{"observation":{"id":"6afd9a45-ca4d-4336-9bf1-660ad4e41244","tool":"scenario","tool_name":"Scenario","criterion":"identity-preservation","criterion_name":"Identity preservation","criterion_definition":"How closely the generated face matches the reference image across scenes.","criterion_evidence_type":"transformation","criterion_rank_role":"decisive","criterion_rank_role_reason":"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)","scenario":"three-quarter-face-portrait","scenario_name":"Three-quarter face portrait","group_tag":null,"scenario_description":"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.","modality":"image","input_text":null,"input_artifact_refs":[],"stresses":["Identity preservation with partial face angle","Hair texture and updo retention","Skin tone fidelity","Reference-image difficulty under softer lighting"],"verdict":"struggled","score":null,"score_total":null,"note":"Identity 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.","evidence_state":"verified","source":null,"artifacts":[{"url":"https://d3epheqghktydj.cloudfront.net/scenario-scenario-input2-market-f1d754c6924c.png","role":"output","alt":null},{"url":"https://d3epheqghktydj.cloudfront.net/scenario-scenario-input2-market-failure-bodydrift-22580f0f2128.png","role":"output","alt":null}],"run_id":"1dfb8fa4-f7f0-47dc-911b-7db3af467e9a","study_title":"Generate Consistent AI Characters Across Different Scenes and Poses","study_kind":"generation","research_task":"86b96df11","tested_at":null,"completeness":"output-only","input":{"state":"not-captured","text":null,"files":[],"modality":"image","stresses":["Identity preservation with partial face angle","Hair texture and updo retention","Skin tone fidelity","Reference-image difficulty under softer lighting"]},"tool_page_slug":"scenario","tool_url":"https://aidemos.com/tools/scenario","permalink":"https://aidemos.com/evidence/6afd9a45-ca4d-4336-9bf1-660ad4e41244","api_url":"https://ai.aidemos.com/v1/observations/6afd9a45-ca4d-4336-9bf1-660ad4e41244"},"peers":[{"id":"0d13a121-3d00-4ff1-a1f2-e9f788a60b06","tool":"chatgpt","tool_name":"ChatGPT","verdict":"worked","score":null,"score_total":null,"note":"Preserves 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.","artifact_count":1,"thumbnail":"https://d3epheqghktydj.cloudfront.net/chatgpt-chatgpt-input2-interrogation-c78a75b73445.png","evidence_url":"https://aidemos.com/evidence/0d13a121-3d00-4ff1-a1f2-e9f788a60b06"},{"id":"384e897c-c4a6-4bc4-a19d-1afddd298650","tool":"gemini","tool_name":"Gemini","verdict":"worked","score":null,"score_total":null,"note":"With 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.","artifact_count":2,"thumbnail":"https://d3epheqghktydj.cloudfront.net/gemini-input-2-1c4e066a03c3.png","evidence_url":"https://aidemos.com/evidence/384e897c-c4a6-4bc4-a19d-1afddd298650"},{"id":"21c5b413-356f-4640-b66f-fe29ed449e6c","tool":"imagineart","tool_name":"ImagineArt","verdict":"worked","score":null,"score_total":null,"note":"The interrogation-room output stays close to the reference in face shape, skin tone, expression, posture, and overall appearance.","artifact_count":2,"thumbnail":"https://d3epheqghktydj.cloudfront.net/imagineart-input-2-a3afbe926005.png","evidence_url":"https://aidemos.com/evidence/21c5b413-356f-4640-b66f-fe29ed449e6c"},{"id":"5846aa66-eaa9-4e03-ab34-910182cf41f4","tool":"leonardo-ai","tool_name":"Leonardo AI","verdict":"mixed","score":null,"score_total":null,"note":"When the face is turned partly away in a busy scene, the output still feels like the same character but cannot be fully verified.","artifact_count":2,"thumbnail":"https://d3epheqghktydj.cloudfront.net/leonardo-ai-image-95c2a8e685d7.png","evidence_url":"https://aidemos.com/evidence/5846aa66-eaa9-4e03-ab34-910182cf41f4"}],"other_criteria":[{"id":"155ee988-70fe-49f3-8db9-00bf9915545d","criterion":"accessory-and-detail-retention","criterion_name":"Accessory & detail retention","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"It retains curly hair texture especially well for the secondary reference, which the report calls the best hair result for that input.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/155ee988-70fe-49f3-8db9-00bf9915545d"}],"appears_in":[{"page_type":"ranking","slug":"consistent-ai-characters","title":"Best AI Tools for Consistent AI Characters Across Scenes and Poses","url":"https://aidemos.com/best/consistent-ai-characters","binding":"run"}],"same_scenario":[{"id":"0d13a121-3d00-4ff1-a1f2-e9f788a60b06","tool":"chatgpt","tool_name":"ChatGPT","verdict":"worked","score":null,"score_total":null,"note":"Preserves 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."},{"id":"384e897c-c4a6-4bc4-a19d-1afddd298650","tool":"gemini","tool_name":"Gemini","verdict":"worked","score":null,"score_total":null,"note":"With 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."},{"id":"21c5b413-356f-4640-b66f-fe29ed449e6c","tool":"imagineart","tool_name":"ImagineArt","verdict":"worked","score":null,"score_total":null,"note":"The interrogation-room output stays close to the reference in face shape, skin tone, expression, posture, and overall appearance."},{"id":"5846aa66-eaa9-4e03-ab34-910182cf41f4","tool":"leonardo-ai","tool_name":"Leonardo AI","verdict":"mixed","score":null,"score_total":null,"note":"When the face is turned partly away in a busy scene, the output still feels like the same character but cannot be fully verified."}]}