Generate Interior Moodboards
Submits a design brief to generate 12 AI visuals, compiles them into a two-page PDF moodboard, and emails it directly to the client.
freelancers and consultants
What it does
Submit your design brief via the form to instantly receive twelve AI-generated visuals compiled into a professional two-page PDF moodboard. The system automatically stores these assets in cloud storage and emails the final deliverable directly to your client for review.
Step by step
- Configure the n8n form webhook to capture user inputs such as style preference and color palette.
- Set up the HTTP request node to call an image generation API with a structured payload containing the generated prompts.
- Define the Nextcloud upload workflow to store each generated image asset in a dedicated folder per project ID.
- Configure Gotenberg to accept HTML input and output a standard A4 or Letter-sized PDF document.
Where the LLM does the work
- Use OpenRouter to analyze the design brief and generate twelve distinct, highly descriptive image prompts that cover various angles and elements of the room.
- Instruct Google Gemini to convert the metadata and selected image URLs into a clean, styled HTML structure suitable for a professional two-page moodboard layout.
- Have an LLM refine the initial prompt generation if the user's brief is vague, ensuring the resulting images are cohesive in style.
Watch out for
HTML-to-PDF converters can break complex layouts if CSS is not strictly inline or embedded, so keep the Gemini output simple and robust.
Nextcloud upload paths may fail silently if the target directory does not exist, so add a check step to create folders dynamically before uploading assets.
Email delivery might trigger spam filters if the PDF contains many external image links, so embed images directly into the HTML or use base64 encoding where possible.
Tools that fit
n8n Form Webhook Service Collect design brief input
OpenRouter Chat Model LLM Generate image prompts via Claude
Google Gemini Chat Model LLM Create HTML moodboard layout
HTTP Request API Generate images via Hugging Face API
The agent brief
Everything your agent needs, including the gotchas. Copy it and go.
You are helping me build the following AI agent workflow. ## Goal Generate Interior Moodboards: Submits a design brief to generate 12 AI visuals, compiles them into a two-page PDF moodboard, and emails it directly to the client. ## Specification - What it does: Submit your design brief via the form to instantly receive twelve AI-generated visuals compiled into a professional two-page PDF moodboard. The system automatically stores these assets in cloud storage and emails the final deliverable directly to your client for review. - Trigger: Triggered by an event (Manual · on form submission) - Autonomy: Fully hands-off - Expected setup effort: a few focused days - Tools/services involved: - n8n Form Webhook: Collect design brief input - OpenRouter Chat Model: Generate image prompts via Claude - Google Gemini Chat Model: Create HTML moodboard layout - HTTP Request: Generate images via Hugging Face API - Nextcloud: Store and share image files ## Known pitfalls, handle each one explicitly in your implementation 1. HTML-to-PDF converters can break complex layouts if CSS is not strictly inline or embedded, so keep the Gemini output simple and robust. 2. Nextcloud upload paths may fail silently if the target directory does not exist, so add a check step to create folders dynamically before uploading assets. 3. Email delivery might trigger spam filters if the PDF contains many external image links, so embed images directly into the HTML or use base64 encoding where possible. ## Reference implementation https://n8n.io/workflows/10880 (workflow template) Fetch and inspect this before building. If it matches my stack, adapt it; if not, rebuild the pattern with my tools. ## Process requirements 1. Before building: ask me which of the listed tools I actually use and what my platform is (n8n / Make / code / other). Do not assume. 2. Adapt the pattern to my answers; do not force the reference stack. 3. Address every pitfall above; tell me how you handled each. 4. Provide a test plan I can run before letting this touch real data. 5. Ask before any step that sends messages, modifies data, or spends money. Source: https://usecasesforagents.com/use-case/generate-interior-moodboards-with-ai/ via usecasesforagents.com
Frequently asked questions
Can I use a different LLM than OpenRouter?
Yes. OpenRouter is only the example LLM in this recipe. The same flow works with Anthropic, Cohere, DeepSeek and Google Gemini. Swap the LLM connection and keep the rest of the setup as written.
Want this running in your business?
This is what I do. I design and build AI agents like this one, and keep them running. If you want it set up for your team instead of doing it yourself, get in touch.
Who it's for
Built for freelancers and consultants juggling this across every client, not just one.