{"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/lafite-towards-language-free-training-for","title":"LAFITE: Towards Language-Free Training for Text-to-Image Generation","arxiv_id":"2111.13792","date":"2021-11-27","proceeding":null,"authors":["Yufan Zhou","Ruiyi Zhang","Changyou Chen","Chunyuan Li","Chris Tensmeyer","Tong Yu","Jiuxiang Gu","Jinhui Xu","Tong Sun"],"abstract":"One of the major challenges in training text-to-image generation models is the need of a large number of high-quality image-text pairs. While image samples are often easily accessible, the associated text descriptions typically require careful human captioning, which is particularly time- and cost-consuming. In this paper, we propose the first work to train text-to-image generation models without any text data. Our method leverages the well-aligned multi-modal semantic space of the powerful pre-trained CLIP model: the requirement of text-conditioning is seamlessly alleviated via generating text features from image features. Extensive experiments are conducted to illustrate the effectiveness of the proposed method. We obtain state-of-the-art results in the standard text-to-image generation tasks. Importantly, the proposed language-free model outperforms most existing models trained with full image-text pairs. Furthermore, our method can be applied in fine-tuning pre-trained models, which saves both training time and cost in training text-to-image generation models. Our pre-trained model obtains competitive results in zero-shot text-to-image generation on the MS-COCO dataset, yet with around only 1% of the model size and training data size relative to the recently proposed large DALL-E model.","url_abs":"https://arxiv.org/abs/2111.13792v3","url_pdf":"https://arxiv.org/pdf/2111.13792v3.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":"lafite-towards-language-free-training-for","repo_url":"https://github.com/drboog/Lafite","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"lafite-towards-language-free-training-for","repo_url":"https://github.com/drboog/Shifted_Diffusion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"CC0-1.0"}},{"paper_slug":"lafite-towards-language-free-training-for","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"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"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"},{"task_slug":"zero-shot-text-to-image-generation","task_name":"Zero-Shot Text-to-Image Generation"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"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":"Lafite","rank_in_archive_order":20,"of":69,"metrics":{"FID":"8.12","Inception score":"32.34","SOA-C":"61.09"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-image-generation-on-coco","task":"Text-to-Image Generation","dataset":"COCO (Common Objects in Context)","model":"Lafite (zero-shot)","rank_in_archive_order":52,"of":69,"metrics":{"FID":"26.94","FID-1":"22.97","FID-2":"18.70","FID-4":"15.72","FID-8":"14.79","Inception score":"26.02"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-image-generation-on-cub","task":"Text-to-Image Generation","dataset":"CUB","model":"Lafite","rank_in_archive_order":7,"of":20,"metrics":{"FID":"10.48","Inception score":"5.97"},"uses_additional_data":true},{"leaderboard":"/sota/text-to-image-generation-on-multi-modal","task":"Text-to-Image Generation","dataset":"Multi-Modal-CelebA-HQ","model":"Lafite","rank_in_archive_order":2,"of":10,"metrics":{"FID":"12.54"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2111.13792","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.13792"}},"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/drboog/Lafite","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/drboog/Shifted_Diffusion","reach":{"status":"ok","spdx":"CC0-1.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/oxygenlu/ratlip","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":2,"ran_draft_wrong":2,"unverified":14},"by_repo_kind":{"official":{"samples":6,"ran":2,"repositories":1},"listed":{"samples":12,"ran":2,"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":"988a3c854b1b13d0","entry":"autopad","repo":"oxygenlu/ratlip","repo_kind":"listed","path":"code/models/RATLIP.py","file_url":"https://github.com/oxygenlu/ratlip/blob/HEAD/code/models/RATLIP.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"988a3c854b1b13d0"}},{"code_sha256_prefix":"a2b45afa097b55b6","entry":"file_ext","repo":"drboog/Lafite","repo_kind":"official","path":"dataset_tool.py","file_url":"https://github.com/drboog/Lafite/blob/HEAD/dataset_tool.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a2b45afa097b55b6"}},{"code_sha256_prefix":"7b1f9c201441fa1c","entry":"get_G_in_out_chs","repo":"oxygenlu/ratlip","repo_kind":"listed","path":"code/models/RATLIP.py","file_url":"https://github.com/oxygenlu/ratlip/blob/HEAD/code/models/RATLIP.py","link_basis":"harvester_set","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":"dd1dc700e87f36cc","entry":"maybe_min","repo":"drboog/Lafite","repo_kind":"official","path":"dataset_tool.py","file_url":"https://github.com/drboog/Lafite/blob/HEAD/dataset_tool.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dd1dc700e87f36cc"}},{"code_sha256_prefix":"a2f5ae76d8f7b686","entry":"MA_GP_FP32","repo":"oxygenlu/ratlip","repo_kind":"listed","path":"code/lib/modules.py","file_url":"https://github.com/oxygenlu/ratlip/blob/HEAD/code/lib/modules.py","link_basis":"harvester_set","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":"a2f5ae76d8f7b686"}},{"code_sha256_prefix":"e881f3aa13c1dfca","entry":"MA_GP_MP","repo":"oxygenlu/ratlip","repo_kind":"listed","path":"code/lib/modules.py","file_url":"https://github.com/oxygenlu/ratlip/blob/HEAD/code/lib/modules.py","link_basis":"harvester_set","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":"e881f3aa13c1dfca"}},{"code_sha256_prefix":"1307498a08bac630","entry":"choose_model","repo":"oxygenlu/ratlip","repo_kind":"listed","path":"code/lib/utils.py","file_url":"https://github.com/oxygenlu/ratlip/blob/HEAD/code/lib/utils.py","link_basis":"harvester_set","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":"1307498a08bac630"}},{"code_sha256_prefix":"080da024bbcdf7bc","entry":"custom_reshape","repo":"drboog/Lafite","repo_kind":"official","path":"dataset_tool.py","file_url":"https://github.com/drboog/Lafite/blob/HEAD/dataset_tool.py","link_basis":"harvester_set","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":"080da024bbcdf7bc"}},{"code_sha256_prefix":"f8cd9b9545621bc0","entry":"get_D_in_out_chs","repo":"oxygenlu/ratlip","repo_kind":"listed","path":"code/models/RATLIP.py","file_url":"https://github.com/oxygenlu/ratlip/blob/HEAD/code/models/RATLIP.py","link_basis":"harvester_set","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":"f8cd9b9545621bc0"}},{"code_sha256_prefix":"1b820b0f9416f8b5","entry":"get_fix_data","repo":"oxygenlu/ratlip","repo_kind":"listed","path":"code/lib/datasets.py","file_url":"https://github.com/oxygenlu/ratlip/blob/HEAD/code/lib/datasets.py","link_basis":"harvester_set","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":"1b820b0f9416f8b5"}},{"code_sha256_prefix":"964f3c53ef8df7cd","entry":"get_imgs","repo":"drboog/Lafite","repo_kind":"official","path":"datasets/datasets_bird_coco.py","file_url":"https://github.com/drboog/Lafite/blob/HEAD/datasets/datasets_bird_coco.py","link_basis":"harvester_set","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":"964f3c53ef8df7cd"}},{"code_sha256_prefix":"7092063b4f5817fa","entry":"get_one_batch_data","repo":"oxygenlu/ratlip","repo_kind":"listed","path":"code/lib/datasets.py","file_url":"https://github.com/oxygenlu/ratlip/blob/HEAD/code/lib/datasets.py","link_basis":"harvester_set","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":"7092063b4f5817fa"}},{"code_sha256_prefix":"2c903601913a4f24","entry":"load_filenames","repo":"drboog/Lafite","repo_kind":"official","path":"datasets/datasets_bird_coco.py","file_url":"https://github.com/drboog/Lafite/blob/HEAD/datasets/datasets_bird_coco.py","link_basis":"harvester_set","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":"2c903601913a4f24"}},{"code_sha256_prefix":"6364051ef9e418c9","entry":"load_npz","repo":"oxygenlu/ratlip","repo_kind":"listed","path":"code/lib/utils.py","file_url":"https://github.com/oxygenlu/ratlip/blob/HEAD/code/lib/utils.py","link_basis":"harvester_set","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":"6364051ef9e418c9"}},{"code_sha256_prefix":"edd67ef305db54ef","entry":"params_count","repo":"oxygenlu/ratlip","repo_kind":"listed","path":"code/lib/utils.py","file_url":"https://github.com/oxygenlu/ratlip/blob/HEAD/code/lib/utils.py","link_basis":"harvester_set","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":"edd67ef305db54ef"}},{"code_sha256_prefix":"5123f0670f4adce1","entry":"prepare_data","repo":"drboog/Lafite","repo_kind":"official","path":"datasets/datasets_bird_coco.py","file_url":"https://github.com/drboog/Lafite/blob/HEAD/datasets/datasets_bird_coco.py","link_basis":"harvester_set","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":"5123f0670f4adce1"}},{"code_sha256_prefix":"31efd08e9e090d29","entry":"prepare_data","repo":"oxygenlu/ratlip","repo_kind":"listed","path":"code/lib/datasets.py","file_url":"https://github.com/oxygenlu/ratlip/blob/HEAD/code/lib/datasets.py","link_basis":"harvester_set","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":"31efd08e9e090d29"}},{"code_sha256_prefix":"d4c40e264c45657c","entry":"prepare_dataset","repo":"oxygenlu/ratlip","repo_kind":"listed","path":"code/lib/perpare.py","file_url":"https://github.com/oxygenlu/ratlip/blob/HEAD/code/lib/perpare.py","link_basis":"harvester_set","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":"d4c40e264c45657c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}