{"id":"W4392619076","doi":"10.1145/3613904.3642803","title":"PromptCharm: Text-to-Image Generation through Multi-modal Prompting and Refinement","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":97,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Usability; Modal; Field (mathematics); Image editing; Inpainting; Quality (philosophy); Image (mathematics); Human–computer interaction; Generative grammar; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001443957,0.001808181,0.0006650862,0.0007105509,0.000369163,0.0009503532,0.002118252,0.00126366,0.020322],"category_scores_gemma":[0.007374861,0.0006230996,0.0009871338,0.0003251825,0.0006581991,0.002163423,0.00300419,0.001088111,0.004595656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003216143,"about_ca_system_score_gemma":0.0003942742,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000573133,"about_ca_topic_score_gemma":0.0008441424,"domain_scores_codex":[0.999343,0.0001988746,0.00003970292,0.0001914738,0.0001758349,0.00005110553],"domain_scores_gemma":[0.9973491,0.00172961,0.0001260219,0.0003910675,0.0002588629,0.0001453616],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002304582,0.0007481638,0.002630219,0.002247941,0.0001060804,0.001889777,0.005246392,0.01308992,0.1872466,0.01117359,0.06166058,0.7116562],"study_design_scores_gemma":[0.001304427,0.002057884,0.006472805,0.0003712138,0.0001547823,0.003341607,0.001396623,0.5229989,0.2235538,0.03808748,0.1997178,0.0005427353],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02271876,0.000247764,0.8595999,0.0001717673,0.0001667374,0.0005981618,0.0007160067,0.1118379,0.003942954],"genre_scores_gemma":[0.1719843,0.0002425486,0.8089911,0.0003433567,0.00007407198,0.001114286,0.001783425,0.006798631,0.008668307],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.020322,"threshold_uncertainty_score":0.06798387,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05568774798347245,"score_gpt":0.3023654428651326,"score_spread":0.2466776948816601,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}