The interrogation-room output retains the bindi and tight back hair correctly, and the report says harsh lighting reveals more skin texture with less over-smoothing than the other Input 1 scenes.
What was measured
Accessory & detail retention
Retention of specific features — bindi, hair texture, skin tone, jewellery.
decisive for this rankingtransformation
Small identifying details like jewellery, bindi, hair texture, and skin tone are part of maintaining a consistent character identity across generations. (3 of 3 judges)
What was given, what came back
Test input: Full frontal portrait · image
Input — what we sent
Full frontal portrait
Full frontal portrait reference image with fair skin, curly dark hair, bindi, gold jhumka earrings, and a green stone necklace. All features are clearly visible in good natural lighting, making it the easiest identity anchor for the tools.
Why this input is hard
- · Baseline identity preservation
- · Accessory retention
- · Best-case frontal face matching
- · Consistent character reuse across varied scenes
Output — unretouched
Also checked on this input — same tool, 8 other criteria
Expression accuracy✗ FailedThe desert-horse output does not match the prompted intensity and determination; the expression is neutral and composed instead.Expression accuracy✓ WorkedThe interrogation-room output matches the requested serious, guarded expression.Identity preservation✓ WorkedThe interrogation-room output is the strongest Input 1 match, with the eyes, nose, lips, and face shape closest to the reference across the Input 1 scenes.Identity preservation⚠ StruggledThe desert-horse output shows clear identity drift, with the eye shape, nose structure, jawline, and face proportions all differing from the reference.Identity preservation◐ MixedThe warm-cafe output keeps the subject recognisable but not exact; the report says eye colour shifts from black to brown and facial proportions are slightly altered.Scene compliance✓ WorkedThe warm-cafe output follows the prompt well, with the café environment, window lighting, outfit, and hairstyle all rendered correctly.Scene compliance◐ MixedThe interrogation-room output follows the harsh lighting, serious expression, formal clothing, tight back hair, and bindi, but it shows less body than the prompt specified.Scene compliance✓ WorkedThe desert-horse output follows the scene prompt well, including the black horse, desert setting, riding outfit, scarf, braided hair, and dynamic motion.
Provenance
- Observation
- 6650d49c-d987-49c9-861d-9cd900685ae5
- Evidence run
- 1dfb8fa4-f7f0-47dc-911b-7db3af467e9a
- Study
- Generate Consistent AI Characters Across Different Scenes and Poses
- Research task
- 86b96df11
- Tested at
- not recorded
- Source
- first-party
- Evidence state
- verified
- Proof shown
- input + output shown
- Cost / latency
- not captured
- Repeat run
- not captured
- Tester
- not captured
The last three rows are honest blanks, not placeholders — our capture has no field for them yet.
Query this
get_evidence({
tool: "imagineart"
})MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, same check — 2 other tools
measured on Accessory & detail retention
ChatGPT✓ WorkedPreserves all three named accessories in a frontal portrait with near-100% retention: the bindi, gold jhumka earrings, and green stone necklace stay visible, and the hair colour/texture remains consistent; the main trade-off is slightly over-smoothed skin texture.Leonardo AI⚠ StruggledIt drops the reference's natural curl pattern and smooths hair and skin detail into a more stylised finish.
This evidence is published in
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com