{"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/unified-diffusion-based-rigid-and-non-rigid","title":"Unified Diffusion-Based Rigid and Non-Rigid Editing with Text and Image Guidance","arxiv_id":"2401.02126","date":"2024-01-04","proceeding":null,"authors":["Jiacheng Wang","Ping Liu","Wei Xu"],"abstract":"Existing text-to-image editing methods tend to excel either in rigid or non-rigid editing but encounter challenges when combining both, resulting in misaligned outputs with the provided text prompts. In addition, integrating reference images for control remains challenging. To address these issues, we present a versatile image editing framework capable of executing both rigid and non-rigid edits, guided by either textual prompts or reference images. We leverage a dual-path injection scheme to handle diverse editing scenarios and introduce an integrated self-attention mechanism for fusion of appearance and structural information. To mitigate potential visual artifacts, we further employ latent fusion techniques to adjust intermediate latents. Compared to previous work, our approach represents a significant advance in achieving precise and versatile image editing. Comprehensive experiments validate the efficacy of our method, showcasing competitive or superior results in text-based editing and appearance transfer tasks, encompassing both rigid and non-rigid settings.","url_abs":"https://arxiv.org/abs/2401.02126v1","url_pdf":"https://arxiv.org/pdf/2401.02126v1.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":"unified-diffusion-based-rigid-and-non-rigid","repo_url":"https://github.com/kihensarn/ti-guided-edit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"appearance-transfer","task_name":"Appearance Transfer"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2401.02126","atlas_url":"https://app.syntology.ai/?focus=2401.02126","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.02126"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/kihensarn/ti-guided-edit","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":4},"by_repo_kind":{"official":{"samples":5,"ran":1,"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":"cb4f657896b3cfe3","entry":"masked_adain","repo":"kihensarn/ti-guided-edit","repo_kind":"official","path":"utils/adain.py","file_url":"https://github.com/kihensarn/ti-guided-edit/blob/HEAD/utils/adain.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cb4f657896b3cfe3"}},{"code_sha256_prefix":"7ee9dfbb0bd00480","entry":"calc_mean_std","repo":"kihensarn/ti-guided-edit","repo_kind":"official","path":"utils/adain.py","file_url":"https://github.com/kihensarn/ti-guided-edit/blob/HEAD/utils/adain.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":"7ee9dfbb0bd00480"}},{"code_sha256_prefix":"dcbb6d9b7d233a4e","entry":"calc_mean_std_2d","repo":"kihensarn/ti-guided-edit","repo_kind":"official","path":"utils/adain.py","file_url":"https://github.com/kihensarn/ti-guided-edit/blob/HEAD/utils/adain.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":"dcbb6d9b7d233a4e"}},{"code_sha256_prefix":"e97c3effd6355f80","entry":"register_conv_control_efficient","repo":"kihensarn/ti-guided-edit","repo_kind":"official","path":"utils/masactrl_utils.py","file_url":"https://github.com/kihensarn/ti-guided-edit/blob/HEAD/utils/masactrl_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":"e97c3effd6355f80"}},{"code_sha256_prefix":"827413ab1b8cdef0","entry":"regiter_attention_editor_diffusers","repo":"kihensarn/ti-guided-edit","repo_kind":"official","path":"utils/masactrl_utils.py","file_url":"https://github.com/kihensarn/ti-guided-edit/blob/HEAD/utils/masactrl_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":"827413ab1b8cdef0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}