Case Study — Fixing Image Drift to Unblock Launch — Straight Up AI
Case Study · Content Creation · GenAI

Launch unblocked,
£500k funding raised

The client's product turns a story into a sequence of generated images. Initial versions of the images were inconsistent with user outfits, scenes and even gender changing between shots. This made the product unshippable. To fix the problem we built an evaluation rubric that scored images according to consistency and story alignment. We then developed a novel strategy that combined reference images with clear story plans.

Client
Startup
Service
AI Engineer
Focus
Generative AI Evaluation
Stack
Python · Gemini · OpenAI · MLflow
The Challenge

The character wouldn't stay the same person

Generating one good image is easy. Generating a sequence that holds together is an open problem in generative story telling. Across a single story certain aspects can (and should) change. These include what the user is wearing and what room they are in. Other attributes though, such as who the user is, should remain consistent.

As images were created in parallel context was not between shots. Individually an image may have been good, but when incorporated into the story it presented something very different.

The usual fix, feeding earlier images back in as a reference, was not tenable due to the latency of generating images in serial. We therefore needed to develop a novel strategy that presented both the changes in the story and the consistency of the character.

The Approach

Give every shot the same anchor

Before
Story prompt onlynothing shared between shots
×
A different person each shotgood images, broken story
After
Reference imagewho the person is
Continuity planwhat changes, shot by shot
Consistent storiessame person, still shot differently
The Results
88%
Story tests passed.
On time
Image inconsistency stopped being a launch blocker.
£500k
Seed round raised according to schedule.

GenAI quality issue holding up your product?

See if we're a fit →
Previous
Previous

Token Reduction