{"url":"/task/zero-shot-text-to-image-generation","name":"Zero-Shot Text-to-Image Generation","slug":"zero-shot-text-to-image-generation","description_markdown":"Image credit: [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://paperswithcode.com/paper/glide-towards-photorealistic-image-generation)","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":16,"papers_with_code":11,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[{"url":"/task/text-to-image-generation","name":"Text-to-Image Generation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":11,"of":11,"tagged_in_all":16,"items":[{"url":"/paper/zero-shot-text-to-image-generation","title":"Zero-Shot Text-to-Image Generation","date":"2021-02-24","arxiv_id":"2102.12092","repositories_listed":12,"syntology":{"n":7,"n_ran":7,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/hierarchical-text-conditional-image","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","date":"2022-04-13","arxiv_id":"2204.06125","repositories_listed":8,"syntology":{"n":38,"n_ran":29,"n_unverified":9,"n_pointer_only":1}},{"url":"/paper/cogview-mastering-text-to-image-generation","title":"CogView: Mastering Text-to-Image Generation via Transformers","date":"2021-05-26","arxiv_id":"2105.13290","repositories_listed":4,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/lafite-towards-language-free-training-for","title":"LAFITE: Towards Language-Free Training for Text-to-Image Generation","date":"2021-11-27","arxiv_id":"2111.13792","repositories_listed":3,"syntology":{"n":18,"n_ran":4,"n_unverified":14,"n_pointer_only":0}},{"url":"/paper/glide-towards-photorealistic-image-generation","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","date":"2021-12-20","arxiv_id":"2112.10741","repositories_listed":2,"syntology":{"n":15,"n_ran":9,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/dreamllm-synergistic-multimodal-comprehension","title":"DreamLLM: Synergistic Multimodal Comprehension and Creation","date":"2023-09-20","arxiv_id":"2309.11499","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/shifted-diffusion-for-text-to-image","title":"Shifted Diffusion for Text-to-image Generation","date":"2022-11-24","arxiv_id":"2211.15388","repositories_listed":1,"syntology":{"n":17,"n_ran":7,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/blended-latent-diffusion","title":"Blended Latent Diffusion","date":"2022-06-06","arxiv_id":"2206.02779","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_unverified":4,"n_pointer_only":1}},{"url":"/paper/fusedream-training-free-text-to-image","title":"FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space Optimization","date":"2021-12-02","arxiv_id":"2112.01573","repositories_listed":1,"syntology":null},{"url":"/paper/blended-diffusion-for-text-driven-editing-of","title":"Blended Diffusion for Text-driven Editing of Natural Images","date":"2021-11-29","arxiv_id":"2111.14818","repositories_listed":1,"syntology":{"n":22,"n_ran":14,"n_unverified":8,"n_pointer_only":1}},{"url":"/paper/l-verse-bidirectional-generation-between","title":"L-Verse: Bidirectional Generation Between Image and Text","date":"2021-11-22","arxiv_id":"2111.11133","repositories_listed":1,"syntology":null}],"syntology_records":9,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":1,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}