{"observation":{"id":"0ffd702f-0559-4b2e-88f3-a9711a961585","tool":"chatgpt","tool_name":"ChatGPT","criterion":"accessory-and-detail-retention","criterion_name":"Accessory & detail retention","criterion_definition":"Retention of specific features — bindi, hair texture, skin tone, jewellery.","criterion_evidence_type":"transformation","criterion_rank_role":"decisive","criterion_rank_role_reason":"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)","scenario":"full-frontal-portrait","scenario_name":"Full frontal portrait","group_tag":null,"scenario_description":"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.","modality":"image","input_text":null,"input_artifact_refs":[],"stresses":["Baseline identity preservation","Accessory retention","Best-case frontal face matching","Consistent character reuse across varied scenes"],"verdict":"worked","score":null,"score_total":null,"note":"Preserves all three named accessories in a frontal portrait with near-100% retention: the bindi, gold jhumka earrings, and green stone necklace stay visible, and the hair colour/texture remains consistent; the main trade-off is slightly over-smoothed skin texture.","evidence_state":"verified","source":null,"artifacts":[{"url":"https://d3epheqghktydj.cloudfront.net/chatgpt-chatgpt-input1-warm-cafe-fd6cb3b29e87.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":["Baseline identity preservation","Accessory retention","Best-case frontal face matching","Consistent character reuse across varied scenes"]},"tool_page_slug":"chatgpt","tool_url":"https://aidemos.com/tools/chatgpt","permalink":"https://aidemos.com/evidence/0ffd702f-0559-4b2e-88f3-a9711a961585","api_url":"https://ai.aidemos.com/v1/observations/0ffd702f-0559-4b2e-88f3-a9711a961585"},"peers":[{"id":"6650d49c-d987-49c9-861d-9cd900685ae5","tool":"imagineart","tool_name":"ImagineArt","verdict":"worked","score":null,"score_total":null,"note":"The interrogation-room output retains the bindi and tight back hair correctly, and the report says harsh lighting reveals more skin texture with less over-smoothing than the other Input 1 scenes.","artifact_count":2,"thumbnail":"https://d3epheqghktydj.cloudfront.net/imagineart-input-1-561e7b836cdd.png","evidence_url":"https://aidemos.com/evidence/6650d49c-d987-49c9-861d-9cd900685ae5"},{"id":"2f9fb0e6-bf73-43da-9569-51dac9414373","tool":"leonardo-ai","tool_name":"Leonardo AI","verdict":"struggled","score":null,"score_total":null,"note":"It drops the reference's natural curl pattern and smooths hair and skin detail into a more stylised finish.","artifact_count":2,"thumbnail":"https://d3epheqghktydj.cloudfront.net/leonardo-ai-input-1-5e817fd0f4a6.png","evidence_url":"https://aidemos.com/evidence/2f9fb0e6-bf73-43da-9569-51dac9414373"}],"other_criteria":[{"id":"dff2415a-48ec-4868-bc7e-970100f82c02","criterion":"expression-accuracy","criterion_name":"Expression accuracy","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"Captures the cold, guarded, unsmiling expression well, with a tight jaw and sharp eyes; the report marks this as the best expression accuracy of the five scenes.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/dff2415a-48ec-4868-bc7e-970100f82c02"},{"id":"6636ced6-0dd3-4d55-aed4-228102bc03f6","criterion":"expression-accuracy","criterion_name":"Expression accuracy","rank_role":"decisive","verdict":"failed","score":null,"score_total":null,"note":"Misses the prompted brave/determined emotional tone and instead outputs a soft neutral expression, leaving the scene with essentially no emotional alignment.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/6636ced6-0dd3-4d55-aed4-228102bc03f6"},{"id":"163f2da9-8a7d-4d76-bc0b-a4ed35e52693","criterion":"identity-preservation","criterion_name":"Identity preservation","rank_role":"decisive","verdict":"struggled","score":null,"score_total":null,"note":"Identity 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.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/163f2da9-8a7d-4d76-bc0b-a4ed35e52693"},{"id":"b461a3a8-6c06-4646-aed7-678dd35f3fa1","criterion":"identity-preservation","criterion_name":"Identity preservation","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"Keeps facial structure close to the reference in a frontal composition and is described as the best output from this input, with identity held strongly overall.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/b461a3a8-6c06-4646-aed7-678dd35f3fa1"},{"id":"73459b52-0b45-453e-b26a-b2c96a3eeb39","criterion":"scene-compliance","criterion_name":"Scene compliance","rank_role":"decisive","verdict":"mixed","score":null,"score_total":null,"note":"Only partially follows the cafe scene: the subject placement is correct, but the background stays weak and the coffee cup and plate are barely visible, so the environment lacks atmosphere.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/73459b52-0b45-453e-b26a-b2c96a3eeb39"},{"id":"be5f9438-9b78-49b9-8383-53ad4dd75958","criterion":"scene-compliance","criterion_name":"Scene compliance","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"Recreates the requested desert action scene accurately, including the environment, scene-appropriate attire, and hairstyle, with no visible distortion or artifacts.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/be5f9438-9b78-49b9-8383-53ad4dd75958"},{"id":"bff43a61-6f40-4da2-922d-1c38161337af","criterion":"scene-compliance","criterion_name":"Scene compliance","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"Follows the full-frontal interrogation setup precisely: the navy shirt, hands on the metal table, and plain background are all present as prompted.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/bff43a61-6f40-4da2-922d-1c38161337af"}],"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":"6650d49c-d987-49c9-861d-9cd900685ae5","tool":"imagineart","tool_name":"ImagineArt","verdict":"worked","score":null,"score_total":null,"note":"The interrogation-room output retains the bindi and tight back hair correctly, and the report says harsh lighting reveals more skin texture with less over-smoothing than the other Input 1 scenes."},{"id":"2f9fb0e6-bf73-43da-9569-51dac9414373","tool":"leonardo-ai","tool_name":"Leonardo AI","verdict":"struggled","score":null,"score_total":null,"note":"It drops the reference's natural curl pattern and smooths hair and skin detail into a more stylised finish."}]}