, TTS, avatar animation, and video stitching. Use when the user wants to create a podcast, talking head video, or multi-speaker conversation video.
tools
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
tools
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
tools
Run 250+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok