{"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/galip-generative-adversarial-clips-for-text","title":"GALIP: Generative Adversarial CLIPs for Text-to-Image Synthesis","arxiv_id":"2301.12959","date":"2023-01-30","proceeding":"CVPR 2023 1","authors":["Ming Tao","Bing-Kun Bao","Hao Tang","Changsheng Xu"],"abstract":"Synthesizing high-fidelity complex images from text is challenging. Based on large pretraining, the autoregressive and diffusion models can synthesize photo-realistic images. Although these large models have shown notable progress, there remain three flaws. 1) These models require tremendous training data and parameters to achieve good performance. 2) The multi-step generation design slows the image synthesis process heavily. 3) The synthesized visual features are difficult to control and require delicately designed prompts. To enable high-quality, efficient, fast, and controllable text-to-image synthesis, we propose Generative Adversarial CLIPs, namely GALIP. GALIP leverages the powerful pretrained CLIP model both in the discriminator and generator. Specifically, we propose a CLIP-based discriminator. The complex scene understanding ability of CLIP enables the discriminator to accurately assess the image quality. Furthermore, we propose a CLIP-empowered generator that induces the visual concepts from CLIP through bridge features and prompts. The CLIP-integrated generator and discriminator boost training efficiency, and as a result, our model only requires about 3% training data and 6% learnable parameters, achieving comparable results to large pretrained autoregressive and diffusion models. Moreover, our model achieves 120 times faster synthesis speed and inherits the smooth latent space from GAN. The extensive experimental results demonstrate the excellent performance of our GALIP. Code is available at https://github.com/tobran/GALIP.","url_abs":"https://arxiv.org/abs/2301.12959v1","url_pdf":"https://arxiv.org/pdf/2301.12959v1.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":"galip-generative-adversarial-clips-for-text","repo_url":"https://github.com/tobran/galip","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"galip-generative-adversarial-clips-for-text","repo_url":"https://github.com/tobran/DF-GAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-to-image-generation-on-coco","task":"Text-to-Image Generation","dataset":"COCO (Common Objects in Context)","model":"GALIP (CC12m)","rank_in_archive_order":33,"of":69,"metrics":{"FID":"12.54"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-image-generation-on-cub","task":"Text-to-Image Generation","dataset":"CUB","model":"GALIP","rank_in_archive_order":4,"of":20,"metrics":{"FID":"10.08"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2301.12959","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12959"}},"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/tobran/galip","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tobran/DF-GAN","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/tobran/GALIP","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6,"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"official":{"samples":9,"ran":6,"repositories":1},"listed":{"samples":2,"ran":1,"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":2,"samples":[{"code_sha256_prefix":"dcdfeb32d64cbd7d","entry":"Affine","repo":"tobran/GALIP","repo_kind":"official","path":"code/models/GALIP.py","file_url":"https://github.com/tobran/GALIP/blob/HEAD/code/models/GALIP.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dcdfeb32d64cbd7d"}},{"code_sha256_prefix":"fa55421f21962920","entry":"CLIP_Adapter","repo":"tobran/GALIP","repo_kind":"official","path":"code/models/GALIP.py","file_url":"https://github.com/tobran/GALIP/blob/HEAD/code/models/GALIP.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fa55421f21962920"}},{"code_sha256_prefix":"95f9b8a9bd0d3592","entry":"DFBLK","repo":"tobran/GALIP","repo_kind":"official","path":"code/models/GALIP.py","file_url":"https://github.com/tobran/GALIP/blob/HEAD/code/models/GALIP.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"95f9b8a9bd0d3592"}},{"code_sha256_prefix":"50f859c074a3bb1e","entry":"G_Block","repo":"tobran/GALIP","repo_kind":"official","path":"code/models/GALIP.py","file_url":"https://github.com/tobran/GALIP/blob/HEAD/code/models/GALIP.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"50f859c074a3bb1e"}},{"code_sha256_prefix":"5a3683f208ea7376","entry":"G_Block","repo":"tobran/DF-GAN","repo_kind":"listed","path":"code/models/GAN.py","file_url":"https://github.com/tobran/DF-GAN/blob/HEAD/code/models/GAN.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"5a3683f208ea7376"}},{"code_sha256_prefix":"700aca9a6a4eac99","entry":"M_Block","repo":"tobran/GALIP","repo_kind":"official","path":"code/models/GALIP.py","file_url":"https://github.com/tobran/GALIP/blob/HEAD/code/models/GALIP.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"700aca9a6a4eac99"}},{"code_sha256_prefix":"7b1f9c201441fa1c","entry":"get_G_in_out_chs","repo":"tobran/GALIP","repo_kind":"official","path":"code/models/GALIP.py","file_url":"https://github.com/tobran/GALIP/blob/HEAD/code/models/GALIP.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7b1f9c201441fa1c"}},{"code_sha256_prefix":"4d38c586ad9ce3fc","entry":"CLIP_Mapper","repo":"tobran/GALIP","repo_kind":"official","path":"code/models/GALIP.py","file_url":"https://github.com/tobran/GALIP/blob/HEAD/code/models/GALIP.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4d38c586ad9ce3fc"}},{"code_sha256_prefix":"98f6bc75d1387ee2","entry":"NetG","repo":"tobran/GALIP","repo_kind":"official","path":"code/models/GALIP.py","file_url":"https://github.com/tobran/GALIP/blob/HEAD/code/models/GALIP.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"98f6bc75d1387ee2"}},{"code_sha256_prefix":"74fe6925fe919a9d","entry":"NetG","repo":"tobran/DF-GAN","repo_kind":"listed","path":"code/models/GAN.py","file_url":"https://github.com/tobran/DF-GAN/blob/HEAD/code/models/GAN.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"74fe6925fe919a9d"}},{"code_sha256_prefix":"95d80ac15e73e11c","entry":"dummy_context_mgr","repo":"tobran/GALIP","repo_kind":"official","path":"code/models/GALIP.py","file_url":"https://github.com/tobran/GALIP/blob/HEAD/code/models/GALIP.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"95d80ac15e73e11c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}