It can render the desert action scene cleanly while replacing the reference with a different character whose face, proportions and overall appearance no longer match.
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, 3 other criteria
Accessory & detail retention⚠ StruggledIt drops the reference's natural curl pattern and smooths hair and skin detail into a more stylised finish.Expression accuracy✗ FailedIt does not translate an explicitly angry or guarded prompt into facial expression, defaulting to calm neutrality.Scene compliance◐ MixedIt can place the subject in a believable interrogation setup with the correct outfit, but the room stays too neat and loses the harsh institutional atmosphere.
Provenance
- Observation
- 862ea299-ef77-4932-baf5-89190b469aae
- 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 Identity preservation
ChatGPT⚠ StruggledIdentity 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.Gemini✗ FailedIn the horse-riding scene, the tool can erase the reference face entirely: the report calls the identity match very weak and says the output is a completely different character with changed face shape, eyes, and eyebrows.ImagineArt✓ 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.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