Learn a repeatable process to generate unique, on-brand images in Midjourney. This workflow uses mood boards, style references (SREFs), and personalization codes to create a consistent visual aesthetic without complex prompts.
with Claire Vo
Before opening Midjourney, collect images on a tool like Pinterest or Cosmos that capture the general vibe and aesthetic you're aiming for. This collection becomes your visual language for the AI.
Instead of using a whole mood board, drag individual images from it into Midjourney as Style References (SREFs). If the generated style is off, identify and remove the specific SREF causing the issue and regenerate to iterate closer to your goal.
Train your own style preference in Midjourney by rating images in a 'this-or-that' format to create a reusable Personalization Code. Apply this code along with your SREFs to add more depth and unique taste to your generations.
Keep prompts simple and direct. Use 'cheat codes' like publication names or camera types for style, and simple descriptive language for objects. For composition, use an image reference; if it introduces unwanted elements, crop the reference image and use the cropped version.
Examples: `Dazed editorial photo shoot`, `Sony RX100`, `on a matte black leather couch`For client work, deliver the system itself in a Figma file. Include the exact Style References, Personalization Codes, and a few base prompts so the client can continue generating their own on-brand images.
Use an advanced AI model to analyze raw packet sniffer logs and research notes to deduce an unknown, proprietary Bluetooth protocol and create a tool to interact with the hardware.
Delegate a complex, multi-format data migration to an AI agent. The model will build the migration script, create a scalable testing system to validate its own work, and repair issues in a self-sustaining loop.
Use an advanced AI model like GPT-5.5 Pro in Codex to automatically analyze a CSV list of security vulnerabilities, group them thematically, propose architectural changes, and implement the necessary code fixes.
Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.