{"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/omnigen-unified-image-generation","title":"OmniGen: Unified Image Generation","arxiv_id":"2409.11340","date":"2024-09-17","proceeding":"CVPR 2025 1","authors":["Shitao Xiao","Yueze Wang","Junjie Zhou","Huaying Yuan","Xingrun Xing","Ruiran Yan","Chaofan Li","Shuting Wang","Tiejun Huang","Zheng Liu"],"abstract":"The emergence of Large Language Models (LLMs) has unified language generation tasks and revolutionized human-machine interaction. However, in the realm of image generation, a unified model capable of handling various tasks within a single framework remains largely unexplored. In this work, we introduce OmniGen, a new diffusion model for unified image generation. OmniGen is characterized by the following features: 1) Unification: OmniGen not only demonstrates text-to-image generation capabilities but also inherently supports various downstream tasks, such as image editing, subject-driven generation, and visual-conditional generation. 2) Simplicity: The architecture of OmniGen is highly simplified, eliminating the need for additional plugins. Moreover, compared to existing diffusion models, it is more user-friendly and can complete complex tasks end-to-end through instructions without the need for extra intermediate steps, greatly simplifying the image generation workflow. 3) Knowledge Transfer: Benefit from learning in a unified format, OmniGen effectively transfers knowledge across different tasks, manages unseen tasks and domains, and exhibits novel capabilities. We also explore the model's reasoning capabilities and potential applications of the chain-of-thought mechanism. This work represents the first attempt at a general-purpose image generation model, and we will release our resources at https://github.com/VectorSpaceLab/OmniGen to foster future advancements.","url_abs":"https://arxiv.org/abs/2409.11340v2","url_pdf":"https://arxiv.org/pdf/2409.11340v2.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":"omnigen-unified-image-generation","repo_url":"https://github.com/vectorspacelab/omnigen","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"edge-detection","task_name":"Edge Detection"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"text-generation","task_name":"Text 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"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2409.11340","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.11340"}},"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/vectorspacelab/omnigen","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"ran":5,"unverified":1},"by_repo_kind":{"official":{"samples":9,"ran":8,"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":"ea73360d2d5d9224","entry":"center_crop_arr","repo":"vectorspacelab/omnigen","repo_kind":"official","path":"OmniGen/utils.py","file_url":"https://github.com/vectorspacelab/omnigen/blob/HEAD/OmniGen/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ea73360d2d5d9224"}},{"code_sha256_prefix":"b2cc78f4103df806","entry":"create_logger","repo":"vectorspacelab/omnigen","repo_kind":"official","path":"OmniGen/utils.py","file_url":"https://github.com/vectorspacelab/omnigen/blob/HEAD/OmniGen/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b2cc78f4103df806"}},{"code_sha256_prefix":"0deb02748179c848","entry":"crop_arr","repo":"vectorspacelab/omnigen","repo_kind":"official","path":"OmniGen/utils.py","file_url":"https://github.com/vectorspacelab/omnigen/blob/HEAD/OmniGen/utils.py","link_basis":"first_harvest_node","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":"0deb02748179c848"}},{"code_sha256_prefix":"b9da3bec8fc652d6","entry":"get_2d_sincos_pos_embed","repo":"vectorspacelab/omnigen","repo_kind":"official","path":"OmniGen/model.py","file_url":"https://github.com/vectorspacelab/omnigen/blob/HEAD/OmniGen/model.py","link_basis":"first_harvest_node","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":"b9da3bec8fc652d6"}},{"code_sha256_prefix":"03310bba324ae4fb","entry":"modulate","repo":"vectorspacelab/omnigen","repo_kind":"official","path":"OmniGen/model.py","file_url":"https://github.com/vectorspacelab/omnigen/blob/HEAD/OmniGen/model.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"03310bba324ae4fb"}},{"code_sha256_prefix":"960d3e8d782a3a71","entry":"sample_timestep","repo":"vectorspacelab/omnigen","repo_kind":"official","path":"OmniGen/train_helper/loss.py","file_url":"https://github.com/vectorspacelab/omnigen/blob/HEAD/OmniGen/train_helper/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"960d3e8d782a3a71"}},{"code_sha256_prefix":"3aee916a58a0f3c2","entry":"sample_x0","repo":"vectorspacelab/omnigen","repo_kind":"official","path":"OmniGen/train_helper/loss.py","file_url":"https://github.com/vectorspacelab/omnigen/blob/HEAD/OmniGen/train_helper/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3aee916a58a0f3c2"}},{"code_sha256_prefix":"bc251f0fab494c0d","entry":"training_losses","repo":"vectorspacelab/omnigen","repo_kind":"official","path":"OmniGen/train_helper/loss.py","file_url":"https://github.com/vectorspacelab/omnigen/blob/HEAD/OmniGen/train_helper/loss.py","link_basis":"first_harvest_node","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":"bc251f0fab494c0d"}},{"code_sha256_prefix":"665d8a4e8f673a4c","entry":"get_2d_sincos_pos_embed_from_grid","repo":"vectorspacelab/omnigen","repo_kind":"official","path":"OmniGen/model.py","file_url":"https://github.com/vectorspacelab/omnigen/blob/HEAD/OmniGen/model.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":"665d8a4e8f673a4c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}