The market output keeps the subject reasonably close overall, but the report still calls the identity match moderate because the skin tone shifts and other facial details change slightly.
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: Three-quarter face portrait · image
Input — what we sent
Three-quarter face portrait
Three-quarter face reference image with medium-dark skin, tight curly hair in an updo, bindi, and a floral dress. The partial angle and softer lighting make it a harder reference than the frontal portrait and are meant to stress identity consistency.
Why this input is hard
- · Identity preservation with partial face angle
- · Hair texture and updo retention
- · Skin tone fidelity
- · Reference-image difficulty under softer lighting
Output — unretouched
Also checked on this input — same tool, 5 other criteria
Accessory & detail retention⚠ StruggledThe interrogation-room output flattens the dense curly hair substantially and makes the eyebrows look shorter and slightly uneven.Accessory & detail retention⚠ StruggledThe market output lightens the skin tone, removes visible skin marks and scars through smoothing, and makes the lips look less full and more evenly coloured.Expression accuracy✓ WorkedThe interrogation-room output preserves the reference expression well.Scene compliance✓ WorkedThe interrogation-room output follows the clothing, lighting, pose, and environment accurately.Scene compliance✓ WorkedThe market output renders the market environment realistically and follows the prompt well.
Provenance
- Observation
- 5ec13c6e-a74e-4f10-abd3-dc5f4dfb070c
- 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 — 4 other tools
measured on Identity preservation
ChatGPT✓ WorkedPreserves face shape and structure well in a frontal composition, though the report notes a slight darkening and a marginally wider, rounder face than the reference.Gemini✓ WorkedWith a 3/4 reference, the interrogation-room output still preserves identity well, keeping face shape, skin tone, curly hair texture, eyebrows, and overall structure close to the input.Leonardo AI◐ MixedOn a harder 3/4 reference, it can keep face shape, skin tone and eyebrows close, but the hair geometry drifts enough that the result is only partly faithful.Scenario⚠ StruggledIdentity drifts in a crowded full-body scene, with a narrower jawline and a thinner body making the result read as a similar-looking person rather than the same subject.
This evidence is published in
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com