{"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/stable-flow-vital-layers-for-training-free","title":"Stable Flow: Vital Layers for Training-Free Image Editing","arxiv_id":"2411.14430","date":"2024-11-21","proceeding":"CVPR 2025 1","authors":["Omri Avrahami","Or Patashnik","Ohad Fried","Egor Nemchinov","Kfir Aberman","Dani Lischinski","Daniel Cohen-Or"],"abstract":"Diffusion models have revolutionized the field of content synthesis and editing. Recent models have replaced the traditional UNet architecture with the Diffusion Transformer (DiT), and employed flow-matching for improved training and sampling. However, they exhibit limited generation diversity. In this work, we leverage this limitation to perform consistent image edits via selective injection of attention features. The main challenge is that, unlike the UNet-based models, DiT lacks a coarse-to-fine synthesis structure, making it unclear in which layers to perform the injection. Therefore, we propose an automatic method to identify \"vital layers\" within DiT, crucial for image formation, and demonstrate how these layers facilitate a range of controlled stable edits, from non-rigid modifications to object addition, using the same mechanism. Next, to enable real-image editing, we introduce an improved image inversion method for flow models. Finally, we evaluate our approach through qualitative and quantitative comparisons, along with a user study, and demonstrate its effectiveness across multiple applications. The project page is available at https://omriavrahami.com/stable-flow","url_abs":"https://arxiv.org/abs/2411.14430v2","url_pdf":"https://arxiv.org/pdf/2411.14430v2.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":"stable-flow-vital-layers-for-training-free","repo_url":"https://github.com/snap-research/stable-flow","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"text-based-image-editing","task_name":"Text-based Image Editing"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2411.14430","atlas_url":"https://app.syntology.ai/?focus=2411.14430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.14430"}},"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/snap-research/stable-flow","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_draft_wrong":2,"unverified":3},"by_repo_kind":{"official":{"samples":5,"ran":2,"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":5,"samples":[{"code_sha256_prefix":"bea2d776a332f2b0","entry":"rescale_noise_cfg","repo":"snap-research/stable-flow","repo_kind":"official","path":"src/diffusers/pipelines/ledits_pp/pipeline_leditspp_stable_diffusion.py","file_url":"https://github.com/snap-research/stable-flow/blob/HEAD/src/diffusers/pipelines/ledits_pp/pipeline_leditspp_stable_diffusion.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":"bea2d776a332f2b0"}},{"code_sha256_prefix":"22b1f260da28f6a5","entry":"retrieve_timesteps","repo":"snap-research/stable-flow","repo_kind":"official","path":"src/diffusers/pipelines/controlnet_sd3/pipeline_stable_diffusion_3_controlnet.py","file_url":"https://github.com/snap-research/stable-flow/blob/HEAD/src/diffusers/pipelines/controlnet_sd3/pipeline_stable_diffusion_3_controlnet.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"22b1f260da28f6a5"}},{"code_sha256_prefix":"27bff28c523da898","entry":"compute_noise_ddim","repo":"snap-research/stable-flow","repo_kind":"official","path":"src/diffusers/pipelines/ledits_pp/pipeline_leditspp_stable_diffusion.py","file_url":"https://github.com/snap-research/stable-flow/blob/HEAD/src/diffusers/pipelines/ledits_pp/pipeline_leditspp_stable_diffusion.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"27bff28c523da898"}},{"code_sha256_prefix":"d5f7d36f84d73743","entry":"compute_noise_sde_dpm_pp_2nd","repo":"snap-research/stable-flow","repo_kind":"official","path":"src/diffusers/pipelines/ledits_pp/pipeline_leditspp_stable_diffusion.py","file_url":"https://github.com/snap-research/stable-flow/blob/HEAD/src/diffusers/pipelines/ledits_pp/pipeline_leditspp_stable_diffusion.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d5f7d36f84d73743"}},{"code_sha256_prefix":"d32228909732c0bc","entry":"retrieve_timesteps","repo":"snap-research/stable-flow","repo_kind":"official","path":"src/diffusers/pipelines/aura_flow/pipeline_aura_flow.py","file_url":"https://github.com/snap-research/stable-flow/blob/HEAD/src/diffusers/pipelines/aura_flow/pipeline_aura_flow.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d32228909732c0bc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}