{"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/reno-enhancing-one-step-text-to-image-models","title":"ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization","arxiv_id":"2406.04312","date":"2024-06-06","proceeding":null,"authors":["Luca Eyring","Shyamgopal Karthik","Karsten Roth","Alexey Dosovitskiy","Zeynep Akata"],"abstract":"Text-to-Image (T2I) models have made significant advancements in recent years, but they still struggle to accurately capture intricate details specified in complex compositional prompts. While fine-tuning T2I models with reward objectives has shown promise, it suffers from \"reward hacking\" and may not generalize well to unseen prompt distributions. In this work, we propose Reward-based Noise Optimization (ReNO), a novel approach that enhances T2I models at inference by optimizing the initial noise based on the signal from one or multiple human preference reward models. Remarkably, solving this optimization problem with gradient ascent for 50 iterations yields impressive results on four different one-step models across two competitive benchmarks, T2I-CompBench and GenEval. Within a computational budget of 20-50 seconds, ReNO-enhanced one-step models consistently surpass the performance of all current open-source Text-to-Image models. Extensive user studies demonstrate that our model is preferred nearly twice as often compared to the popular SDXL model and is on par with the proprietary Stable Diffusion 3 with 8B parameters. Moreover, given the same computational resources, a ReNO-optimized one-step model outperforms widely-used open-source models such as SDXL and PixArt-$\\alpha$, highlighting the efficiency and effectiveness of ReNO in enhancing T2I model performance at inference time. Code is available at https://github.com/ExplainableML/ReNO.","url_abs":"https://arxiv.org/abs/2406.04312v2","url_pdf":"https://arxiv.org/pdf/2406.04312v2.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":"reno-enhancing-one-step-text-to-image-models","repo_url":"https://github.com/explainableml/reno","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.04312","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04312"}},"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":"deterministic:regex_extraction","url":"https://github.com/salesforce/DOODL","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/ExplainableML/ReNO","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/explainableml/reno","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":7,"ran_violates":1,"ran_draft_wrong":2,"unverified":12},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1},"found_in_text":{"samples":19,"ran":7,"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":"4b9a1f20af5b88a2","entry":"attention_drop","repo":"salesforce/DOODL","repo_kind":"found_in_text","path":"fgvc_ws_dan_helpers/attention.py","file_url":"https://github.com/salesforce/DOODL/blob/HEAD/fgvc_ws_dan_helpers/attention.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4b9a1f20af5b88a2"}},{"code_sha256_prefix":"06864fef7f15d70b","entry":"batch_norm","repo":"salesforce/DOODL","repo_kind":"found_in_text","path":"memcnn/models/resnet.py","file_url":"https://github.com/salesforce/DOODL/blob/HEAD/memcnn/models/resnet.py","link_basis":"first_harvest_node","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":"06864fef7f15d70b"}},{"code_sha256_prefix":"4e3ad3679e5c37b2","entry":"calculate_shift","repo":"ExplainableML/ReNO","repo_kind":"official","path":"models/RewardFlux.py","file_url":"https://github.com/ExplainableML/ReNO/blob/HEAD/models/RewardFlux.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4e3ad3679e5c37b2"}},{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"salesforce/DOODL","repo_kind":"found_in_text","path":"memcnn/models/resnet.py","file_url":"https://github.com/salesforce/DOODL/blob/HEAD/memcnn/models/resnet.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"1e2c27972c98db0d","entry":"get_alpha_and_beta","repo":"salesforce/DOODL","repo_kind":"found_in_text","path":"helper_functions.py","file_url":"https://github.com/salesforce/DOODL/blob/HEAD/helper_functions.py","link_basis":"first_harvest_node","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":"1e2c27972c98db0d"}},{"code_sha256_prefix":"eafa252fd6f86857","entry":"get_parameter_device","repo":"salesforce/DOODL","repo_kind":"found_in_text","path":"my_half_diffusers/modeling_utils.py","file_url":"https://github.com/salesforce/DOODL/blob/HEAD/my_half_diffusers/modeling_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":"eafa252fd6f86857"}},{"code_sha256_prefix":"dc2045840ce679cb","entry":"get_parameter_dtype","repo":"salesforce/DOODL","repo_kind":"found_in_text","path":"my_half_diffusers/modeling_utils.py","file_url":"https://github.com/salesforce/DOODL/blob/HEAD/my_half_diffusers/modeling_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":"dc2045840ce679cb"}},{"code_sha256_prefix":"0b56680ee1708fee","entry":"retrieve_timesteps","repo":"ExplainableML/ReNO","repo_kind":"official","path":"models/RewardFlux.py","file_url":"https://github.com/ExplainableML/ReNO/blob/HEAD/models/RewardFlux.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":"0b56680ee1708fee"}},{"code_sha256_prefix":"6c337532224391b0","entry":"retrieve_timesteps","repo":"ExplainableML/ReNO","repo_kind":"official","path":"models/RewardStableDiffusion.py","file_url":"https://github.com/ExplainableML/ReNO/blob/HEAD/models/RewardStableDiffusion.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":"6c337532224391b0"}},{"code_sha256_prefix":"6fa6035b98a8620c","entry":"symmetry_loss_fn","repo":"salesforce/DOODL","repo_kind":"found_in_text","path":"doodl.py","file_url":"https://github.com/salesforce/DOODL/blob/HEAD/doodl.py","link_basis":"first_harvest_node","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":"6fa6035b98a8620c"}},{"code_sha256_prefix":"f4b39efe5d9d4cd6","entry":"attention_crop","repo":"salesforce/DOODL","repo_kind":"found_in_text","path":"fgvc_ws_dan_helpers/attention.py","file_url":"https://github.com/salesforce/DOODL/blob/HEAD/fgvc_ws_dan_helpers/attention.py","link_basis":"first_harvest_node","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":"f4b39efe5d9d4cd6"}},{"code_sha256_prefix":"90d39f0e29e120ed","entry":"attention_crop_drop","repo":"salesforce/DOODL","repo_kind":"found_in_text","path":"fgvc_ws_dan_helpers/attention.py","file_url":"https://github.com/salesforce/DOODL/blob/HEAD/fgvc_ws_dan_helpers/attention.py","link_basis":"first_harvest_node","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":"90d39f0e29e120ed"}},{"code_sha256_prefix":"301682fc3342590a","entry":"check_imports","repo":"salesforce/DOODL","repo_kind":"found_in_text","path":"my_half_diffusers/dynamic_modules_utils.py","file_url":"https://github.com/salesforce/DOODL/blob/HEAD/my_half_diffusers/dynamic_modules_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":"301682fc3342590a"}},{"code_sha256_prefix":"98d441978db01287","entry":"clip_loss_fn","repo":"salesforce/DOODL","repo_kind":"found_in_text","path":"doodl.py","file_url":"https://github.com/salesforce/DOODL/blob/HEAD/doodl.py","link_basis":"first_harvest_node","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":"98d441978db01287"}},{"code_sha256_prefix":"2b1d2002a86e6988","entry":"forward_step","repo":"salesforce/DOODL","repo_kind":"found_in_text","path":"helper_functions.py","file_url":"https://github.com/salesforce/DOODL/blob/HEAD/helper_functions.py","link_basis":"first_harvest_node","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":"2b1d2002a86e6988"}},{"code_sha256_prefix":"00cc853a73f3aeb6","entry":"get_relative_import_files","repo":"salesforce/DOODL","repo_kind":"found_in_text","path":"my_half_diffusers/dynamic_modules_utils.py","file_url":"https://github.com/salesforce/DOODL/blob/HEAD/my_half_diffusers/dynamic_modules_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":"00cc853a73f3aeb6"}},{"code_sha256_prefix":"450aeffe7f80f917","entry":"get_relative_imports","repo":"salesforce/DOODL","repo_kind":"found_in_text","path":"my_half_diffusers/dynamic_modules_utils.py","file_url":"https://github.com/salesforce/DOODL/blob/HEAD/my_half_diffusers/dynamic_modules_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":"450aeffe7f80f917"}},{"code_sha256_prefix":"281fab24f1d00b4d","entry":"inception_v3","repo":"salesforce/DOODL","repo_kind":"found_in_text","path":"fgvc_ws_dan_helpers/inception_bap.py","file_url":"https://github.com/salesforce/DOODL/blob/HEAD/fgvc_ws_dan_helpers/inception_bap.py","link_basis":"first_harvest_node","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":"281fab24f1d00b4d"}},{"code_sha256_prefix":"0be62823f1d5be59","entry":"inception_v3_bap","repo":"salesforce/DOODL","repo_kind":"found_in_text","path":"fgvc_ws_dan_helpers/inception_bap.py","file_url":"https://github.com/salesforce/DOODL/blob/HEAD/fgvc_ws_dan_helpers/inception_bap.py","link_basis":"first_harvest_node","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":"0be62823f1d5be59"}},{"code_sha256_prefix":"77bd5e6e8ca8c91d","entry":"load_state_dict","repo":"salesforce/DOODL","repo_kind":"found_in_text","path":"my_half_diffusers/modeling_utils.py","file_url":"https://github.com/salesforce/DOODL/blob/HEAD/my_half_diffusers/modeling_utils.py","link_basis":"first_harvest_node","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":"77bd5e6e8ca8c91d"}},{"code_sha256_prefix":"6dfd0473df9ccaa5","entry":"reverse_step","repo":"salesforce/DOODL","repo_kind":"found_in_text","path":"helper_functions.py","file_url":"https://github.com/salesforce/DOODL/blob/HEAD/helper_functions.py","link_basis":"first_harvest_node","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":"6dfd0473df9ccaa5"}},{"code_sha256_prefix":"216e276b9fb00d10","entry":"spherical_dist_loss","repo":"salesforce/DOODL","repo_kind":"found_in_text","path":"doodl.py","file_url":"https://github.com/salesforce/DOODL/blob/HEAD/doodl.py","link_basis":"first_harvest_node","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":"216e276b9fb00d10"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}