Case Study · AI Production Pipeline
Academy of Sports · Publicis Sapient · 2026

Replacing the model shoot — one AI-generated lifestyle image at a time.

Academy of Sports needed lifestyle photography for thousands of SKUs — everything from running gear to fishing tackle to swim equipment — without the cost or timeline of traditional shoots. I built and ran the pipeline that turned raw product photography into production-ready lifestyle imagery: 3,000+ images across a 1.5-month production run, at a sustained 70–100 a day.

AI Image Generation Prompt Engineering Visual QC Retail Production Workflow Design
ClientAcademy of Sports
RolePipeline Lead — AI Imagery Production & QC
AgencyPublicis Sapient
Output3,000+ assets · 1.5 months · 70–100/day

A catalog that doesn't photograph the same way twice.

Academy of Sports' catalog spans categories that don't photograph the same way twice — running accessories, roller skates, pool inflatables, swim gear, fishing tackle, hunting equipment. Traditional lifestyle photography for a catalog at this scale would mean booking models, locations, and studio time for every SKU, category by category, on a timeline retail can't afford.

The brief: take the raw product photography that already existed for every SKU and generate realistic, on-brand lifestyle imagery — a person actually wearing, using, or holding the product in context — at a volume and speed no shoot calendar could match, without it looking synthetic or generic.

Owning the pipeline end-to-end.

I owned the pipeline end-to-end: turning a spreadsheet of SKU data into a repeatable production process, writing and refining the prompts, and building the quality bar the output had to clear before it reached review.

Pipeline & Workflow Design Prompt Engineering Product Research AI Output Quality Control Retouch Direction Cross-functional Review

From spreadsheet to shot.

Every batch started as a SKU log — product ID, category, color variant, and the raw product photography on file. Working from that data, I developed a repeatable process to composite each product onto a human model in a real-world setting, rather than generating a person and product from scratch each time.

Research before the prompt. For anything mainstream — apparel, running accessories, swimwear — a prompt could draw on common knowledge of how the product is worn or used. But a large share of the catalog wasn't mainstream. Fishing lures, hooks, and tackle; hunting and shooting accessories; niche sporting equipment — products with no obvious "lifestyle" reference point, and no room for a generic AI guess. Before a prompt could be written, I had to research the product itself: how it's actually held, rigged, mounted, or used, from every angle the source photography offered. A fishing lure prompted without that research renders as a shape floating in a hand; one grounded in how it's actually rigged and cast renders as something a customer recognizes.

Prompting for the product's context, not just its look. The goal wasn't a photorealistic render — it was a photorealistic render that understood what the product was for. That meant encoding not just color and geometry into the prompt, but use case, orientation, and setting: a waistpack sits at the hip mid-run, not draped over a shoulder; a fishing bait is rigged and mid-cast, not lying inert in an open palm.

Generation at volume. Once a prompt pattern was validated for a category, it was applied across every color and size variant in that category — the mechanism that sustained 70–100 assets a day, and 3,000+ images across the project's 1.5-month run, without writing a new prompt for every SKU.

One validated prompt pattern, three color variants generated in the same batch — CK Wrestling Headgear.

AI-generated lifestyle image of a wrestler wearing white CK wrestling headgear, mid-practice on a wrestling mat
White / Clear
AI-generated lifestyle image of a wrestler wearing pink and black CK wrestling headgear, mid-practice on a wrestling mat
Pink / Black
AI-generated lifestyle image of a wrestler wearing navy blue CK wrestling headgear, mid-practice on a wrestling mat
Navy Blue

Generating the image was the easy half.

The harder discipline was knowing which ones were good enough to ship — and catching the ones that weren't before they reached a stakeholder review. I built a three-way triage that every generated asset passed through: Passed (ready to publish), To Be Retouched (usable with targeted fixes), or Rejected (regenerate from scratch). Across one representative production batch of 197 SKUs, the split looked like this:

43%
Passed clean
Ready for publish on first generation — no rework required.
38%
Needed targeted retouching
Close, but not shippable as-is — nearly two-thirds of these flags traced back to AI-mangled text or logos.
15%
Rejected outright
Sent back for a fresh generation attempt — usually a product-accuracy issue, not a rendering one.

The single most common defect, by a wide margin: AI-mangled text and logos. Branded products live or die on legible logos and labels, and diffusion models are notoriously unreliable at rendering small text.

The rejection pile told a different story — one about product accuracy rather than rendering artifacts: a bait shown lying in the frame instead of rigged for use, a mount shown the wrong way, a compartment that didn't match the actual product, a hook that had gone missing entirely between generations. Catching these required actually knowing the product — which is what made categories like fishing tackle and hunting gear the hardest in the catalog, and the ones that most rewarded the research done up front.

Product by product. Category by category.

A representative cross-section of the pipeline's output — spanning running accessories, water recreation, swim, nutrition, and hunting gear. Left: the raw product photography on file. Right: the generated lifestyle output.

01
Nike Slim Waistpack 4.0
Running accessories — worn exactly the way it's meant to be.
Before — Source Listing
Academy Sports product listing page for the Nike Slim Waistpack 4.0 in blue, studio product photography only
After — AI Generated
AI-generated lifestyle image of a runner mid-stride on a park path, blue Nike waistpack sitting naturally at the hip
02
AquaCradle Pool Float
Water recreation — extending a single-person studio shot into a two-person resort scene.
Before — Studio Product Shot
Studio product photography of a teal and white AquaCradle inflatable pool float on a white background
After — AI Generated
AI-generated lifestyle image of a couple laughing together on an AquaCradle pool float at a resort infinity pool overlooking the ocean
03
Nike Swim Goggles
Swim gear — worn and fogged with real water detail, mid-stroke.
Before — Studio Product Shot
Studio product photography of clear and green Nike swim goggles with a black strap on a white background
After — AI Generated
AI-generated lifestyle image of a swimmer mid-stroke in a pool, wearing Nike swim goggles fogged with water detail
04
RYSE Loaded Protein
Nutrition — a static tub shot becomes an everyday gym moment.
Before — Studio Product Shot
Studio product photography of a RYSE Loaded Protein tub, Strawberry Shortcake Rolls flavor, on a white background
After — AI Generated
AI-generated lifestyle image of a woman in a gym scooping RYSE Loaded Protein powder from the tub
05
Winter Pool Cover
Seasonal outdoor — real-world context the original studio shot never captured.
Before — Studio Product Shot
Studio product photography of a round navy winter pool cover fitted to an above-ground pool, on a white background
After — AI Generated
AI-generated lifestyle image of the same winter pool cover fitted to a backyard pool during a snowfall
06
Federal Premium Turkey Shotshells
Hunting & tackle — the hardest category in the catalog, and where research mattered most.
Before — Studio Product Shot
Studio product photography of a box of Federal Premium Heavyweight TSS 12-gauge turkey shotshells and a single shell on a white background
After — AI Generated
AI-generated lifestyle image of the same turkey shotshell box and shell staged on a wooden platform in a forest hunting environment with turkey feathers nearby
06 — Outcomes

The bottleneck moved from budget to research.

The pipeline didn't just cut cost — it changed what was possible on the timeline. Categories that would never have justified a dedicated shoot could now get the same lifestyle treatment as the catalog's best-sellers.

3,000+
Assets Generated
Over a 1.5-month production run, at a sustained 70–100/day
43%
First-Pass Yield
Images that passed quality review with zero rework
197
SKUs / Batch
Reviewed in one representative batch, running to fishing tackle
0
Model Shoots Required
To produce the lifestyle imagery this catalog needed

Accuracy beat elaboration, every time.

The best prompts weren't the most elaborate ones — they were the most accurate ones. Every hour spent understanding how a product actually works saved multiple regeneration cycles downstream.

Quality control turned out to be as much a design skill as prompt-writing: knowing what "wrong" looks like for a product you've never held requires the same research discipline as designing for a user you've never met.

Back