{"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/omnigen2-exploration-to-advanced-multimodal","title":"OmniGen2: Exploration to Advanced Multimodal Generation","arxiv_id":"2506.18871","date":"2025-06-23","proceeding":null,"authors":["Chenyuan Wu","Pengfei Zheng","Ruiran Yan","Shitao Xiao","Xin Luo","Yueze Wang","Wanli Li","Xiyan Jiang","Yexin Liu","Junjie Zhou","Ze Liu","Ziyi Xia","Chaofan Li","Haoge Deng","Jiahao Wang","Kun Luo","Bo Zhang","Defu Lian","Xinlong Wang","Zhongyuan Wang","Tiejun Huang","Zheng Liu"],"abstract":"In this work, we introduce OmniGen2, a versatile and open-source generative model designed to provide a unified solution for diverse generation tasks, including text-to-image, image editing, and in-context generation. Unlike OmniGen v1, OmniGen2 features two distinct decoding pathways for text and image modalities, utilizing unshared parameters and a decoupled image tokenizer. This design enables OmniGen2 to build upon existing multimodal understanding models without the need to re-adapt VAE inputs, thereby preserving the original text generation capabilities. To facilitate the training of OmniGen2, we developed comprehensive data construction pipelines, encompassing image editing and in-context generation data. Additionally, we introduce a reflection mechanism tailored for image generation tasks and curate a dedicated reflection dataset based on OmniGen2. Despite its relatively modest parameter size, OmniGen2 achieves competitive results on multiple task benchmarks, including text-to-image and image editing. To further evaluate in-context generation, also referred to as subject-driven tasks, we introduce a new benchmark named OmniContext. OmniGen2 achieves state-of-the-art performance among open-source models in terms of consistency. We will release our models, training code, datasets, and data construction pipeline to support future research in this field. Project Page: https://vectorspacelab.github.io/OmniGen2; GitHub Link: https://github.com/VectorSpaceLab/OmniGen2","url_abs":"https://arxiv.org/abs/2506.18871v2","url_pdf":"https://arxiv.org/pdf/2506.18871v2.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":"omnigen2-exploration-to-advanced-multimodal","repo_url":"https://github.com/vectorspacelab/omnigen2","is_official":1,"mentioned_in_paper":1,"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-generation","task_name":"Text Generation"},{"task_slug":"multimodal-generation","task_name":"multimodal generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2506.18871","atlas_url":"https://app.syntology.ai/?focus=2506.18871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.18871"}},"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/vectorspacelab/omnigen2","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1,"unverified":8},"by_repo_kind":{"official":{"samples":9,"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":"60584419d54b85d5","entry":"compute_snr","repo":"vectorspacelab/omnigen2","repo_kind":"official","path":"omnigen2/training_utils.py","file_url":"https://github.com/vectorspacelab/omnigen2/blob/HEAD/omnigen2/training_utils.py","link_basis":"harvester_set","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":"60584419d54b85d5"}},{"code_sha256_prefix":"a6ba03fb70bfe8c6","entry":"apply_chat_template","repo":"vectorspacelab/omnigen2","repo_kind":"official","path":"OmniGen2-RL/reward_server/reward_server.py","file_url":"https://github.com/vectorspacelab/omnigen2/blob/HEAD/OmniGen2-RL/reward_server/reward_server.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":"a6ba03fb70bfe8c6"}},{"code_sha256_prefix":"18b51f2c1d11064b","entry":"apply_rotary_emb","repo":"vectorspacelab/omnigen2","repo_kind":"official","path":"omnigen2/models/embeddings.py","file_url":"https://github.com/vectorspacelab/omnigen2/blob/HEAD/omnigen2/models/embeddings.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":"18b51f2c1d11064b"}},{"code_sha256_prefix":"f8786be3f2b88338","entry":"cache_init","repo":"vectorspacelab/omnigen2","repo_kind":"official","path":"omnigen2/cache_functions/cache_init.py","file_url":"https://github.com/vectorspacelab/omnigen2/blob/HEAD/omnigen2/cache_functions/cache_init.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":"f8786be3f2b88338"}},{"code_sha256_prefix":"20df7e00382b5e77","entry":"decode_base64_image","repo":"vectorspacelab/omnigen2","repo_kind":"official","path":"OmniGen2-RL/reward_server/reward_server.py","file_url":"https://github.com/vectorspacelab/omnigen2/blob/HEAD/OmniGen2-RL/reward_server/reward_server.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":"20df7e00382b5e77"}},{"code_sha256_prefix":"d5acc36a2f75002f","entry":"parse_and_validate_request","repo":"vectorspacelab/omnigen2","repo_kind":"official","path":"OmniGen2-RL/reward_server/reward_server.py","file_url":"https://github.com/vectorspacelab/omnigen2/blob/HEAD/OmniGen2-RL/reward_server/reward_server.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":"d5acc36a2f75002f"}},{"code_sha256_prefix":"103f9506653843ee","entry":"prepare_request_data","repo":"vectorspacelab/omnigen2","repo_kind":"official","path":"OmniGen2-RL/reward_server/reward_proxy.py","file_url":"https://github.com/vectorspacelab/omnigen2/blob/HEAD/OmniGen2-RL/reward_server/reward_proxy.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":"103f9506653843ee"}},{"code_sha256_prefix":"596bed30be61c6e8","entry":"resolve_interpolation_mode","repo":"vectorspacelab/omnigen2","repo_kind":"official","path":"omnigen2/training_utils.py","file_url":"https://github.com/vectorspacelab/omnigen2/blob/HEAD/omnigen2/training_utils.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":"596bed30be61c6e8"}},{"code_sha256_prefix":"20dc3dd57e8a52d6","entry":"start_server","repo":"vectorspacelab/omnigen2","repo_kind":"official","path":"OmniGen2-RL/reward_server/start_multi_servers.py","file_url":"https://github.com/vectorspacelab/omnigen2/blob/HEAD/OmniGen2-RL/reward_server/start_multi_servers.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":"20dc3dd57e8a52d6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}