{"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/controlvar-exploring-controllable-visual","title":"ControlVAR: Exploring Controllable Visual Autoregressive Modeling","arxiv_id":"2406.09750","date":"2024-06-14","proceeding":null,"authors":["Xiang Li","Kai Qiu","Hao Chen","Jason Kuen","Zhe Lin","Rita Singh","Bhiksha Raj"],"abstract":"Conditional visual generation has witnessed remarkable progress with the advent of diffusion models (DMs), especially in tasks like control-to-image generation. However, challenges such as expensive computational cost, high inference latency, and difficulties of integration with large language models (LLMs) have necessitated exploring alternatives to DMs. This paper introduces ControlVAR, a novel framework that explores pixel-level controls in visual autoregressive (VAR) modeling for flexible and efficient conditional generation. In contrast to traditional conditional models that learn the conditional distribution, ControlVAR jointly models the distribution of image and pixel-level conditions during training and imposes conditional controls during testing. To enhance the joint modeling, we adopt the next-scale AR prediction paradigm and unify control and image representations. A teacher-forcing guidance strategy is proposed to further facilitate controllable generation with joint modeling. Extensive experiments demonstrate the superior efficacy and flexibility of ControlVAR across various conditional generation tasks against popular conditional DMs, \\eg, ControlNet and T2I-Adaptor. Code: \\url{https://github.com/lxa9867/ControlVAR}.","url_abs":"https://arxiv.org/abs/2406.09750v2","url_pdf":"https://arxiv.org/pdf/2406.09750v2.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":"controlvar-exploring-controllable-visual","repo_url":"https://github.com/lxa9867/ControlVAR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.09750","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09750"}},"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/lxa9867/ControlVAR","reach":{"status":"ok"}}],"summary":{"ran_honours":1,"ran":6,"ran_draft_wrong":4,"unverified":3},"by_repo_kind":{"official":{"samples":14,"ran":11,"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":14,"samples":[{"code_sha256_prefix":"7439a9d4c6be04b0","entry":"adopt_weight","repo":"lxa9867/ControlVAR","repo_kind":"official","path":"losses/vqperceptual.py","file_url":"https://github.com/lxa9867/ControlVAR/blob/HEAD/losses/vqperceptual.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7439a9d4c6be04b0"}},{"code_sha256_prefix":"42d03794aad024c8","entry":"dice_coefficient","repo":"lxa9867/ControlVAR","repo_kind":"official","path":"losses/dice.py","file_url":"https://github.com/lxa9867/ControlVAR/blob/HEAD/losses/dice.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"42d03794aad024c8"}},{"code_sha256_prefix":"462717b2dbf64e04","entry":"dice_loss","repo":"lxa9867/ControlVAR","repo_kind":"official","path":"losses/dice.py","file_url":"https://github.com/lxa9867/ControlVAR/blob/HEAD/losses/dice.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"462717b2dbf64e04"}},{"code_sha256_prefix":"65d02fdb37906970","entry":"find_classes","repo":"lxa9867/ControlVAR","repo_kind":"official","path":"datasets/imagenetC.py","file_url":"https://github.com/lxa9867/ControlVAR/blob/HEAD/datasets/imagenetC.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"65d02fdb37906970"}},{"code_sha256_prefix":"e70eb36cf08faee4","entry":"get_ckpt_path","repo":"lxa9867/ControlVAR","repo_kind":"official","path":"losses/util.py","file_url":"https://github.com/lxa9867/ControlVAR/blob/HEAD/losses/util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e70eb36cf08faee4"}},{"code_sha256_prefix":"22a83df891d750c6","entry":"hinge_d_loss","repo":"lxa9867/ControlVAR","repo_kind":"official","path":"losses/vqperceptual.py","file_url":"https://github.com/lxa9867/ControlVAR/blob/HEAD/losses/vqperceptual.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"22a83df891d750c6"}},{"code_sha256_prefix":"07d90bd6ae1be7db","entry":"md5_hash","repo":"lxa9867/ControlVAR","repo_kind":"official","path":"losses/util.py","file_url":"https://github.com/lxa9867/ControlVAR/blob/HEAD/losses/util.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"07d90bd6ae1be7db"}},{"code_sha256_prefix":"7257fdf155f5ef45","entry":"normalize_tensor","repo":"lxa9867/ControlVAR","repo_kind":"official","path":"losses/lpips.py","file_url":"https://github.com/lxa9867/ControlVAR/blob/HEAD/losses/lpips.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7257fdf155f5ef45"}},{"code_sha256_prefix":"31543f3e2c18272e","entry":"retrieve","repo":"lxa9867/ControlVAR","repo_kind":"official","path":"losses/util.py","file_url":"https://github.com/lxa9867/ControlVAR/blob/HEAD/losses/util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"31543f3e2c18272e"}},{"code_sha256_prefix":"e268053216b1dd62","entry":"spatial_average","repo":"lxa9867/ControlVAR","repo_kind":"official","path":"losses/lpips.py","file_url":"https://github.com/lxa9867/ControlVAR/blob/HEAD/losses/lpips.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e268053216b1dd62"}},{"code_sha256_prefix":"263c54290c553ddd","entry":"vanilla_d_loss","repo":"lxa9867/ControlVAR","repo_kind":"official","path":"losses/vqperceptual.py","file_url":"https://github.com/lxa9867/ControlVAR/blob/HEAD/losses/vqperceptual.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"263c54290c553ddd"}},{"code_sha256_prefix":"e847ee15f089dee6","entry":"allgather","repo":"lxa9867/ControlVAR","repo_kind":"official","path":"dist.py","file_url":"https://github.com/lxa9867/ControlVAR/blob/HEAD/dist.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e847ee15f089dee6"}},{"code_sha256_prefix":"ff4c548fd07140d0","entry":"allreduce","repo":"lxa9867/ControlVAR","repo_kind":"official","path":"dist.py","file_url":"https://github.com/lxa9867/ControlVAR/blob/HEAD/dist.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ff4c548fd07140d0"}},{"code_sha256_prefix":"826ea3fc406a6a09","entry":"new_group","repo":"lxa9867/ControlVAR","repo_kind":"official","path":"dist.py","file_url":"https://github.com/lxa9867/ControlVAR/blob/HEAD/dist.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"826ea3fc406a6a09"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}