{"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/mige-a-unified-framework-for-multimodal","title":"MIGE: A Unified Framework for Multimodal Instruction-Based Image Generation and Editing","arxiv_id":"2502.21291","date":"2025-02-28","proceeding":null,"authors":["Xueyun Tian","Wei Li","Bingbing Xu","Yige Yuan","Yuanzhuo Wang","HuaWei Shen"],"abstract":"Despite significant progress in diffusion-based image generation, subject-driven generation and instruction-based editing remain challenging. Existing methods typically treat them separately, struggling with limited high-quality data and poor generalization. However, both tasks require capturing complex visual variations while maintaining consistency between inputs and outputs. Therefore, we propose MIGE, a unified framework that standardizes task representations using multimodal instructions. It treats subject-driven generation as creation on a blank canvas and instruction-based editing as modification of an existing image, establishing a shared input-output formulation. MIGE introduces a novel multimodal encoder that maps free-form multimodal instructions into a unified vision-language space, integrating visual and semantic features through a feature fusion mechanism. This unification enables joint training of both tasks, providing two key advantages: (1) Cross-Task Enhancement: By leveraging shared visual and semantic representations, joint training improves instruction adherence and visual consistency in both subject-driven generation and instruction-based editing. (2) Generalization: Learning in a unified format facilitates cross-task knowledge transfer, enabling MIGE to generalize to novel compositional tasks, including instruction-based subject-driven editing. Experiments show that MIGE excels in both subject-driven generation and instruction-based editing while setting a state-of-the-art in the new task of instruction-based subject-driven editing. Code and model have been publicly available at https://github.com/Eureka-Maggie/MIGE.","url_abs":"https://arxiv.org/abs/2502.21291v2","url_pdf":"https://arxiv.org/pdf/2502.21291v2.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":"mige-a-unified-framework-for-multimodal","repo_url":"https://github.com/eureka-maggie/mige","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.21291","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.21291"}},"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/eureka-maggie/mige","reach":null}],"summary":{"ran_violates":1,"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"5ee56a4cbe4e7318","entry":"compute_cosine_distance","repo":"eureka-maggie/mige","repo_kind":"official","path":"infer_scripts/edit.py","file_url":"https://github.com/eureka-maggie/mige/blob/HEAD/infer_scripts/edit.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"5ee56a4cbe4e7318"}},{"code_sha256_prefix":"dffe7ac3c59d89ee","entry":"resize_with_padding","repo":"eureka-maggie/mige","repo_kind":"official","path":"infer_scripts/subject/MIGE_subject_infer.py","file_url":"https://github.com/eureka-maggie/mige/blob/HEAD/infer_scripts/subject/MIGE_subject_infer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"dffe7ac3c59d89ee"}},{"code_sha256_prefix":"aaa4609673d37899","entry":"safe_filename","repo":"eureka-maggie/mige","repo_kind":"official","path":"infer_scripts/subject/MIGE_subject_infer.py","file_url":"https://github.com/eureka-maggie/mige/blob/HEAD/infer_scripts/subject/MIGE_subject_infer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"aaa4609673d37899"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}