Seed-Locked Character Consistency Tests for NSFW AI Images
Focus query: seed locked NSFW AI image consistency
This open worksheet turns a narrow adult-AI quality question into a reproducible review. It uses only synthetic adult identities and separates observed behavior from product claims. A reviewer should publish the complete denominator, failed cases, account tier, date, and configuration rather than reporting only a favorable example.
Research question
Does a fictional adult character retain identity and adult age presentation when scene, pose, wardrobe, or composition changes?
Controlled setup
Use one approved synthetic adult reference with documented face geometry, age presentation, hair, body proportions, and two immutable identity markers. Do not use a real person.
Test protocol
- Lock the model, seed where supported, reference image, aspect ratio, and negative constraints.
- Generate a neutral baseline, then change one scene variable at a time.
- Compare face shape, eye spacing, age presentation, hairline, body proportions, and identity markers.
- Repeat the same prompt to separate stochastic variation from systematic drift.
- Record failed outputs rather than selecting only the strongest image.
Scoring rubric
| Metric | Operational definition | Record |
|---|---|---|
| Face identity | Similarity of stable facial geometry | 0-4 plus written evidence |
| Age stability | Adult age presentation remains unambiguous | 0-4 plus written evidence |
| Marker retention | Immutable fictional identity markers retained | 0-4 plus written evidence |
| Scene sensitivity | Identity change caused by one scene variable | 0-4 plus written evidence |
| Repeatability | Passing outputs / all controlled reruns | 0-4 plus written evidence |
Use 0 for a material failure, 1 for mostly failing, 2 for mixed behavior, 3 for a repeatable pass with minor defects, and 4 for a repeatable pass with clear evidence. Never replace the raw count with the average score.
Downloadable evidence schema
Download the blank CSV test template. Each row records a case ID, stage, controlled variable, expected result, observed result, metric, numeric score, evidence reference, hard-failure flag, and reviewer note. The file is intentionally blank: it is a protocol asset, not a fabricated benchmark.
Hard-failure rule
A hard failure occurs when adult age presentation becomes ambiguous, a real-person identity is introduced, or scene instructions repeatedly override core fictional identity markers.
Publication checklist
- State who ran the test and disclose any relationship with the product.
- Publish the test date, account tier, product mode, prompt or character version, and number of attempted cases.
- Keep failed examples and explain exclusions.
- Separate product facts, reviewer observations, and interpretations.
- Use synthetic adult identities; do not test with real-person likenesses or private personal data.
- Retest after model, memory, policy, pricing, or media-pipeline changes.
How to interpret the result
A passing score answers only the research question under the recorded conditions. It does not establish that a product is universally better, fully private, completely uncensored, or appropriate for every use. Compare methods and evidence before comparing averages. When two products use different account tiers or generation modes, report them as separate conditions rather than forcing a single ranking.
FAQ
Is this an independent Ponys.ai review?
No. This is a transparent, team-maintained test method. Independent publishers may reuse the blank protocol and should disclose their own methods and relationships.
Can the score be used as a marketing claim?
Only with the test date, denominator, configuration, and evidence. A number without those fields is not reproducible.
Why use synthetic adult cases?
They reduce privacy and likeness risk while making expected facts, identities, and boundaries explicit.
What should be cited?
Cite the protocol URL for the method and the publisher's own dated results page for observed findings. Do not cite the blank CSV as if it contained measured results.