{"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/generating-illustrated-instructions","title":"Generating Illustrated Instructions","arxiv_id":"2312.04552","date":"2023-12-07","proceeding":"CVPR 2024 1","authors":["Sachit Menon","Ishan Misra","Rohit Girdhar"],"abstract":"We introduce the new task of generating Illustrated Instructions, i.e., visual instructions customized to a user's needs. We identify desiderata unique to this task, and formalize it through a suite of automatic and human evaluation metrics, designed to measure the validity, consistency, and efficacy of the generations. We combine the power of large language models (LLMs) together with strong text-to-image generation diffusion models to propose a simple approach called StackedDiffusion, which generates such illustrated instructions given text as input. The resulting model strongly outperforms baseline approaches and state-of-the-art multimodal LLMs; and in 30% of cases, users even prefer it to human-generated articles. Most notably, it enables various new and exciting applications far beyond what static articles on the web can provide, such as personalized instructions complete with intermediate steps and pictures in response to a user's individual situation.","url_abs":"https://arxiv.org/abs/2312.04552v2","url_pdf":"https://arxiv.org/pdf/2312.04552v2.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":"generating-illustrated-instructions","repo_url":"https://github.com/sachit-menon/generating-illustrated-instructions-reproduction","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"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"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2312.04552","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04552"}},"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/sachit-menon/generating-illustrated-instructions-reproduction","reach":{"status":"ok"}}],"summary":{"ran":4,"ran_honours":1,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"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":7,"samples":[{"code_sha256_prefix":"694ad5c8799b9dea","entry":"convert_to_np","repo":"sachit-menon/generating-illustrated-instructions-reproduction","repo_kind":"official","path":"helpers.py","file_url":"https://github.com/sachit-menon/generating-illustrated-instructions-reproduction/blob/HEAD/helpers.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"694ad5c8799b9dea"}},{"code_sha256_prefix":"191a0905a11888a1","entry":"denormalize","repo":"sachit-menon/generating-illustrated-instructions-reproduction","repo_kind":"official","path":"utils.py","file_url":"https://github.com/sachit-menon/generating-illustrated-instructions-reproduction/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"191a0905a11888a1"}},{"code_sha256_prefix":"f4b47e5a1889aa50","entry":"extract_argparse_info","repo":"sachit-menon/generating-illustrated-instructions-reproduction","repo_kind":"official","path":"utils.py","file_url":"https://github.com/sachit-menon/generating-illustrated-instructions-reproduction/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f4b47e5a1889aa50"}},{"code_sha256_prefix":"7ab037059d015859","entry":"extracted_info_to_hydra_config","repo":"sachit-menon/generating-illustrated-instructions-reproduction","repo_kind":"official","path":"utils.py","file_url":"https://github.com/sachit-menon/generating-illustrated-instructions-reproduction/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7ab037059d015859"}},{"code_sha256_prefix":"33805df68cb6892e","entry":"get_emb","repo":"sachit-menon/generating-illustrated-instructions-reproduction","repo_kind":"official","path":"layers.py","file_url":"https://github.com/sachit-menon/generating-illustrated-instructions-reproduction/blob/HEAD/layers.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"33805df68cb6892e"}},{"code_sha256_prefix":"1eeddaf11b50286c","entry":"create_diagram","repo":"sachit-menon/generating-illustrated-instructions-reproduction","repo_kind":"official","path":"helpers.py","file_url":"https://github.com/sachit-menon/generating-illustrated-instructions-reproduction/blob/HEAD/helpers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1eeddaf11b50286c"}},{"code_sha256_prefix":"d5288b587cd15fcf","entry":"download_image","repo":"sachit-menon/generating-illustrated-instructions-reproduction","repo_kind":"official","path":"helpers.py","file_url":"https://github.com/sachit-menon/generating-illustrated-instructions-reproduction/blob/HEAD/helpers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d5288b587cd15fcf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}