The warm cafe prompt is followed strongly, with the cozy cafe setting, warm lighting, background blur, sweater, braided hairstyle, and natural pose all rendered correctly.
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: Full frontal portrait · image
Input — what we sent
Chatgpt input 1.png
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, 4 other criteria
Expression accuracy✓ WorkedThe tool can capture a prompted angry and guarded mood, with direct eye contact and an intense expression in the interrogation shot.Identity preservation✗ FailedAgainst the full-frontal reference, the warm cafe output can drift into a different character: it was judged very weak and the report says multiple facial features changed.Identity preservation✗ 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.Identity preservation✓ 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.
Provenance
- Observation
- 4478b970-4ebb-48c8-9921-315ce84fd9fe
- 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✓ WorkedFollows the full-frontal interrogation setup precisely: the navy shirt, hands on the metal table, and plain background are all present as prompted.ImagineArt✓ WorkedThe warm-cafe output follows the prompt well, with the café environment, window lighting, outfit, and hairstyle all rendered correctly.Leonardo AI◐ 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.Scenario◐ MixedIt can reproduce the interrogation-room setup and wardrobe, but the requested harsh mood is softened because the lighting and facial affect stay gentle.
This evidence is published in
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com