Identity drops to only a 50–70% match in an action scene, with significant facial-structure drift away from the reference even though the body styling remains plausible.
What was measured
Identity preservation
How closely the generated face matches the reference image across scenes.
decisive for this rankingtransformation
This is the core of the task: the tool must keep the same character looking like the reference image across scenes. (3 of 3 judges)
What was given, what came back
Test input: Full frontal portrait · image
Input — what we sent
Input not captured
This run recorded no prompt or input file for the test, so we cannot show you what produced the result below. Capture gaps are tracked, not hidden.
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, 6 other criteria
Accessory & detail retention✓ 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.Expression accuracy✓ WorkedCaptures the cold, guarded, unsmiling expression well, with a tight jaw and sharp eyes; the report marks this as the best expression accuracy of the five scenes.Expression accuracy✗ FailedMisses the prompted brave/determined emotional tone and instead outputs a soft neutral expression, leaving the scene with essentially no emotional alignment.Scene compliance◐ MixedOnly partially follows the cafe scene: the subject placement is correct, but the background stays weak and the coffee cup and plate are barely visible, so the environment lacks atmosphere.Scene compliance✓ WorkedRecreates the requested desert action scene accurately, including the environment, scene-appropriate attire, and hairstyle, with no visible distortion or artifacts.Scene compliance✓ WorkedFollows the full-frontal interrogation setup precisely: the navy shirt, hands on the metal table, and plain background are all present as prompted.
Provenance
- Observation
- 163f2da9-8a7d-4d76-bc0b-a4ed35e52693
- 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
- output only
- 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: "chatgpt"
})MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, same check — 4 other tools
measured on Identity preservation
Gemini✓ WorkedThe plain interrogation setup is the best identity anchor for this input, keeping the eyes, face shape, nose, and overall facial structure close to the reference.ImagineArt⚠ StruggledThe desert-horse output shows clear identity drift, with the eye shape, nose structure, jawline, and face proportions all differing from the reference.Leonardo AI◐ MixedIt can keep a frontal character recognisable in a new scene, but the face is refined enough that the match is only moderate.Scenario✓ WorkedThe tool can keep a subject recognisably the same person in an action scene, with face shape, eyes, and overall look staying close to the reference.
This evidence is published in
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com