{"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":"/code/text-under-image","entry":"text_under_image","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":27,"n_papers_ran":21,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":14,"n_samples_ran":11,"n_samples_fingerprinted":0,"n_places":27,"n_places_pointer_only":16,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":11,"unverified":3},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2509.25940","paper":"/paper/arxiv-2509-25940","title":"Steer Away From Mode Collisions: Improving Composition In Diffusion Models","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"debottam-dutta7/co3","path":"composers/utils/ptp_utils.py","file_url":"https://github.com/debottam-dutta7/co3/blob/HEAD/composers/utils/ptp_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"42f35256bd885673","mcp_get_code":{"code_sha256":"42f35256bd885673"}},{"arxiv_id":"2410.04844","paper":"/paper/postedit-posterior-sampling-for-efficient","title":"PostEdit: Posterior Sampling for Efficient Zero-Shot Image Editing","date":"2024-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TFNTF/PostEdit","path":"ptp_utils.py","file_url":"https://github.com/TFNTF/PostEdit/blob/HEAD/ptp_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"85d5eb123674597d","mcp_get_code":{"code_sha256":"85d5eb123674597d"}},{"arxiv_id":"2409.19967","paper":"/paper/magnet-we-never-know-how-text-to-image","title":"Magnet: We Never Know How Text-to-Image Diffusion Models Work, Until We Learn How Vision-Language Models Function","date":"2024-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"I2-Multimedia-Lab/Magnet","path":"utils/ptp_utils.py","file_url":"https://github.com/I2-Multimedia-Lab/Magnet/blob/HEAD/utils/ptp_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d9c8674eef29679e","mcp_get_code":{"code_sha256":"d9c8674eef29679e"}},{"arxiv_id":"2409.12466","paper":"/paper/audioeditor-a-training-free-diffusion-based","title":"AudioEditor: A Training-Free Diffusion-Based Audio Editing Framework","date":null,"month_inferred_from_arxiv_id":"2024-09","title_source":"archive","repo":"nku-hlt/audioeditor","path":"prompt2prompt/ptp_utils.py","file_url":"https://github.com/nku-hlt/audioeditor/blob/HEAD/prompt2prompt/ptp_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"ef08b7ba80d0df19","mcp_get_code":{"code_sha256":"ef08b7ba80d0df19"}},{"arxiv_id":"2407.07197","paper":"/paper/colorpeel-color-prompt-learning-with","title":"ColorPeel: Color Prompt Learning with Diffusion Models via Color and Shape Disentanglement","date":"2024-07-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"moatifbutt/color-peel","path":"src/train/train_colorpeel.py","file_url":"https://github.com/moatifbutt/color-peel/blob/HEAD/src/train/train_colorpeel.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1e8c10ff412d6286","mcp_get_code":{"code_sha256":"1e8c10ff412d6286"}},{"arxiv_id":"2405.18025","paper":"/paper/unveiling-the-power-of-diffusion-features-for","title":"Where's Waldo: Diffusion Features for Personalized Segmentation and Retrieval","date":"2024-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dvirsamuel/PDM","path":"ptp_utils.py","file_url":"https://github.com/dvirsamuel/PDM/blob/HEAD/ptp_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"957a22837d69c59e","mcp_get_code":{"code_sha256":"957a22837d69c59e"}},{"arxiv_id":"2404.04960","paper":"/paper/pairaug-what-can-augmented-image-text-pairs","title":"PairAug: What Can Augmented Image-Text Pairs Do for Radiology?","date":"2024-04-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YtongXie/PairAug","path":"utils/ptp_utils.py","file_url":"https://github.com/YtongXie/PairAug/blob/HEAD/utils/ptp_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"85d5eb123674597d","mcp_get_code":{"code_sha256":"85d5eb123674597d"}},{"arxiv_id":"2403.18551","paper":"/paper/attention-calibration-for-disentangled-text","title":"Attention Calibration for Disentangled Text-to-Image Personalization","date":"2024-03-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"monalissaa/disendiff","path":"sample.py","file_url":"https://github.com/monalissaa/disendiff/blob/HEAD/sample.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ac63e51754d948b","mcp_get_code":{"code_sha256":"3ac63e51754d948b"}},{"arxiv_id":"2403.16990","paper":"/paper/be-yourself-bounded-attention-for-multi","title":"Be Yourself: Bounded Attention for Multi-Subject Text-to-Image Generation","date":"2024-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"omer11a/bounded-attention","path":"utils.py","file_url":"https://github.com/omer11a/bounded-attention/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"12d5ac647acea4fc","mcp_get_code":{"code_sha256":"12d5ac647acea4fc"}},{"arxiv_id":"2403.12658","paper":"/paper/tuning-free-image-customization-with-image","title":"Tuning-Free Image Customization with Image and Text Guidance","date":"2024-03-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zrealli/TIGIC","path":"ptp_scripts/ptp_utils_ori.py","file_url":"https://github.com/zrealli/TIGIC/blob/HEAD/ptp_scripts/ptp_utils_ori.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"85d5eb123674597d","mcp_get_code":{"code_sha256":"85d5eb123674597d"}},{"arxiv_id":"2403.11627","paper":"/paper/lora-composer-leveraging-low-rank-adaptation","title":"LoRA-Composer: Leveraging Low-Rank Adaptation for Multi-Concept Customization in Training-Free Diffusion Models","date":"2024-03-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"young98cn/lora_composer","path":"region_lora/utils/attn_util.py","file_url":"https://github.com/young98cn/lora_composer/blob/HEAD/region_lora/utils/attn_util.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"cbb03c8ff754e2d0","mcp_get_code":{"code_sha256":"cbb03c8ff754e2d0"}},{"arxiv_id":"2403.05053","paper":"/paper/primecomposer-faster-progressively-combined","title":"PrimeComposer: Faster Progressively Combined Diffusion for Image Composition with Attention Steering","date":"2024-03-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"codegoat24/primecomposer","path":"ptp_scripts/ptp_utils.py","file_url":"https://github.com/codegoat24/primecomposer/blob/HEAD/ptp_scripts/ptp_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"85d5eb123674597d","mcp_get_code":{"code_sha256":"85d5eb123674597d"}},{"arxiv_id":"2402.12908","paper":"/paper/realcompo-dynamic-equilibrium-between-realism","title":"RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models","date":"2024-02-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yangling0818/realcompo","path":"keypoint_model/attention.py","file_url":"https://github.com/yangling0818/realcompo/blob/HEAD/keypoint_model/attention.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fa11e1f8bcafb6d1","mcp_get_code":{"code_sha256":"fa11e1f8bcafb6d1"}},{"arxiv_id":"2402.11846","paper":"/paper/unlearncanvas-a-stylized-image-dataset-to","title":"UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sen-mao/SuppressEOT","path":"utils/ptp_utils.py","file_url":"https://github.com/sen-mao/SuppressEOT/blob/HEAD/utils/ptp_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"85d5eb123674597d","mcp_get_code":{"code_sha256":"85d5eb123674597d"}},{"arxiv_id":"2312.12540","paper":"/paper/fixed-point-inversion-for-text-to-image","title":"Lightning-Fast Image Inversion and Editing for Text-to-Image Diffusion Models","date":"2023-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dvirsamuel/FPI","path":"p2p/ptp_utils.py","file_url":"https://github.com/dvirsamuel/FPI/blob/HEAD/p2p/ptp_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cadccc5f1e1e3a53","mcp_get_code":{"code_sha256":"cadccc5f1e1e3a53"}},{"arxiv_id":"2312.12232","paper":"/paper/brush-your-text-synthesize-any-scene-text-on","title":"Brush Your Text: Synthesize Any Scene Text on Images via Diffusion Model","date":"2023-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ecnuljzhang/brush-your-text","path":"models/attention_utils.py","file_url":"https://github.com/ecnuljzhang/brush-your-text/blob/HEAD/models/attention_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"85d5eb123674597d","mcp_get_code":{"code_sha256":"85d5eb123674597d"}},{"arxiv_id":"2311.16491","paper":"/paper/z-zero-shot-style-transfer-via-attention","title":"$Z^*$: Zero-shot Style Transfer via Attention Rearrangement","date":"2023-11-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HolmesShuan/Zero-shot-Style-Transfer-via-Attention-Rearrangement","path":"ptp_utils.py","file_url":"https://github.com/HolmesShuan/Zero-shot-Style-Transfer-via-Attention-Rearrangement/blob/HEAD/ptp_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"85d5eb123674597d","mcp_get_code":{"code_sha256":"85d5eb123674597d"}},{"arxiv_id":"2309.14494","paper":"/paper/free-bloom-zero-shot-text-to-video-generator","title":"Free-Bloom: Zero-Shot Text-to-Video Generator with LLM Director and LDM Animator","date":"2023-09-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"soolab/free-bloom","path":"freebloom/prompt_attention/ptp_utils.py","file_url":"https://github.com/soolab/free-bloom/blob/HEAD/freebloom/prompt_attention/ptp_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"45af788f85d9d0c3","mcp_get_code":{"code_sha256":"45af788f85d9d0c3"}},{"arxiv_id":"2308.06160","paper":"/paper/datasetdm-synthesizing-data-with-perception-1","title":"DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models","date":"2023-08-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"showlab/datasetdm","path":"ptp_utils.py","file_url":"https://github.com/showlab/datasetdm/blob/HEAD/ptp_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2f61baa7d4185642","mcp_get_code":{"code_sha256":"2f61baa7d4185642"}},{"arxiv_id":"2307.14352","paper":"/paper/general-image-to-image-translation-with-one","title":"General Image-to-Image Translation with One-Shot Image Guidance","date":"2023-07-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"crystalneuro/visual-concept-translator","path":"ptp_utils.py","file_url":"https://github.com/crystalneuro/visual-concept-translator/blob/HEAD/ptp_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"85d5eb123674597d","mcp_get_code":{"code_sha256":"85d5eb123674597d"}},{"arxiv_id":"2307.12493","paper":"/paper/tf-icon-diffusion-based-training-free-cross","title":"TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition","date":"2023-07-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Shilin-LU/TF-ICON","path":"ptp_scripts/ptp_utils.py","file_url":"https://github.com/Shilin-LU/TF-ICON/blob/HEAD/ptp_scripts/ptp_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"85d5eb123674597d","mcp_get_code":{"code_sha256":"85d5eb123674597d"}},{"arxiv_id":"2307.10864","paper":"/paper/divide-bind-your-attention-for-improved","title":"Divide & Bind Your Attention for Improved Generative Semantic Nursing","date":"2023-07-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"boschresearch/Divide-and-Bind","path":"utils/ptp_utils.py","file_url":"https://github.com/boschresearch/Divide-and-Bind/blob/HEAD/utils/ptp_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"code_sha256_prefix":"42f35256bd885673","mcp_get_code":{"code_sha256":"42f35256bd885673"}},{"arxiv_id":"2307.10816","paper":"/paper/boxdiff-text-to-image-synthesis-with-training","title":"BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion","date":"2023-07-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"showlab/boxdiff","path":"utils/ptp_utils.py","file_url":"https://github.com/showlab/boxdiff/blob/HEAD/utils/ptp_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"42f35256bd885673","mcp_get_code":{"code_sha256":"42f35256bd885673"}},{"arxiv_id":"2305.16311","paper":"/paper/break-a-scene-extracting-multiple-concepts","title":"Break-A-Scene: Extracting Multiple Concepts from a Single Image","date":"2023-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google/break-a-scene","path":"ptp_utils.py","file_url":"https://github.com/google/break-a-scene/blob/HEAD/ptp_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"cbb03c8ff754e2d0","mcp_get_code":{"code_sha256":"cbb03c8ff754e2d0"}},{"arxiv_id":"2305.13921","paper":"/paper/compositional-text-to-image-synthesis-with","title":"Compositional Text-to-Image Synthesis with Attention Map Control of Diffusion Models","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OPPO-Mente-Lab/attention-mask-control","path":"p2p.py","file_url":"https://github.com/OPPO-Mente-Lab/attention-mask-control/blob/HEAD/p2p.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"75f3f5c72eded945","mcp_get_code":{"code_sha256":"75f3f5c72eded945"}},{"arxiv_id":"2301.13826","paper":"/paper/attend-and-excite-attention-based-semantic","title":"Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models","date":"2023-01-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AttendAndExcite/Attend-and-Excite","path":"utils/ptp_utils.py","file_url":"https://github.com/AttendAndExcite/Attend-and-Excite/blob/HEAD/utils/ptp_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"42f35256bd885673","mcp_get_code":{"code_sha256":"42f35256bd885673"}},{"arxiv_id":"aaai_28210","paper":null,"title":"arXiv:aaai_28210","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"AnonymousPony/adap-edit","path":"ptp_utils.py","file_url":"https://github.com/AnonymousPony/adap-edit/blob/HEAD/ptp_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"85d5eb123674597d","mcp_get_code":{"code_sha256":"85d5eb123674597d"}}]}