AI Illustration System

A client needed a large illustration set for their app: multiple categories of content, each needing its own visual treatment. Whitespectre isn't an illustration studio, and this scope would normally be handed to a specialist agency. I could see that AI image generation had reached a quality level that made this feasible. But generating one strong illustration and generating 200 consistent, on-brand ones are very different problems. The challenge I identified immediately was visual fatigue: with a uniform style applied at scale, ten illustrations on a screen start to look identical regardless of subject matter. The brief was really three things at once: quality, consistency, and meaningful variation across a large volume.

The first architectural decision was the most important. The client had an existing content library of hundreds of descriptions written for users, not for image generators. Feeding that raw content directly into an image model produces inconsistent, often inaccurate results. But mixing content and style instructions in a single prompt means you can't tune either independently. I designed a two-step pipeline. Step one: an LLM takes the raw content entry and a category-specific template and generates a pure scene description: what's happening, who's in the frame, what they're doing, what the environment looks like. No colour. No style. Just content. Step two: that scene description is injected into the full image generation prompt alongside the style lock, colour strategy, composition type, and reference images. This separation was critical for debugging. When an image doesn't come out right, you can immediately identify whether the problem is in the content description (step one) or in the style and colour system (step two), then fix exactly that layer without touching anything else.

Getting one consistent style wasn't enough. At volume, stylistic uniformity creates visual fatigue. I needed the system to produce genuine variation in colour, composition and framing while keeping the style coherent across every output. I designed eight colour strategies based on the client's existing brand palette. Each strategy defines foreground and background colour relationships using a warm/cool separation principle, with three distinct hues distributed across body planes, clothing, and equipment within each figure. Switching strategies produces a completely different feel while never leaving the brand spectrum. I also designed five composition types (narrative wide, iconic portrait, detail close-up, environmental, still life). One thing I discovered along the way: composition instructions had to live in both steps of the pipeline, injected into the scene description in step one so the LLM frames the content appropriately, and again in step two to instruct the image model on spatial treatment. For food-related content, I introduced a separate naturalistic colour override, because foreground and background colour separation breaks down when the foreground is food that needs to be its natural colour.

The original plan was to build a proper orchestration tool with a developer. I was doing manual testing in the meantime: copying prompts between notes and spreadsheets, downloading results, comparing in Figma. It was laborious and error-prone. The wrong prompt version, a missed component, and a generation is wasted. More importantly, you can't trust your conclusions about what's working if your testing process introduces human error. I decided to try building the tool myself in Lovable. The risk felt low. I was already waiting on generations. If it came to nothing, I hadn't wasted much. Within a few hours I had something that stored all prompt components in separate, editable sections, linked directly to the image generation API, and could generate with a single button click. When I showed it to our developer (the person who was supposed to build the proper version), he looked at it for a few minutes and said: “we should just use this.” That was the moment the experiment became the product. From there I built out the full tool: CSV upload for bulk content import, batch generation with randomisation, a gallery with full prompt visibility per image, named reference sets, collections for curation, in-tool editing for minor adjustments, and CSV export for client handoff.

Getting a style prompt right is not a one-shot exercise. It takes iteration, but careless iteration produces confusion rather than progress. The methodology I developed: generate in batches of four or five (never single images, which can be outliers), identify what's wrong, hypothesise which layer of the system is responsible, make one targeted change, generate again. The most instructive example was the polygon problem. I wanted a geometric, graphic illustration style: bold planes, strong tonal contrast. But using the word “geometric” prominently in the style lock caused the image model to produce figures that looked like early 3D game characters, polygon meshes rather than people. No amount of “but make it look human” could counteract the word's association. The fix was to relocate geometry explicitly: clothing gets angular panels, backgrounds get geometric plane divisions, equipment gets clean angular forms. But figure silhouettes and skin surfaces must use natural curves. The geometric quality lives everywhere except the body. I also used the in-tool editing function as a diagnostic tool. Beyond client refinements, it let me test whether a specific change would move results in the right direction before committing to a system-wide prompt update.