{"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/scaling-rectified-flow-transformers-for-high","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","arxiv_id":"2403.03206","date":"2024-03-05","proceeding":null,"authors":["Patrick Esser","Sumith Kulal","Andreas Blattmann","Rahim Entezari","Jonas Müller","Harry Saini","Yam Levi","Dominik Lorenz","Axel Sauer","Frederic Boesel","Dustin Podell","Tim Dockhorn","Zion English","Kyle Lacey","Alex Goodwin","Yannik Marek","Robin Rombach"],"abstract":"Diffusion models create data from noise by inverting the forward paths of data towards noise and have emerged as a powerful generative modeling technique for high-dimensional, perceptual data such as images and videos. Rectified flow is a recent generative model formulation that connects data and noise in a straight line. Despite its better theoretical properties and conceptual simplicity, it is not yet decisively established as standard practice. In this work, we improve existing noise sampling techniques for training rectified flow models by biasing them towards perceptually relevant scales. Through a large-scale study, we demonstrate the superior performance of this approach compared to established diffusion formulations for high-resolution text-to-image synthesis. Additionally, we present a novel transformer-based architecture for text-to-image generation that uses separate weights for the two modalities and enables a bidirectional flow of information between image and text tokens, improving text comprehension, typography, and human preference ratings. We demonstrate that this architecture follows predictable scaling trends and correlates lower validation loss to improved text-to-image synthesis as measured by various metrics and human evaluations. Our largest models outperform state-of-the-art models, and we will make our experimental data, code, and model weights publicly available.","url_abs":"https://arxiv.org/abs/2403.03206v1","url_pdf":"https://arxiv.org/pdf/2403.03206v1.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":"scaling-rectified-flow-transformers-for-high","repo_url":"https://github.com/Karine-Huang/T2I-CompBench","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"scaling-rectified-flow-transformers-for-high","repo_url":"https://github.com/hxixixh/adaflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"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"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/on-wise","task":"","dataset":"WISE","model":"SD3.5-large","rank_in_archive_order":6,"of":11,"metrics":{"Biology":"0.44","Chemistry":"0.31","Cultural":"0.44","Overall":"0.46","Physics":"0.56","Space":"0.58","Time":"0.50"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-wise","task":"Image Generation","dataset":"WISE","model":"stable-diffusion-3.5-large","rank_in_archive_order":8,"of":14,"metrics":{"Biology":"0.44","Chemistry":"0.31","Cultural":"0.44","Overall":"0.46","Physics":"0.52","Space":"0.58","Time":"0.50"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2403.03206","atlas_url":"https://app.syntology.ai/?focus=2403.03206","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03206"}},"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/Karine-Huang/T2I-CompBench","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hxixixh/adaflow","reach":{"status":"ok"}}],"summary":{"ran":10,"unverified":1},"by_repo_kind":{"listed":{"samples":11,"ran":10,"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":11,"samples":[{"code_sha256_prefix":"3da7e2c1f60ed411","entry":"align_timestamps","repo":"hxixixh/adaflow","repo_kind":"listed","path":"adaflow/common/timestamp_accumulator.py","file_url":"https://github.com/hxixixh/adaflow/blob/HEAD/adaflow/common/timestamp_accumulator.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":"3da7e2c1f60ed411"}},{"code_sha256_prefix":"a8760aa62907510c","entry":"create_indices","repo":"hxixixh/adaflow","repo_kind":"listed","path":"adaflow/common/sampler.py","file_url":"https://github.com/hxixixh/adaflow/blob/HEAD/adaflow/common/sampler.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":"a8760aa62907510c"}},{"code_sha256_prefix":"e889bd81b4735ee5","entry":"dict_apply","repo":"hxixixh/adaflow","repo_kind":"listed","path":"adaflow/common/pytorch_util.py","file_url":"https://github.com/hxixixh/adaflow/blob/HEAD/adaflow/common/pytorch_util.py","link_basis":"harvester_set","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":"e889bd81b4735ee5"}},{"code_sha256_prefix":"8c6a9f390c7af799","entry":"dict_apply_split","repo":"hxixixh/adaflow","repo_kind":"listed","path":"adaflow/common/pytorch_util.py","file_url":"https://github.com/hxixixh/adaflow/blob/HEAD/adaflow/common/pytorch_util.py","link_basis":"harvester_set","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":"8c6a9f390c7af799"}},{"code_sha256_prefix":"85ef80fba2caa71d","entry":"downsample_mask","repo":"hxixixh/adaflow","repo_kind":"listed","path":"adaflow/common/sampler.py","file_url":"https://github.com/hxixixh/adaflow/blob/HEAD/adaflow/common/sampler.py","link_basis":"harvester_set","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":"85ef80fba2caa71d"}},{"code_sha256_prefix":"0b8592a8f5963d97","entry":"get_accumulate_timestamp_idxs","repo":"hxixixh/adaflow","repo_kind":"listed","path":"adaflow/common/timestamp_accumulator.py","file_url":"https://github.com/hxixixh/adaflow/blob/HEAD/adaflow/common/timestamp_accumulator.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":"0b8592a8f5963d97"}},{"code_sha256_prefix":"1d4ddad52e215d73","entry":"get_optimal_chunks","repo":"hxixixh/adaflow","repo_kind":"listed","path":"adaflow/common/replay_buffer.py","file_url":"https://github.com/hxixixh/adaflow/blob/HEAD/adaflow/common/replay_buffer.py","link_basis":"harvester_set","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":"1d4ddad52e215d73"}},{"code_sha256_prefix":"ed689847c85c1288","entry":"get_val_mask","repo":"hxixixh/adaflow","repo_kind":"listed","path":"adaflow/common/sampler.py","file_url":"https://github.com/hxixixh/adaflow/blob/HEAD/adaflow/common/sampler.py","link_basis":"harvester_set","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":"ed689847c85c1288"}},{"code_sha256_prefix":"ad05722d0bd12d1e","entry":"pad_remaining_dims","repo":"hxixixh/adaflow","repo_kind":"listed","path":"adaflow/common/pytorch_util.py","file_url":"https://github.com/hxixixh/adaflow/blob/HEAD/adaflow/common/pytorch_util.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":"ad05722d0bd12d1e"}},{"code_sha256_prefix":"116acbede4989d1c","entry":"protective_squeeze","repo":"hxixixh/adaflow","repo_kind":"listed","path":"adaflow/codecs/imagecodecs_numcodecs.py","file_url":"https://github.com/hxixixh/adaflow/blob/HEAD/adaflow/codecs/imagecodecs_numcodecs.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":"116acbede4989d1c"}},{"code_sha256_prefix":"d83f4930e9aa9202","entry":"read_json_log","repo":"hxixixh/adaflow","repo_kind":"listed","path":"adaflow/common/json_logger.py","file_url":"https://github.com/hxixixh/adaflow/blob/HEAD/adaflow/common/json_logger.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":"d83f4930e9aa9202"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}