The rooftop scene is only partially followed: the outfit, rooftop, skyline, and body pose are present, but the face is too frontal, the occlusion stress condition is missed, and the golden-hour lighting shifts cooler and more daytime-like.
What was measured
Scene compliance
How accurately the output follows the prompt — environment, attire, pose, props.
decisive for this rankingtransformation
The ranking is about using the character in varied scenes and poses, so following the requested environment, attire, pose, and props is central to success. (3 of 3 judges)
What was given, what came back
Test input: Near-profile occluded portrait stress test · 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.
Near-profile portrait reference used as the maximum-difficulty stress test: face turned roughly 80–90 degrees, one eye partially occluded by fringe, short dark wavy hair, and natural outdoor lighting. Designed to probe whether tools can preserve identity under severe pose and occlusion.
Why this input is hard
- · Near-profile identity preservation
- · Occlusion handling
- · Extreme pose consistency
- · Lighting and hair-detail retention under stress
Output — unretouched
Also checked on this input — same tool, 2 other criteria
Provenance
- Observation
- f0e88898-addc-4e27-aaf7-43d6c35286fc
- 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: "gemini"
})MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, same check — 4 other tools
measured on Scene compliance
ChatGPT✓ WorkedMatches the rooftop prompt well: full-body framing, black turtleneck, beige wide-leg trousers, golden-hour amber lighting, city skyline, and rooftop railing are all present.ImagineArt⚠ StruggledThe rooftop output only partially follows the prompt: the sleeve length is wrong, the arms are asymmetrically raised, and the golden-hour lighting is only partly captured.Leonardo AI✓ WorkedIt follows the rooftop, city skyline, golden-hour light and outfit correctly, even though the face angle is too extreme for identity testing.Scenario✓ WorkedIt executes the sunset rooftop prompt cleanly, including amber lighting, correct shadow fall, and the black top with beige trousers.
This evidence is published in
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com