{"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/zero-shot-text-to-image-generation","title":"Zero-Shot Text-to-Image Generation","arxiv_id":"2102.12092","date":"2021-02-24","proceeding":null,"authors":["Aditya Ramesh","Mikhail Pavlov","Gabriel Goh","Scott Gray","Chelsea Voss","Alec Radford","Mark Chen","Ilya Sutskever"],"abstract":"Text-to-image generation has traditionally focused on finding better modeling assumptions for training on a fixed dataset. These assumptions might involve complex architectures, auxiliary losses, or side information such as object part labels or segmentation masks supplied during training. We describe a simple approach for this task based on a transformer that autoregressively models the text and image tokens as a single stream of data. With sufficient data and scale, our approach is competitive with previous domain-specific models when evaluated in a zero-shot fashion.","url_abs":"https://arxiv.org/abs/2102.12092v2","url_pdf":"https://arxiv.org/pdf/2102.12092v2.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":"zero-shot-text-to-image-generation","repo_url":"https://github.com/openai/DALL-E","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"zero-shot-text-to-image-generation","repo_url":"https://github.com/JoyPang123/Textmage","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"zero-shot-text-to-image-generation","repo_url":"https://github.com/avihu111/viewpoint_disentanglement","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"zero-shot-text-to-image-generation","repo_url":"https://github.com/borisdayma/dalle-mini","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"zero-shot-text-to-image-generation","repo_url":"https://github.com/explainingai-code/Dalle-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"zero-shot-text-to-image-generation","repo_url":"https://github.com/jam-ing/DALLE-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"zero-shot-text-to-image-generation","repo_url":"https://github.com/kakaobrain/rq-vae-transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"zero-shot-text-to-image-generation","repo_url":"https://github.com/liuqk3/put","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"zero-shot-text-to-image-generation","repo_url":"https://github.com/lucidrains/DALLE-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"zero-shot-text-to-image-generation","repo_url":"https://github.com/neonbjb/tortoise-tts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"zero-shot-text-to-image-generation","repo_url":"https://github.com/teoaivalis/Search-Based_Data_Influence_Analysis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"zero-shot-text-to-image-generation","repo_url":"https://github.com/xyzforever/bevt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"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":"1-bit-adam","method_name":"1-bit Adam"},{"method_slug":"adam","method_name":"Adam"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2102.12092","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.12092"}},"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/kakaobrain/rq-vae-transformer","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/neonbjb/tortoise-tts","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/openai/DALL-E","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/borisdayma/dalle-mini","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jam-ing/DALLE-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xyzforever/bevt","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JoyPang123/Textmage","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lucidrains/DALLE-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/explainingai-code/Dalle-Pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/teoaivalis/Search-Based_Data_Influence_Analysis","reach":{"status":"unanswered"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/MinfengZhu/DM-GAN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/avihu111/viewpoint_disentanglement","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/liuqk3/put","reach":{"status":"unanswered"}}],"summary":{"ran_draft_wrong":4,"ran_violates":2,"ran_honours":1},"by_repo_kind":{"listed":{"samples":5,"ran":5,"repositories":3}},"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":3,"samples":[{"code_sha256_prefix":"fe5dd5258046898c","entry":"always","repo":"jam-ing/DALLE-pytorch","repo_kind":"listed","path":"dalle_pytorch/dalle_pytorch.py","file_url":"https://github.com/jam-ing/DALLE-pytorch/blob/HEAD/dalle_pytorch/dalle_pytorch.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":"fe5dd5258046898c"}},{"code_sha256_prefix":"7ae941c6130274cb","entry":"cp_path_to_dir","repo":"jam-ing/DALLE-pytorch","repo_kind":"listed","path":"train_dalle.py","file_url":"https://github.com/jam-ing/DALLE-pytorch/blob/HEAD/train_dalle.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":"7ae941c6130274cb"}},{"code_sha256_prefix":"60fff7c3c400d7ff","entry":"default","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"60fff7c3c400d7ff"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"863c2d358b6285ad","entry":"get_trainable_params","repo":"jam-ing/DALLE-pytorch","repo_kind":"listed","path":"train_dalle.py","file_url":"https://github.com/jam-ing/DALLE-pytorch/blob/HEAD/train_dalle.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":"863c2d358b6285ad"}},{"code_sha256_prefix":"a91aa4d3b29e189e","entry":"is_empty","repo":"lucidrains/DALLE-pytorch","repo_kind":"listed","path":"dalle_pytorch/dalle_pytorch.py","file_url":"https://github.com/lucidrains/DALLE-pytorch/blob/HEAD/dalle_pytorch/dalle_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a91aa4d3b29e189e"}},{"code_sha256_prefix":"b706edf96c81728a","entry":"train_for_one_epoch","repo":"explainingai-code/Dalle-Pytorch","repo_kind":"listed","path":"tools/train_dalle.py","file_url":"https://github.com/explainingai-code/Dalle-Pytorch/blob/HEAD/tools/train_dalle.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b706edf96c81728a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}