{"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/elite-encoding-visual-concepts-into-textual","title":"ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation","arxiv_id":"2302.13848","date":"2023-02-27","proceeding":"ICCV 2023 1","authors":["Yuxiang Wei","Yabo Zhang","Zhilong Ji","Jinfeng Bai","Lei Zhang","WangMeng Zuo"],"abstract":"In addition to the unprecedented ability in imaginary creation, large text-to-image models are expected to take customized concepts in image generation. Existing works generally learn such concepts in an optimization-based manner, yet bringing excessive computation or memory burden. In this paper, we instead propose a learning-based encoder, which consists of a global and a local mapping networks for fast and accurate customized text-to-image generation. In specific, the global mapping network projects the hierarchical features of a given image into multiple new words in the textual word embedding space, i.e., one primary word for well-editable concept and other auxiliary words to exclude irrelevant disturbances (e.g., background). In the meantime, a local mapping network injects the encoded patch features into cross attention layers to provide omitted details, without sacrificing the editability of primary concepts. We compare our method with existing optimization-based approaches on a variety of user-defined concepts, and demonstrate that our method enables high-fidelity inversion and more robust editability with a significantly faster encoding process. Our code is publicly available at https://github.com/csyxwei/ELITE.","url_abs":"https://arxiv.org/abs/2302.13848v2","url_pdf":"https://arxiv.org/pdf/2302.13848v2.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":"elite-encoding-visual-concepts-into-textual","repo_url":"https://github.com/csyxwei/elite","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"elite-encoding-visual-concepts-into-textual","repo_url":"https://github.com/lukemelas/realfusion","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"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2302.13848","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13848"}},"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/csyxwei/elite","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lukemelas/realfusion","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/csyxwei/ELITE","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1,"ran_draft_wrong":2,"unverified":4},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":6,"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":"ec19d67d17615772","entry":"Mapper","repo":"csyxwei/ELITE","repo_kind":"official","path":"train_global.py","file_url":"https://github.com/csyxwei/ELITE/blob/HEAD/train_global.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ec19d67d17615772"}},{"code_sha256_prefix":"b90dcdfe160a18ff","entry":"get_view_direction","repo":"lukemelas/realfusion","repo_kind":"listed","path":"nerf/provider_image.py","file_url":"https://github.com/lukemelas/realfusion/blob/HEAD/nerf/provider_image.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b90dcdfe160a18ff"}},{"code_sha256_prefix":"8ed7b9fc7f33d1dd","entry":"sample_pdf","repo":"lukemelas/realfusion","repo_kind":"listed","path":"nerf/renderer.py","file_url":"https://github.com/lukemelas/realfusion/blob/HEAD/nerf/renderer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8ed7b9fc7f33d1dd"}},{"code_sha256_prefix":"560d6afc12b32a5a","entry":"circle_poses","repo":"lukemelas/realfusion","repo_kind":"listed","path":"nerf/provider_image.py","file_url":"https://github.com/lukemelas/realfusion/blob/HEAD/nerf/provider_image.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"560d6afc12b32a5a"}},{"code_sha256_prefix":"0a816b8f3726f079","entry":"get_encoder","repo":"lukemelas/realfusion","repo_kind":"listed","path":"encoding.py","file_url":"https://github.com/lukemelas/realfusion/blob/HEAD/encoding.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0a816b8f3726f079"}},{"code_sha256_prefix":"5c4d5e0b16b2494f","entry":"near_far_from_bound","repo":"lukemelas/realfusion","repo_kind":"listed","path":"nerf/renderer.py","file_url":"https://github.com/lukemelas/realfusion/blob/HEAD/nerf/renderer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5c4d5e0b16b2494f"}},{"code_sha256_prefix":"eff45372d59473d9","entry":"rand_poses","repo":"lukemelas/realfusion","repo_kind":"listed","path":"nerf/provider_image.py","file_url":"https://github.com/lukemelas/realfusion/blob/HEAD/nerf/provider_image.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"eff45372d59473d9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}