Extract a visual language spec from an existing brand's presence
Before briefing a designer or running image-gen prompts at scale, you need a written spec of what a brand actually looks like. This prompt reverse-engineers that spec from references you already have.
You are a creative director writing a visual language reference document. I will describe an existing brand's visual presence and you will extract a structured spec from it.
Brand name: {{BRAND_NAME}}
Description of brand visuals (describe website, packaging, ads, social media, or paste alt-text descriptions of key images): {{VISUAL_DESCRIPTION}}
Industry and audience: {{INDUSTRY_AND_AUDIENCE}}
1. Summarize the brand's visual personality in exactly 3 adjectives. For each, write one sentence explaining what specific visual choice produces that feeling.
2. Describe the apparent color system: primary palette (name colors in plain language, not just hex), how contrast is used, and any color the brand conspicuously avoids.
3. Describe typography patterns: apparent type weight preferences, whether type is used expressively or functionally, and any notable typographic gestures.
4. Describe photographic or illustrative style: subject matter, lighting mood, level of polish, human presence (yes/no/how).
5. Identify one visual rule this brand seems to follow that most competitors in the same industry do not.
6. Write a one-paragraph image-gen system prompt that a designer could use to generate on-brand assets, based entirely on what you've documented above.
Note: This prompt works from descriptions and alt-text. If you paste in raw URLs, the model cannot retrieve them — describe what you see instead. {{BRAND_NAME}}{{VISUAL_DESCRIPTION}}{{INDUSTRY_AND_AUDIENCE}}
How to use this prompt
- Copy the prompt above (Copy button on the top-right).
- Replace each
{{VAR}}with your own value. Variables:{{BRAND_NAME}}{{VISUAL_DESCRIPTION}}{{INDUSTRY_AND_AUDIENCE}}. - Paste it into one of the recommended tools below.
- Iterate: tighten constraints in the prompt if the output is generic.
Why this prompt is structured this way
The prompt is split into explicit steps because LLMs do better when the path is named, not implied. Each variable forces specificity at the input layer — vague inputs get vague outputs.
Pair this prompt with a tool
Leonardo.ai
$12/moImage generation with style consistency and control.
Leonardo competes with Midjourney but adds first-class control: ControlNet, style transfer, fine-tuned models per use case. Better workflow for repeat-use brand imagery.
Claude (Anthropic)
$0/mo (Pro at $20)Frontier model with long context and strong reasoning.
Claude (Opus / Sonnet / Haiku tiers) is the assistant favored by writers and engineers who care about reasoning quality and tone. 1M token context on Opus.
ChatGPT (OpenAI)
$0/mo (Plus at $20)The category-defining general-purpose AI assistant.
ChatGPT has the broadest feature surface: image gen, voice, custom GPTs, web browsing, code execution. Often the right default; sometimes beaten on specific tasks by Claude or Perplexity.
Midjourney
$10/moThe aesthetic king of AI image generation.
Midjourney still produces the most stylistically distinctive imagery of any image model. The Discord-native workflow is divisive but the web app caught up in 2025.
The PlaybookPrompts weekly
One short email per week. The five sharpest prompts we found, one tool worth your attention, one anti-pattern to avoid. Unsubscribe in one click.
Newsletter signup is not configured. Set PUBLIC_NEWSLETTER_USERNAME in the build env.