{"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/sdxl-improving-latent-diffusion-models-for","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","arxiv_id":"2307.01952","date":"2023-07-04","proceeding":null,"authors":["Dustin Podell","Zion English","Kyle Lacey","Andreas Blattmann","Tim Dockhorn","Jonas Müller","Joe Penna","Robin Rombach"],"abstract":"We present SDXL, a latent diffusion model for text-to-image synthesis. Compared to previous versions of Stable Diffusion, SDXL leverages a three times larger UNet backbone: The increase of model parameters is mainly due to more attention blocks and a larger cross-attention context as SDXL uses a second text encoder. We design multiple novel conditioning schemes and train SDXL on multiple aspect ratios. We also introduce a refinement model which is used to improve the visual fidelity of samples generated by SDXL using a post-hoc image-to-image technique. We demonstrate that SDXL shows drastically improved performance compared the previous versions of Stable Diffusion and achieves results competitive with those of black-box state-of-the-art image generators. In the spirit of promoting open research and fostering transparency in large model training and evaluation, we provide access to code and model weights at https://github.com/Stability-AI/generative-models","url_abs":"https://arxiv.org/abs/2307.01952v1","url_pdf":"https://arxiv.org/pdf/2307.01952v1.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":"sdxl-improving-latent-diffusion-models-for","repo_url":"https://github.com/stability-ai/generative-models","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"sdxl-improving-latent-diffusion-models-for","repo_url":"https://github.com/andrew-miao/RPO","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"sdxl-improving-latent-diffusion-models-for","repo_url":"https://github.com/benearnthof/fm_boosting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"sdxl-improving-latent-diffusion-models-for","repo_url":"https://github.com/bytedance/cascadev","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"AGPL-3.0"}},{"paper_slug":"sdxl-improving-latent-diffusion-models-for","repo_url":"https://github.com/compvis/fm-boosting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"sdxl-improving-latent-diffusion-models-for","repo_url":"https://github.com/tillmannohm/fruit-SALAD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"sdxl-improving-latent-diffusion-models-for","repo_url":"https://github.com/vision-xl/codes","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"sdxl-improving-latent-diffusion-models-for","repo_url":"https://github.com/wellzline/protip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"sdxl-improving-latent-diffusion-models-for","repo_url":"https://github.com/yuchen413/text2image_safety","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"latent-diffusion-model","method_name":"Latent Diffusion Model"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/on-wise","task":"","dataset":"WISE","model":"SDXL","rank_in_archive_order":7,"of":11,"metrics":{"Biology":"0.44","Chemistry":"0.27","Cultural":"0.43","Overall":"0.43","Physics":"0.45","Space":"0.47","Time":"0.48"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-wise","task":"Image Generation","dataset":"WISE","model":"stable-diffusion-xl-base-0.9","rank_in_archive_order":9,"of":14,"metrics":{"Biology":"0.44","Chemistry":"0.27","Cultural":"0.43","Overall":"0.43","Physics":"0.45","Space":"0.47","Time":"0.48"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2307.01952","atlas_url":"https://app.syntology.ai/?focus=2307.01952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.01952"}},"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/andrew-miao/RPO","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/benearnthof/fm_boosting","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tillmannohm/fruit-SALAD","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/compvis/fm-boosting","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bytedance/cascadev","reach":{"status":"ok","spdx":"AGPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yuchen413/text2image_safety","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vision-xl/codes","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wellzline/protip","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/stability-ai/generative-models","reach":null}],"summary":{"ran":11,"unverified":16},"by_repo_kind":{"official":{"samples":14,"ran":4,"repositories":1},"listed":{"samples":13,"ran":7,"repositories":2}},"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":"ad950c2482098461","entry":"AlphaBlender","repo":"stability-ai/generative-models","repo_kind":"official","path":"sgm/modules/diffusionmodules/openaimodel.py","file_url":"https://github.com/stability-ai/generative-models/blob/HEAD/sgm/modules/diffusionmodules/openaimodel.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":"ad950c2482098461"}},{"code_sha256_prefix":"03cbae4dc00dbd28","entry":"Downsample","repo":"compvis/fm-boosting","repo_kind":"listed","path":"fmboost/models/unet/model.py","file_url":"https://github.com/compvis/fm-boosting/blob/HEAD/fmboost/models/unet/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"03cbae4dc00dbd28"}},{"code_sha256_prefix":"3ee1e71fc45df15b","entry":"Downsample","repo":"stability-ai/generative-models","repo_kind":"official","path":"sgm/modules/diffusionmodules/openaimodel.py","file_url":"https://github.com/stability-ai/generative-models/blob/HEAD/sgm/modules/diffusionmodules/openaimodel.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3ee1e71fc45df15b"}},{"code_sha256_prefix":"5dc3f2495524ee28","entry":"LinearQKVAttention","repo":"compvis/fm-boosting","repo_kind":"listed","path":"fmboost/models/unet/model.py","file_url":"https://github.com/compvis/fm-boosting/blob/HEAD/fmboost/models/unet/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5dc3f2495524ee28"}},{"code_sha256_prefix":"7340098015ec809d","entry":"Pool2d","repo":"compvis/fm-boosting","repo_kind":"listed","path":"fmboost/models/unet/model.py","file_url":"https://github.com/compvis/fm-boosting/blob/HEAD/fmboost/models/unet/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7340098015ec809d"}},{"code_sha256_prefix":"0bb33f06a6461c7a","entry":"QKVAttention","repo":"compvis/fm-boosting","repo_kind":"listed","path":"fmboost/models/unet/model.py","file_url":"https://github.com/compvis/fm-boosting/blob/HEAD/fmboost/models/unet/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0bb33f06a6461c7a"}},{"code_sha256_prefix":"48e8939cab1b71e2","entry":"ResBlock","repo":"compvis/fm-boosting","repo_kind":"listed","path":"fmboost/models/unet/model.py","file_url":"https://github.com/compvis/fm-boosting/blob/HEAD/fmboost/models/unet/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":"48e8939cab1b71e2"}},{"code_sha256_prefix":"9eb2201b9e41a2d3","entry":"Timestep","repo":"stability-ai/generative-models","repo_kind":"official","path":"sgm/modules/diffusionmodules/openaimodel.py","file_url":"https://github.com/stability-ai/generative-models/blob/HEAD/sgm/modules/diffusionmodules/openaimodel.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9eb2201b9e41a2d3"}},{"code_sha256_prefix":"8e7f07ae79ee1de0","entry":"UnPool2d","repo":"compvis/fm-boosting","repo_kind":"listed","path":"fmboost/models/unet/model.py","file_url":"https://github.com/compvis/fm-boosting/blob/HEAD/fmboost/models/unet/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8e7f07ae79ee1de0"}},{"code_sha256_prefix":"63b3160a59e80ddb","entry":"Upsample","repo":"compvis/fm-boosting","repo_kind":"listed","path":"fmboost/models/unet/model.py","file_url":"https://github.com/compvis/fm-boosting/blob/HEAD/fmboost/models/unet/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"63b3160a59e80ddb"}},{"code_sha256_prefix":"184b9747aa868755","entry":"Upsample","repo":"stability-ai/generative-models","repo_kind":"official","path":"sgm/modules/diffusionmodules/openaimodel.py","file_url":"https://github.com/stability-ai/generative-models/blob/HEAD/sgm/modules/diffusionmodules/openaimodel.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"184b9747aa868755"}},{"code_sha256_prefix":"40d8ba71b73d29d4","entry":"BasicTransformerBlock","repo":"stability-ai/generative-models","repo_kind":"official","path":"sgm/modules/diffusionmodules/openaimodel.py","file_url":"https://github.com/stability-ai/generative-models/blob/HEAD/sgm/modules/diffusionmodules/openaimodel.py","link_basis":"first_harvest_node","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":"40d8ba71b73d29d4"}},{"code_sha256_prefix":"75e42984360b91c5","entry":"CrossAttention","repo":"stability-ai/generative-models","repo_kind":"official","path":"sgm/modules/diffusionmodules/openaimodel.py","file_url":"https://github.com/stability-ai/generative-models/blob/HEAD/sgm/modules/diffusionmodules/openaimodel.py","link_basis":"first_harvest_node","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":"75e42984360b91c5"}},{"code_sha256_prefix":"173b3ff1d8ad06a9","entry":"EfficientUNet","repo":"compvis/fm-boosting","repo_kind":"listed","path":"fmboost/models/unet/model.py","file_url":"https://github.com/compvis/fm-boosting/blob/HEAD/fmboost/models/unet/model.py","link_basis":"first_harvest_node","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":"173b3ff1d8ad06a9"}},{"code_sha256_prefix":"5cbc6286835eafa2","entry":"MemoryEfficientCrossAttention","repo":"stability-ai/generative-models","repo_kind":"official","path":"sgm/modules/diffusionmodules/openaimodel.py","file_url":"https://github.com/stability-ai/generative-models/blob/HEAD/sgm/modules/diffusionmodules/openaimodel.py","link_basis":"first_harvest_node","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":"5cbc6286835eafa2"}},{"code_sha256_prefix":"77ab8d10090cbbae","entry":"ResBlock","repo":"stability-ai/generative-models","repo_kind":"official","path":"sgm/modules/diffusionmodules/openaimodel.py","file_url":"https://github.com/stability-ai/generative-models/blob/HEAD/sgm/modules/diffusionmodules/openaimodel.py","link_basis":"first_harvest_node","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":"77ab8d10090cbbae"}},{"code_sha256_prefix":"ffc4ff1275bb5b7d","entry":"SpatialSelfAttention","repo":"compvis/fm-boosting","repo_kind":"listed","path":"fmboost/models/unet/model.py","file_url":"https://github.com/compvis/fm-boosting/blob/HEAD/fmboost/models/unet/model.py","link_basis":"first_harvest_node","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":"ffc4ff1275bb5b7d"}},{"code_sha256_prefix":"9778f92ec0ba682d","entry":"SpatialTransformer","repo":"stability-ai/generative-models","repo_kind":"official","path":"sgm/modules/diffusionmodules/openaimodel.py","file_url":"https://github.com/stability-ai/generative-models/blob/HEAD/sgm/modules/diffusionmodules/openaimodel.py","link_basis":"first_harvest_node","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":"9778f92ec0ba682d"}},{"code_sha256_prefix":"d0977bbe6d3f1b49","entry":"SpatialVideoTransformer","repo":"stability-ai/generative-models","repo_kind":"official","path":"sgm/modules/diffusionmodules/openaimodel.py","file_url":"https://github.com/stability-ai/generative-models/blob/HEAD/sgm/modules/diffusionmodules/openaimodel.py","link_basis":"first_harvest_node","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":"d0977bbe6d3f1b49"}},{"code_sha256_prefix":"579d378f598c87ed","entry":"TimestepBlock","repo":"stability-ai/generative-models","repo_kind":"official","path":"sgm/modules/diffusionmodules/openaimodel.py","file_url":"https://github.com/stability-ai/generative-models/blob/HEAD/sgm/modules/diffusionmodules/openaimodel.py","link_basis":"first_harvest_node","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":"579d378f598c87ed"}},{"code_sha256_prefix":"0b73a46bc27e47c6","entry":"TimestepEmbedSequential","repo":"stability-ai/generative-models","repo_kind":"official","path":"sgm/modules/diffusionmodules/openaimodel.py","file_url":"https://github.com/stability-ai/generative-models/blob/HEAD/sgm/modules/diffusionmodules/openaimodel.py","link_basis":"first_harvest_node","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":"0b73a46bc27e47c6"}},{"code_sha256_prefix":"5c5d69427c0df4ac","entry":"UNetModel","repo":"stability-ai/generative-models","repo_kind":"official","path":"sgm/modules/diffusionmodules/openaimodel.py","file_url":"https://github.com/stability-ai/generative-models/blob/HEAD/sgm/modules/diffusionmodules/openaimodel.py","link_basis":"first_harvest_node","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":"5c5d69427c0df4ac"}},{"code_sha256_prefix":"54cb1b411b5423e1","entry":"VideoTransformerBlock","repo":"stability-ai/generative-models","repo_kind":"official","path":"sgm/modules/diffusionmodules/openaimodel.py","file_url":"https://github.com/stability-ai/generative-models/blob/HEAD/sgm/modules/diffusionmodules/openaimodel.py","link_basis":"first_harvest_node","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":"54cb1b411b5423e1"}},{"code_sha256_prefix":"0cdcae7b2ec00219","entry":"accuracy","repo":"yuchen413/text2image_safety","repo_kind":"listed","path":"rl_utils.py","file_url":"https://github.com/yuchen413/text2image_safety/blob/HEAD/rl_utils.py","link_basis":"first_harvest_node","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":"0cdcae7b2ec00219"}},{"code_sha256_prefix":"8b2e0a95b5d28430","entry":"get_dictionary","repo":"yuchen413/text2image_safety","repo_kind":"listed","path":"search_utils.py","file_url":"https://github.com/yuchen413/text2image_safety/blob/HEAD/search_utils.py","link_basis":"first_harvest_node","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":"8b2e0a95b5d28430"}},{"code_sha256_prefix":"73a61f7a5d72f3e7","entry":"load_data","repo":"yuchen413/text2image_safety","repo_kind":"listed","path":"search_utils.py","file_url":"https://github.com/yuchen413/text2image_safety/blob/HEAD/search_utils.py","link_basis":"first_harvest_node","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":"73a61f7a5d72f3e7"}},{"code_sha256_prefix":"b85c3309a7d80fdd","entry":"load_nsfw_prompts","repo":"yuchen413/text2image_safety","repo_kind":"listed","path":"baseline/baseline.py","file_url":"https://github.com/yuchen413/text2image_safety/blob/HEAD/baseline/baseline.py","link_basis":"first_harvest_node","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":"b85c3309a7d80fdd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}