{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004463131,0.0004478248,0.0003908371,0.000125895,0.000204533,0.001375137,0.0006470738,0.0001800555,0.00005051821],"category_scores_gemma":[0.00005840233,0.0003708725,0.0001124426,0.0002288986,0.00004446368,0.0003084202,0.004773831,0.0005052833,0.0001273602],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009484207,"about_ca_system_score_gemma":0.0001446312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002467574,"about_ca_topic_score_gemma":0.00007859006,"domain_scores_codex":[0.9971707,0.0001247988,0.0004682405,0.001473484,0.0003476206,0.0004150913],"domain_scores_gemma":[0.9987769,0.00003272266,0.0001288062,0.0007472063,0.0001754878,0.0001389206],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002698388,0.000658851,0.0000775314,0.001429301,0.0008163901,0.0001852299,0.0215673,0.06064341,0.2931464,0.03037451,0.09157269,0.4995013],"study_design_scores_gemma":[0.0001976792,0.00006864912,0.0001385948,0.0001758133,0.00003802517,0.000006843199,0.00004915261,0.9701791,0.02173301,0.002218664,0.004632056,0.0005624571],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0070969,0.0005446758,0.9798252,0.006883486,0.00153303,0.00114381,0.00001069212,0.0003253245,0.0026369],"genre_scores_gemma":[0.2382119,0.00006070747,0.7578327,0.0006474773,0.0008697212,0.0002347124,0.00002021943,0.0000336137,0.002088941],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9095356,"threshold_uncertainty_score":0.9998743,"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."}}