{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/attngan-fine-grained-text-to-image-generation","title":"AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks","arxiv_id":"1711.10485","date":"2017-11-28","proceeding":"CVPR 2018 6","authors":["Tao Xu","Pengchuan Zhang","Qiuyuan Huang","Han Zhang","Zhe Gan","Xiaolei Huang","Xiaodong He"],"abstract":"In this paper, we propose an Attentional Generative Adversarial Network\n(AttnGAN) that allows attention-driven, multi-stage refinement for fine-grained\ntext-to-image generation. With a novel attentional generative network, the\nAttnGAN can synthesize fine-grained details at different subregions of the\nimage by paying attentions to the relevant words in the natural language\ndescription. In addition, a deep attentional multimodal similarity model is\nproposed to compute a fine-grained image-text matching loss for training the\ngenerator. The proposed AttnGAN significantly outperforms the previous state of\nthe art, boosting the best reported inception score by 14.14% on the CUB\ndataset and 170.25% on the more challenging COCO dataset. A detailed analysis\nis also performed by visualizing the attention layers of the AttnGAN. It for\nthe first time shows that the layered attentional GAN is able to automatically\nselect the condition at the word level for generating different parts of the\nimage.","url_abs":"http://arxiv.org/abs/1711.10485v1","url_pdf":"http://arxiv.org/pdf/1711.10485v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"attngan-fine-grained-text-to-image-generation","repo_url":"https://github.com/ChihchengHsieh/AttnGAN_Implementation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"attngan-fine-grained-text-to-image-generation","repo_url":"https://github.com/Maymaher/StackGANv2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"attngan-fine-grained-text-to-image-generation","repo_url":"https://github.com/Vigneshthanga/stackGAN-v2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"attngan-fine-grained-text-to-image-generation","repo_url":"https://github.com/aleksey-egorov/attngan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"attngan-fine-grained-text-to-image-generation","repo_url":"https://github.com/alexmotogna/attngan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"attngan-fine-grained-text-to-image-generation","repo_url":"https://github.com/alexmotogna/generatorapi","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"attngan-fine-grained-text-to-image-generation","repo_url":"https://github.com/huiyegit/T2I_CL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"attngan-fine-grained-text-to-image-generation","repo_url":"https://github.com/komiya-m/MirrorGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"attngan-fine-grained-text-to-image-generation","repo_url":"https://github.com/oxygenlu/ratlip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"attngan-fine-grained-text-to-image-generation","repo_url":"https://github.com/pioneerAlpha/BanglaText2ImageGeneration","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"attngan-fine-grained-text-to-image-generation","repo_url":"https://github.com/priscillalui/StackGAN-Stories","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"attngan-fine-grained-text-to-image-generation","repo_url":"https://github.com/rightlit/cycle-image-gan-rev","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"attngan-fine-grained-text-to-image-generation","repo_url":"https://github.com/roxanasoto/AttGanESRGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"attngan-fine-grained-text-to-image-generation","repo_url":"https://github.com/sidward14/Style-AttnGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"attngan-fine-grained-text-to-image-generation","repo_url":"https://github.com/taki0112/AttnGAN-Tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"attngan-fine-grained-text-to-image-generation","repo_url":"https://github.com/ucsd-ml-arts/ml-art-final-jeffrey","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"attngan-fine-grained-text-to-image-generation","repo_url":"https://github.com/Shuvrajit9904/PairedCycleGAN-tf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"attngan-fine-grained-text-to-image-generation","repo_url":"https://github.com/bprabhakar/text-to-image","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"attngan-fine-grained-text-to-image-generation","repo_url":"https://github.com/davidstap/AttnGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"attngan-fine-grained-text-to-image-generation","repo_url":"https://github.com/taoxugit/AttnGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"image-text-matching","task_name":"Image-text matching"},{"task_slug":"text-matching","task_name":"Text Matching"},{"task_slug":"text-to-image-generation-1","task_name":"Text to Image Generation"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-to-image-generation-on-cub","task":"Text-to-Image Generation","dataset":"CUB","model":"AttnGAN","rank_in_archive_order":19,"of":20,"metrics":{"Inception score":"4.36"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-image-generation-on-ms-coco","task":"Text-to-Image Generation","dataset":"MS-COCO","model":"AttnGAN","rank_in_archive_order":1,"of":2,"metrics":{"FID":"35.49","Inception score":"25.89","SOA-C":"25.88"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-image-generation-on-multi-modal","task":"Text-to-Image Generation","dataset":"Multi-Modal-CelebA-HQ","model":"AttnGAN","rank_in_archive_order":8,"of":10,"metrics":{"Acc":"13.0","FID":"125.98","LPIPS":"0.512","Real":"11.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.10485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.10485"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bprabhakar/text-to-image","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Maymaher/StackGANv2","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ucsd-ml-arts/ml-art-final-jeffrey","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/taoxugit/AttnGAN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rightlit/cycle-image-gan-rev","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/davidstap/AttnGAN","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/huiyegit/T2I_CL","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alexmotogna/attngan","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sidward14/Style-AttnGAN","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/komiya-m/MirrorGAN","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pioneerAlpha/BanglaText2ImageGeneration","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aleksey-egorov/attngan","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ChihchengHsieh/AttnGAN_Implementation","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Shuvrajit9904/PairedCycleGAN-tf","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/priscillalui/StackGAN-Stories","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/taki0112/AttnGAN-Tensorflow","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/roxanasoto/AttGanESRGAN","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/oxygenlu/ratlip","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Vigneshthanga/stackGAN-v2","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alexmotogna/generatorapi","reach":{"status":"unanswered"}}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"listed":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"19379807ba70daaa","entry":"conv1x1","repo":"alexmotogna/attngan","repo_kind":"listed","path":"code/model.py","file_url":"https://github.com/alexmotogna/attngan/blob/HEAD/code/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"19379807ba70daaa"}},{"code_sha256_prefix":"ea864de5c552bc4a","entry":"conv3x3","repo":"alexmotogna/attngan","repo_kind":"listed","path":"code/model.py","file_url":"https://github.com/alexmotogna/attngan/blob/HEAD/code/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ea864de5c552bc4a"}},{"code_sha256_prefix":"0785179f5f580004","entry":"upBlock","repo":"alexmotogna/attngan","repo_kind":"listed","path":"code/model.py","file_url":"https://github.com/alexmotogna/attngan/blob/HEAD/code/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0785179f5f580004"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}