Dense natural curls are not retained; the tool flattens them into straight, oily-looking hair.

⚠ Struggled🧾 artifact-verifiedinput + output shownTest date not recordedLeonardo AI
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: Three-quarter face portrait · image
Input — what we sent
Input file 1 — as supplied
Input file 1 — as supplied
Input file 2 — as supplied
Three-quarter face portrait
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
image
Provenance
Observation
35aac695-703c-4e69-a46a-714a16e4a073
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: "leonardo-ai"
})
MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, same check — 4 other tools
measured on Accessory & detail retention
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com