Dataset Viewer (First 5GB)
Auto-converted to Parquet
webp
imagewidth (px)
92
2.05k
__key__
stringlengths
45
49
__url__
stringclasses
563 values
danbooru_1005011_5c9d10ad7073b8eae2ea34f751cb18f2
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1005012_16fdedc9a4069a50a392d74c6d1e5e9d
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1005088_b95d878c2f8a75ef8a107dc8c5a56977
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1005335_43b12bbdad0b06163c9eddd7116bbbda
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1005421_4db9172f2843730e2f7b320f0457d5a7
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1005438_12247b59cd4facd0f4047194970799a9
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1005439_21cd27f91a6ad2be985341a3933eff1a
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1005440_f35bd425af734cbfb1a1abd5b7f92886
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1005441_cba501b83f0dbefb2b3a8f654b69c83b
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1005521_806a69bef6abd8a38b554441661df173
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1005703_a15648cecc760d38b7f60088ec742984
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1005706_7bb86a9b7cad4c388d46e390f9442ca5
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1005734_3ad059372f3ed81dff52a893d1bc8e00
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1005767_aafcdd894812221d3c7f251c59b8a0bb
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1005770_550270d45eb4ab8a6eee763c382b4294
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1006056_c1d0cb26fd97bd74d405e72a33d34dd5
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1006094_5d6a1cc39d9d858761e1b862b21a70ac
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1006111_378d6401c24da19d7e4f35b72af5a7b7
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1006166_b8eb352a630e69b30e00afb083127a8a
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1006397_7a64ed55dd9cdb9e94fd46a3650bf985
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1006458_ac40cc21c581877a302993561693e7b9
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1006578_92897a76a141df06e4d4d99653c3186c
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1006640_4cb6bab0971d3359d1fe5e783924cd89
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1006803_b434327ad7751667816608b198e23638
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1006915_98935e5aa7c14aa3f2c973c718b0ae27
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1006950_bf8530ccc6750fc0d356e4e6699368ac
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1007062_0e27c2152bb67d4c1c5fe60cfc8bb6ce
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1007074_49ab4e3b58a7e5b1228210db6c60150a
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1007417_1f8a2851e85d1773698500e64bafe22c
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1007625_392c947061fa8f5c5dbe2c7295ec8cca
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1007701_52da22a41d577ec1700181c5cac080d4
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1007706_97fa94f52a5c7d740901215896e3c799
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1007711_0f7ec69be5bd39bc60d3d3f4c8f16419
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1007799_f77145d186a74141e19d4c6ab7ac0772
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1007835_040945a7e996dd3e2a1aba5dd3735f6d
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1008027_c2a11c956d5b8fc88456d03ee6025a74
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1008064_d69350fc58fdca31819ce9fe2f5ea19a
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1008070_0582f413128be201cc9f9cff8c89b44f
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1008072_66cfdea689f8215ee5d03f0dc85a956a
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1008076_09c022b0b66123f3c006e2d21270e1d8
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1008197_e43c0487e5230748d02fbde1575e6f7f
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1008290_fed0fa9f2493edfaa7e7def27ddf074d
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1008336_c8215540708e3ba9bff39c95a97d158c
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1008411_99d0679a915b7b030c92fa823bcc5888
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1008441_e3a4f6a32927f76f911ddbb30855e98b
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1008481_11a1b2cab76ef1029be1a2519f072e62
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1008639_d235585f7cc106de248b6fe559b6ad6e
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1008663_30dce5156909280ef658c1b4e906a52c
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1008665_7071cc2285da6b34fea7c1886fa7502f
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1008698_8489d4930b18732afda8d0acbfda6a7f
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1008870_390c36c2c897b7f06b3fe899b6bc6677
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1008871_e117a47162865891d99d661d3fbb3af7
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1009058_c6b8238eaff16f8990c6025a62c9cf4f
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1009068_1f5d63a1a2917805cc274566628e77cc
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1009088_3422eeb9d68403ebe0fe2084e13cf023
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1009374_9fd1916436109e4c157b7c54dab1b552
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1009441_fadd44c01033101f568c3865352de4b4
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1009465_9fe36c3d800c4c22a0fe289d5b62808c
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1009467_1c8b0f6d02f9933ad3a7d52e817b4b13
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1009473_065ab342561b87401620d63120d2d6ca
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1009474_2f2294ff9fce4537fe72dd16b808b152
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1009476_d43f63f552c17bea13a6d36b10fcd8d4
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1009478_fa04f90d877f09fd206010dc8d77abae
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1009588_b1b46ff882442344494e25c865a040b4
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1009615_5fd344b0dc2d56f2f5abf7e085421f40
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1009747_80869fdb0a2cef4b4ea05e292cded33c
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1009857_40b4a5b07d3cfb8e5c25c5fcdd7c5629
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1010071_422873d106732733ce6c71602459cfee
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1010107_cb5066cc3230e3615c75a8bb2b6981cb
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1010125_8c6973529599119905d6ed9a2bcfb3b5
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1010199_bf273d84431ab24a77937c9f2352880c
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1010314_a64a271c6e6d21aae4bb3a57e5ee06af
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1010316_9196e42bb77aec3b325453ae5a3c27b2
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1010319_b25b449891cbf3a6c50b211a8f6afd29
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1010346_b04605ab183589c47b170d995fab1bb5
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1010433_373f0fda8ca8b10a4887cb8cefa40a37
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1010463_9dfc78cbd7bc499e9c565740b0598bb2
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1010476_bf726527727bb52055fd8d585ced8b7d
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1010493_713ab9d799d5330c5436c794c9e67b20
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1010496_8367706b25afdc7ee9ac9463b4eba831
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1010502_7818438ddf4a3483df9050216b40fb30
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1010672_6514f4d231a7b29fc78dca72d372d83f
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1010759_5d553c6462d64b836ccb97c681d66af2
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1010889_1a2066ded3ab5a4ecdf37cf9457fe3a7
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1010965_c9839a9ac767990a2b1e771aba8990be
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1011088_050e734f26fb49946284c3751af78569
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1011129_da687e6344fe7973cee38bb7709f35a2
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1011163_4413d7b83c5525636051cd002ffc7dc2
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1011323_f33a6955dd54d0949f73f489becb8cd9
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1011343_912d9f1e213a5c2fb56c0e57efd7dc66
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1011357_989054cf61fc32a862de7a6b72ed3375
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1011448_fd3692e9bec08ce64dab4787f2643319
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1011574_d985ba01a820f780904abbf17647c917
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1011738_a5c0f749b0e328339e415d6fef813ea5
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1011758_6b52554d3a70673867df4fc52d9f8d8a
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1011761_0992953c2706692eab49e138e687b61a
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1011763_bdbf36aa633b191a669d78be966bef46
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1011766_9aac7a990141d15d0d04cd3169d31cd1
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1011768_f875f4683e157ef174b78452fec7ea75
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
danbooru_1011770_4e4ce267871f30686821da791e3a7b4a
hf://datasets/WarriorMama777/PureDanbooru@24c1de588173364a9890fe184caf694365faa027/alphachannel/Danbooru/images_by_15000id_01/id_1005001__1020000.tar
End of preview. Expand in Data Studio

PureDanbooru Dataset

WarriorMama777/PureDanbooru

WarriorMama777/PureDanbooru



概要

このデータセットはDanbooruをメインに700万枚のイラストで構成された大規模な画像データセットです。

特徴は以下の通りです。

  • Danbooruのタグを純粋に維持した未検閲のトレーニング用データセット。Danbooruのユーザーたちが地道に長年作業してきたタグ付けの作業がピュアに維持されています。
  • 丁寧な前処理、およびトレーニング用にデータを整形済み。sd-scriptsのFinetuningに準拠した形でトレーニング用Jsonが提供されており、箱から出してすぐに使えます。

データセットの詳細

画像は主にDanbooruのイラストレーションで構成されています(Danbooruの一部のタグは隠されており有料会員しか閲覧できないので、その部分をGelbooru等から補填しています)。

画像の収集

主にDanbooruからgallery-dlを使用して収集したデータセットです。収集方法の詳細は以下の通りです。

  • 収集方法:

    • Danbooruのクエリを用いて特定の検索ワードに対するURLを取得し、gallery-dlのためのコマンドリストを作成。
    • 画像IDを15,000ごとに分割し、2024年4月時点でDanbooruに存在していたほぼすべての画像を数日から数週間かけて収集。
  • 画像フィルタリング:

    • スコアがマイナスの画像を除外。
    • 画像サイズが10KB以上15MB以下のものに限定。これは、非常に大きなキャンバスサイズの画像が収集作業の妨げになるのを防ぐためです。
  • 注意点:

    • 収集過程でリクエストを大量に送信した結果、CloudflareからBANを受け、生IPではDanbooruから画像をダウンロードできなくなりました🥺 このため、VPNを使用して作業を継続しましたが、この方法は推奨しません。

内容

  • 初板
    • Danbooru|id1 ~ id7440000

ダウンロードコマンド例

  • Danbooruの検索クエリ:score:>-1 id:1..15000 filetype:png,jpg,webp filesize:10kb..15m
  • gallery-dlのダウンロードコマンド例:gallery-dl "https://danbooru.donmai.us/posts?tags=score%3A%3E-1+id%3A1..15000+filetype%3Apng%2Cjpg%2Cwebp+filesize%3A10kb..15M&z=5" -d "D:\dataset\danbooru\images_by_15000id" --write-metadata

前処理ツール

データセットの規模と複雑性に対応するため、前処理スクリプトライブラリを同時に開発する必要がありました。このライブラリ"data-kitchen"は、すべてがAI によってプログラミングされたシンプルなコードで構成されていますが、データセットを構築する上での様々なタスクを効率的に処理することができました。
このカスタム前処理ライブラリのおかげで、データセットの構築プロセスが合理化され、大規模な画像コレクションを作成することができました。

WarriorMama777/data-kitchen WarriorMama777/data-kitchen

サイズ

  • 画像/メタデータ/タグテキスト:それぞれ約700万
  • 画像総ファイルサイズ:約1.3TB (圧縮時&解凍時)
  • データセットjson:約2000万行、約40億文字数

画像の前処理

圧縮

画像の形式および削減率
画像はすべて以下の形式に前処理されています。

  • 画像形式:webp
  • 品質:90
  • 長辺が2048pxになるようにリサイズ
  • 透過背景は白背景に変換

これによって、7.86 TB だった圧縮前のデータ量が、圧縮後には 1.3 TB になりました。これはデータ量を約 83.47% 削減したことになります。

前処理コマンドサンプル

python image_converter_pillow.py --dir "H:\dataset\raw\images\danbooru\images_by_15000id_02\id_7425001__7440000" --save_dir "H:\dataset\comp_image\webp\images_by_15000id_02" --extension jpg png webp --preserve_own_folder --format webp --quality 90 --resize 2048 --background ffffff --gc_disable --threads 20 --comp 4

重複削除

すべての画像はdata-kitchen/image_cleaner.pyを使って、重複画像の検出および整理がされています。
dhash(差分ハッシュ)を使用して画像の類似性を判定し、しきい値(Hamming距離の閾値)12を使用して、表情差分のような画像は1枚のみを残して、他はすべてduplicate_imageフォルダに移動・整理されています。

画像例

duplicate image sample

duplicate image sample

前処理コマンドサンプル

python image_cleaner.py --dir "H:\dataset\comp_image\webp\images_by_15000id_01\id_1__15000" --save_dir "H:\dataset\image\Danbooru\images_by_15000id_01" --extension "jpg png webp" --threshold 12 --gc_disable --preserve_own_folder --save_dir_duplicate "H:\dataset\duplicate_image\Danbooru\images_by_15000id_01" --process_group 8

透過情報

sd-scriptsにおける学習において画像の透過情報は有害なノイズの原因となるためすべての画像は白背景に変換されていますが、透過情報が失われるのは避けつつ、データセットが肥大化するのも避けたかったため、アルファチャンネル情報だけ保存しておくことにしました。
alphachannelフォルダには、透過情報を持っていると判定された画像のみ、白黒形式に変換された画像が保存されています。

画像例

alphachannel image sample

alphachannel image sample

前処理コマンドサンプル

python image_converter_pillow.py --dir "H:\dataset\raw\images\danbooru\images_by_15000id_02" --save_dir "H:\dataset\alphachannel\images_by_15000id_02" --extension png webp --recursive --preserve_own_folder --preserve_structure --format webp --quality 90 --resize 2048 --gc_disable --threads 22 --comp 4 --save_only_alphachannel --by_folder

タグとメタデータ

メタデータ

メタデータはgallery-dlの--write-metadataを使ってDanbooruのオリジナルな情報を収集しています。
具体的には以下のような形式で保存されています。

{
    "id": 1,
    "created_at": "2005-05-23T23:35:31.000-04:00",
    "uploader_id": 1,
    "score": 715,
    "source": "http://www.biwa.ne.jp/~kyogoku/nekotama.jpg",
    "md5": "d34e4cf0a437a5d65f8e82b7bcd02606",
    "last_comment_bumped_at": "2024-03-11T16:09:34.477-04:00",
    "rating": "s",
    "image_width": 459,
    "image_height": 650,
    "tag_string": "1girl 2000s_(style) white_border white_thighhighs",
    "fav_count": 1101,
    "file_ext": "jpg",
    "last_noted_at": null,
    "parent_id": 57501,
    "has_children": false,
    "approver_id": null,
    "tag_count_general": 61,
    "tag_count_artist": 1,
    "tag_count_character": 1,
    "tag_count_copyright": 2,
    "file_size": 127238,
    "up_score": 702,
    "down_score": -3,
    "is_pending": false,
    "is_flagged": false,
    "is_deleted": false,
    "tag_count": 69,
    "updated_at": "2024-02-23T23:16:23.261-05:00",
    "is_banned": false,
    "pixiv_id": null,
    "last_commented_at": "2024-05-23T13:44:46.633-04:00",
    "has_active_children": false,
    "bit_flags": 0,
    "tag_count_meta": 4,
    "has_large": false,
    "has_visible_children": false,
    "media_asset": {
        "id": 1,
        "created_at": "2005-05-23T23:35:31.000-04:00",
        "updated_at": "2023-02-23T03:15:45.265-05:00",
        "md5": "d34e4cf0a437a5d65f8e82b7bcd02606",
        "file_ext": "jpg",
        "file_size": 127238,
        "image_width": 459,
        "image_height": 650,
        "duration": null,
        "status": "active",
        "file_key": "wUufKEivb",
        "is_public": true,
        "pixel_hash": "9c877dd5674d7fa251ce2de0c956fd36",
        "variants": [
            {
                "type": "180x180",
                "url": "https://cdn.donmai.us/180x180/d3/4e/d34e4cf0a437a5d65f8e82b7bcd02606.jpg",
                "width": 127,
                "height": 180,
                "file_ext": "jpg"
            },
            {
                "type": "360x360",
                "url": "https://cdn.donmai.us/360x360/d3/4e/d34e4cf0a437a5d65f8e82b7bcd02606.jpg",
                "width": 254,
                "height": 360,
                "file_ext": "jpg"
            },
            {
                "type": "720x720",
                "url": "https://cdn.donmai.us/720x720/d3/4e/d34e4cf0a437a5d65f8e82b7bcd02606.webp",
                "width": 459,
                "height": 650,
                "file_ext": "webp"
            },
            {
                "type": "original",
                "url": "https://cdn.donmai.us/original/d3/4e/d34e4cf0a437a5d65f8e82b7bcd02606.jpg",
                "width": 459,
                "height": 650,
                "file_ext": "jpg"
            }
        ]
    },
    "tag_string_general": "1girl 2000s_(style) white_thighhighs",
    "tag_string_character": "kousaka_tamaki",
    "tag_string_copyright": "to_heart_(series) to_heart_2",
    "tag_string_artist": "kyogoku_shin",
    "tag_string_meta": "bad_id bad_link commentary translated",
    "file_url": "https://cdn.donmai.us/original/d3/4e/d34e4cf0a437a5d65f8e82b7bcd02606.jpg",
    "large_file_url": "https://cdn.donmai.us/original/d3/4e/d34e4cf0a437a5d65f8e82b7bcd02606.jpg",
    "preview_file_url": "https://cdn.donmai.us/180x180/d3/4e/d34e4cf0a437a5d65f8e82b7bcd02606.jpg",
    "filename": "d34e4cf0a437a5d65f8e82b7bcd02606",
    "extension": "jpg",
    "date": "2005-05-24 03:35:31",
    "tags": [
        "1girl",
        "white_thighhighs"
    ],
    "tags_artist": [
        "kyogoku_shin"
    ],
    "tags_character": [
        "kousaka_tamaki"
    ],
    "tags_copyright": [
        "to_heart_(series)",
        "to_heart_2"
    ],
    "tags_general": [
        "1girl",
        "2000s_(style)",
        "white_thighhighs"
    ],
    "tags_meta": [
        "bad_id",
        "bad_link",
        "commentary",
        "translated"
    ],
    "search_tags": "score:>-1 id:1..15000 filetype:png,jpg,webp filesize:10kb..5M",
    "category": "danbooru",
    "subcategory": "tag"
}

タグ

形式

タグはメタデータから以下のような形式に変換されています。

tenmaso,rozen_maiden,suiseiseki,illustration,|||,1girl,brown_hair,corset,dress,drill_hair,frills,green_dress,green_eyes,hat,heterochromia,lolita_fashion,long_hair,long_sleeves,red_eyes,ribbon,simple_background,solo,twin_drills,twintails,very_long_hair,|||,rating_g

タグは、下記のコマンドによってメタデータから以下のような形式に変換されています。

  • Danbooruメタデータからプレーンテキストに変換された純粋なタグ
  • すべてのタグにillustrationを付与
  • sd-scriptsで次のように指定することで使用できるセパレータ|||を、タグテキストの先頭と末尾に付与しています。:--keep_tokens_separator="|||"
  • 並び順|「アーティスト名→作品名→キャラクター名→illustration,|||→タグテキスト→|||→レーティング」
変換処理

タグはdata-kitchen/metadata_converter_danbooru.pyを使ってメタデータからプレーンテキストに変換され、tagフォルダに保存されています。変換処理のサンプルコマンドは以下のような形式になります。コマンドの具体的な内容については、data-kitchenリポジトリを確認してください。

python metadata_converter_danbooru.py --metadata_order "tag_string_artist" "tag_string_copyright" "tag_string_character" "tag_string_general" "rating" --dir "H:\dataset\metadata\Danbooru\images_by_15000id_01" --save_dir "H:\dataset\tag\Danbooru\images_by_15000id_01" --insert_custom_text 3 "`illustration,|||`" 4 "|||" --recursive --preserve_own_folder --preserve_structure --gc_disable --by_folder

キャプション

現状、次のような理由からキャプションは付属していません。

  • ローカルで処理するにはコンピュータ等のリソースに限界がある
  • 日本語性能の良いオープンソースVLMモデルが存在しない

CogVLMやMini-CPMは素晴らしいですが、ほとんど英語しか理解できず、多言語のOCRはできないようです。GPT4oは本当に完璧ですが有料です。

どういうことか気になる人は、以下のトグルを確認してください🥺

👁‍🗨VLM Test Result Sample (Anime illustration)

▼Test01:OCR

VLM用プロンプト

Please write a caption. It's a brief sentence that describes an image. Summarize it objectively and concisely, logically describing the main focus, actions, and context of the image. Start with the overall picture and then add specific details. Avoid personal opinions and non-essential details, and do not discuss the atmosphere of the scene or the emotions it may evoke. If there is text in the image, read it like OCR and describe it in the language it is written in (do not translate it into English unnecessarily). For background art, accurately describe objects and situations in the background. If there are no people, only describe the background. If there are characters, accurately describe features such as clothing and appearance. Summarize and describe this image in one paragraph. The base language for the description is English, but note that this does not apply to the OCR transcription function.

対象画像


CogVLM2

A young woman with short, dark hair and red eyes is captured in a moment of singing into a microphone. She wears a traditional kimono adorned with floral patterns, suggesting a cultural or celebratory event. The background is simple, with soft, warm colors and Japanese text, which may indicate the lyrics or a poetic context for her performance.

→🤔

GLM 4v 9B
cuuupid/glm-4v-9b – Run with an API on Replicate

The image depicts an animated character with short, dark blue hair and red eyes holding a microphone, suggesting they are singing or speaking. The character is dressed in a traditional Japanese kimono with a floral pattern in shades of blue and purple. The background is plain white with Japanese text in a casual script, likely lyrics or a poem, to the right of the character

→🤔

GPT4o

The image depicts an anime-style character with short dark blue hair and red eyes, dressed in a traditional blue floral kimono. The character is holding a microphone and appears to be singing. Surrounding the character, there is Japanese text: "勇気の鈴が りんりんりーん ♪ ふしぎな冒険 るんるんるーん ♪".

→💯🎉😭🎉💯

なんのキャラクターか分かりますか?

ChatGPT
はい、このキャラクターは『アイドルマスター シャイニーカラーズ』に登場する杜野凛世(もりの りんぜ)です。彼女は283プロダクションに所属するアイドルの一人で、静かでおしとやかな性格が特徴です。

→💯🎉😭🎉💯


▼Test02:キャラクター理解

対象画像

CogVLM2:EN

In a library setting, a young woman with short blue hair and glasses is engrossed in reading a green book. Beside her, a young woman with long brown hair tied in a ponytail leans in, her hand resting on the other woman's head, possibly in a gesture of comfort or to draw attention to something in the book.

→🤔

GPT4o

The image depicts two characters from the anime "Sailor Moon." On the left is Makoto Kino (Sailor Jupiter), with long brown hair tied in a ponytail and green eyes, wearing a school uniform with a green collar and lacing detail. She is resting her head on one hand and using her other hand to pat the head of Ami Mizuno (Sailor Mercury), who has short blue hair and is wearing glasses. Ami is reading a green book and also dressed in a school uniform with a blue collar. The background features bookshelves filled with colorful books.

→💯🎉😭🎉💯

json

jsonフォルダには、タグと画像を結びつけたトレーニング用メタデータjsonファイルが保存されています。

相対パス

相対パスで記載されたJson形式は以下のようになっています。

{
  "Danbooru\\images_by_15000id_01\\id_1__15000\\danbooru_1_d34e4cf0a437a5d65f8e82b7bcd02606.webp": {
    "tags": "kyogoku_shin,to_heart_(series),to_heart_2,kousaka_tamaki,illustration,|||,1girl,2000s_(style),white_thighhighs,|||,rating_s"
  },
  "Danbooru\\images_by_15000id_01\\id_1__15000\\danbooru_2_710fd9cba4ef37260f9152ffa9d154d8.webp": {
    "tags": "nakamura_hisashi,cardcaptor_sakura,comic_party,leaf_(studio),to_heart_(series),to_heart_2,trigun,card_master_peach,haga_reiko,kuhonbutsu_taishi,sendou_kazuki,takase_mizuki,yoshio_(leaf),yuzuhara_konomi,illustration,|||,2boys,2girls,ahoge,,|||,rating_s"
  }
}
相対パスでもデータセットの画像を読めるようにする

⚠sd-scriptsは現在、相対パスで記載されたJsonを読み込みません。以下のようにコードを変更する必要があります。

train_util.py スクリプトで相対パスに基づいてデータセットを正しく読み込めるように修正するには、次のようにtrain_util.pyスクリプトを修正します。具体的には、abs_path を設定する部分で、os.path.exists を使用する際に、相対パスが subset.image_dir からの相対パスであることを考慮して、そのパスを絶対パスに変換する処理を追加します。これによって、スクリプトがある場所に依存せずに、指定されたデータセットディレクトリ内のファイルを正しく参照できるようになります。

修正前のコード部分:

                if os.path.exists(image_key):
                    abs_path = image_key
                else:
                    paths = glob_images(subset.image_dir, image_key)
                    if len(paths) > 0:
                        abs_path = paths[0]

修正後のコード:

                # 相対パスを絶対パスに変換するためのパスを結合
                potential_path = os.path.join(subset.image_dir, image_key)
                if os.path.exists(potential_path):
                    abs_path = potential_path
                else:
                    # glob_imagesを使って、ディレクトリ内でマッチするファイルを探す
                    paths = glob_images(subset.image_dir, image_key)
                    if len(paths) > 0:
                        abs_path = paths[0]

この変更により、image_keysubset.image_dir からの相対パスである場合、そのパスを subset.image_dir に基づいて絶対パスに変換し、存在するかどうかをチェックします。image_key が直接存在しない場合に限り、glob_images 関数を使用してマッチするファイルを探します。これにより、入力された相対パスが機能し、データセットを正しく読み込むことができるようになります。

絶対パス

現状、sd-scriptsは絶対パスであればコードを修正しなくても正しく画像を読み込むようです。
そのため絶対パスで記載されたJsonも同梱しています。形式は以下のようになっています。

{
  "H:\\Resources\\Resources_AI\\__Dataset\\forLeaningImages\\__Danbooru\\__BooruDiffusion\\dataset\\image\\Danbooru\\images_by_15000id_01\\id_1__15000\\danbooru_1_d34e4cf0a437a5d65f8e82b7bcd02606.webp": {
    "tags": "kyogoku_shin,to_heart_(series),to_heart_2,kousaka_tamaki,illustration,|||,1girl,2000s_(style),white_thighhighs,|||,rating_s"
  }
}

ただし記載されているパスはデータセット構築時のローカルのWindows環境下でのパスであり役に立ちませんので、適宜置換する必要があります。たとえばクラウド環境下(Runpod等)に置く場合は以下のように置換する必要があるでしょう

  • 置換元:H:\\Resources\\Resources_AI\\__Dataset\\forLeaningImages\\__Danbooru\\__BooruDiffusion\\dataset\\image
  • 置換先:\\workspace\\__MyFolder\\image
変換処理サンプルコマンド

変換処理のサンプルコマンドは以下のような形式になります。コマンドの具体的な内容については、data-kitchenリポジトリを確認してください。

python metadata_merger.py --dir_base "H:\dataset\Danbooru\image\images_by_15000id_01\id_1__15000" --dir_append_data "H:\dataset\Danbooru\tag\images_by_15000id_01\id_1__15000" --dir_save_json "H:\dataset\Danbooru\json\datasets_metadata.json" --append_data_key tags --save_full_path
編集方法

データセット用のjsonは非常に巨大で、一番大きいもので2000万の行、42億のテキストがあるため、編集する際はまともなテキストエディタで開いてください。

  • 推奨:Notepad++
  • 非推奨:VSCODE、EmEditor Free、メモ帳など

使用方法

ダウンロード

ダウンロードはhuggingface-cliを推奨します。事前にhuggingface-cliが使えるようにインストールてください。

pip install huggingface-hub

すべてダウンロード

このデータセットをすべてダウンロードするには以下を実行します。
huggingfaceへのログインが求められた場合、huggingfaceのアクセストークンを入力してください。huggingfaceのアクセストークンを持っていない場合、huggingfaceでアクセストークンを作成してください。

huggingface-cli download WarriorMama777/PureDanbooru --repo-type dataset --local-dir "<download_directory_path>"

gitでも可能ですが、ダウンロード総量が肥大化するため非推奨です。

git lfs clone https://huggingface.co/WarriorMama777/PureDanbooru

特定のディレクトリをダウンロード

特定のディレクトリをダウンロードするには、以下のコマンドを使用します:

huggingface-cli download WarriorMama777/PureDanbooru --repo-type dataset --local-dir "<download_directory_path>" --include <directory_to_download>
  • <repo_id> はダウンロードしたいリポジトリのID(例:username/model_name
  • <repo_type> はリポジトリのタイプ(modeldatasetspaceのいずれか)
  • <download_directory_path> はダウンロードしたファイルの保存先ディレクトリパス
  • <directory_to_download> はリポジトリ内でダウンロードしたいディレクトリのパス

解凍方法

データセットは130個ほどの分割されたtarで圧縮されています。
tarを解凍する方法は様々ですが、以下にdata-kitchenの圧縮・解凍スクリプトを用いた解凍方法を記載しておきます。.tar.001を指定することで分割された圧縮ファイルを自動的に認識し、解凍します。
コマンドの具体的な内容については、data-kitchenリポジトリを確認してください。

python packer.py --unpack --dir "./dataset_danbooru.tar.001"

オプション

  • --dir_save "<unpack_directory_path>"

使用例

実際にsd-scriptsを使用して学習する場合、以下のようになるでしょう。
以下はworkspace__MyFolderというディレクトリを作成し、そこにPureDanbooruをダウンロード、解凍した場合を想定しています。
ただしtomlを使用して行う方法もありますので、その場合は各自でお調べください。

accelerate launch --num_processes=4 --multi_gpu --num_machines=1 --gpu_ids=0,1,2,3 sdxl_train.py --pretrained_model_name_or_path "/workspace/stable-diffusion-webui/models/Stable-diffusion/sdxl.safetensors" --in_json "/workspace/__MyFolder/json/datasets_metadata_danbooru_images_by_15000id_01-02_hiddentag_relative-path.json" --train_data_dir "/workspace/__MyFolder/image" --output_dir "/workspace/__MyFolder/model" --precision "float" --save_precision "float" --mixed_precision "fp16" --xformers --gradient_checkpointing --enable_bucket --save_model_as "safetensors" --resolution 1024 --train_batch_size 16 --max_train_epochs 20 --save_every_n_epochs 2 --optimizer_type "prodigy" --learning_rate 1 --lr_scheduler_num_cycles 5 --lr_scheduler "cosine" --output_name "Finetuning_SDXL_PureDanbooru_v1_prodigy" --max_token_length 225 --shuffle_caption --seed 42 --logging_dir "/workspace/__MyFolder/log" --log_prefix=Finetuning_SDXL_PureDanbooru_v1_prodigy --fp8_base --optimizer_args "d_coef=0.8" "decouple=True" "weight_decay=0.01"  "use_bias_correction=True" "safeguard_warmup=True" "betas=0.9,0.99" "eps=1e-08" --keep_tokens_separator="|||" --noise_offset 0.05 --noise_offset_random_strength

データセットの構造

ファイル構成

.
├── alphachannel
│   └── Danbooru
│       ├── images_by_15000id_01
│       │   ├── id_1__15000
│       │   ├── ~~~~~~~~~~~~
│       │   └── id_3330001__3345000
│       └── images_by_15000id_02
│           ├── id_3345001__3360000
│           ├── ~~~~~~~~~~~~
│           └── id_7425001__7440000
├── duplicate_image
│   ├── Danbooru
│   │   ├── images_by_15000id_01
│   │   │   ├── id_1__15000
│   │   │   ├── ~~~~~~~~~~~~
│   │   │   └── id_3330001__3345000
│   │   └── images_by_15000id_02
│   │       ├── id_3345001__3360000
│   │       ├── ~~~~~~~~~~~~
│   │       └── id_7425001__7440000
│   └── Gelbooru
│       ├── hidden_tag_01
│       ├── hidden_tag_02
│       └── hidden_tag_03
├── image
│   ├── Danbooru
│   │   ├── images_by_15000id_01
│   │   │   ├── id_1__15000
│   │   │   ├── ~~~~~~~~~~~~
│   │   │   └── id_3330001__3345000
│   │   └── images_by_15000id_02
│   │       ├── id_3345001__3360000
│   │       ├── ~~~~~~~~~~~~
│   │       └── id_7425001__7440000
│   └── Gelbooru
├── json
│   ├── datasets_metadata_danbooru_images_by_15000id_01-02_full-path.json
│   ├── datasets_metadata_danbooru_images_by_15000id_01-02_hiddentag_full-path.json
│   ├── datasets_metadata_danbooru_images_by_15000id_01-02_hiddentag_relative-path.json
│   └── datasets_metadata_danbooru_images_by_15000id_01-02_relative-path.json
├── metadata
│   ├── Danbooru
│   │   ├── images_by_15000id_01
│   │   │   ├── id_1__15000
│   │   │   ├── ~~~~~~~~~~~~
│   │   │   └── id_3330001__3345000
│   │   └── images_by_15000id_02
│   │       ├── id_3345001__3360000
│   │       ├──~~~~~~~~~~~~
│   │       └── id_7425001__7440000
│   └── Gelbooru
│       ├── hidden_tag_01
│       ├── hidden_tag_02
│       └── hidden_tag_03
└── tag
    ├── Danbooru
    │   ├── images_by_15000id_01
    │   │   ├── id_1__15000
    │   │   ├──~~~~~~~~~~~~
    │   │   └── id_3330001__3345000
    │   └── images_by_15000id_02
    │       ├── id_3345001__3360000
    │       ├── ~~~~~~~~~~~~
    │       └── id_7425001__7440000
    └── Gelbooru
        ├── hidden_tag_01
        ├── hidden_tag_02
        └── hidden_tag_03

データ形式

これはtarで固めたデータセットをアップロードしただけの素朴なデータセットです。
SQL🥃? Datasets🤗?? Dask🍡??? Croissant🥐??????? Parquet🤯?????????
わたしはなにもわからない。

ライセンス

creativeml-openrail-m

引用

強制ではありませんが、引用する場合は以下の形式を使用すると良いでしょう。

WarriorMama777. (2024). "PureDanbooru" (Version 1.0). Hugging Face. https://huggingface.co/datasets/WarriorMama777/PureDanbooru

謝辞

Danbooruおよび、Danbooruで長年にわたって地道にタグ付け作業してきたユーザーの仕事に感謝します。アーティストの皆様に対しては一方的に謝辞を送ることは控えますが、それぞれの仕事に対して敬意を表します。

連絡先情報

当huggingfaceリポジトリのディスカッション欄へどうぞ。

更新履歴

バージョン 日付 変更内容
v1.0.0 2024-07-07 初板

免責事項

READ MORE: Disclaimer (JPN) 1. AIの学習等における機械学習時の著作物の利用については、日本国著作権法第三十条の四第二項「情報解析(多数の著作物その他の大量の情報から、当該情報を構成する言語、音、影像その他の要素に係る情報を抽出し、比較、分類その他の解析を行うことをいう。第四十七条の五第一項第二号において同じ。)の用に供する場合」を参照し行っております。 [著作権法 | e-Gov法令検索: デジタル庁](https://elaws.e-gov.go.jp/document?lawid=345AC0000000048#Mp-At_30) 2. 著作物の掲載にあたっては、私的使用や研究目的である場合、商品化の資料として使用する場合(但し、商品化されるものが著作物の主たる利用目的となる場合にはこの限りではない)、批評・論評・報道での利用である場合、パロディや二次創作としてオリジナリティを発揮する場合等の例外的な著作物の使用が認められるケースに該当すると考え掲載しています。 3. 当該学習データセットは、わいせつな視覚コンテンツを直ちに表示されないよう配慮されており、学習データセットによる投稿が公共の場においてわいせつな内容を表示することを意図するものではありません。 なお、著作権者の意に反する利用や不当な利益を得る利用は避けるべきであり、著作権保有者によって正当な理由をもって当該データセットの関係する過半数の関係者から申し立てされた場合、掲載は速やかに中止されることが保証されます。 また本人は、使用する機械学習データセット中に、著作権者の権利を十分に尊重していないと評価され得る可能性を持つ情報源からのデータが含まれ得ることを認識しており、開発者等関係者が依拠すべき法律の整備等の動向について適切な監視と管理の義務を負っています。 本人は、法律や倫理に反する行為を意図しておらず、著作権者を含むイラストレーター及びアーティスト等の権利を尊重し、人工知能の開発を進めることに努めます。

-----English------

PureDanbooru Dataset

WarriorMama777/PureDanbooru

WarriorMama777/PureDanbooru

Overview

This dataset is a large-scale image dataset composed of 7 million illustrations, primarily from Danbooru.

Its features are as follows:

  • An uncensored training dataset that purely maintains Danbooru tags. The tagging work that Danbooru users have diligently carried out over many years is purely maintained.
  • Carefully preprocessed and formatted data for training. Training JSON is provided in a format compliant with sd-scripts Finetuning, ready to use out of the box.

Dataset Details

The images are mainly composed of illustrations from Danbooru (some tags on Danbooru are hidden and can only be viewed by paid members, so those parts are supplemented from sources like Gelbooru).

Image Collection

This dataset was mainly collected from Danbooru using gallery-dl. The details of the collection method are as follows:

  • Collection Method:

    • Created a command list for gallery-dl by obtaining URLs for specific search words using Danbooru queries.
    • Divided image IDs into groups of 15,000 and collected almost all images that existed on Danbooru as of April 2024 over a period of several days to several weeks.
  • Image Filtering:

    • Excluded images with negative scores.
    • Limited to images with file sizes between 10KB and 15MB. This is to prevent very large canvas size images from hindering the collection process.
  • Note:

    • As a result of sending a large number of requests during the collection process, I was banned by Cloudflare and could no longer download images from Danbooru using a raw IP 🥺 Therefore, I continued our work using a VPN, but this method is not recommended.

Content

  • Initial version
    • Danbooru | id1 ~ id7440000

Download Command Example

  • Danbooru search query: score:>-1 id:1..15000 filetype:png,jpg,webp filesize:10kb..15m
  • gallery-dl download command example: gallery-dl "https://danbooru.donmai.us/posts?tags=score%3A%3E-1+id%3A1..15000+filetype%3Apng%2Cjpg%2Cwebp+filesize%3A10kb..15M&z=5" -d "D:\dataset\danbooru\images_by_15000id" --write-metadata

Preprocessing Tool

To handle the scale and complexity of the dataset, I needed to simultaneously develop a preprocessing script library. This library "data-kitchen" consists entirely of simple code programmed by AI, but it was able to efficiently process various tasks in building the dataset.
Thanks to this custom preprocessing library, the dataset construction process was streamlined, allowing me to create a large-scale image collection.

WarriorMama777/data-kitchen WarriorMama777/data-kitchen

Image Preprocessing

Compression

Image format and reduction rate
All images have been preprocessed to the following format:

  • Image format: webp
  • Quality: 90
  • Resized so that the long side becomes 2048px
  • Transparent backgrounds converted to white backgrounds

This reduced the pre-compression data volume of 7.86 TB to 1.3 TB after compression. This represents a data volume reduction of about 83.47%.

Sample preprocessing command

python image_converter_pillow.py --dir "H:\dataset\raw\images\danbooru\images_by_15000id_02\id_7425001__7440000" --save_dir "H:\dataset\comp_image\webp\images_by_15000id_02" --extension jpg png webp --preserve_own_folder --format webp --quality 90 --resize 2048 --background ffffff --gc_disable --threads 20 --comp 4

Duplicate Removal

All images have been processed for duplicate detection and organization using data-kitchen/image_cleaner.py.
Using dhash (difference hash) to determine image similarity, with a threshold (Hamming distance threshold) of 12, only one image is kept for images with differences like facial expressions, while all others are moved and organized into the duplicate_image folder.

Image example

duplicate image sample

duplicate image sample

Sample preprocessing command

python image_cleaner.py --dir "H:\dataset\comp_image\webp\images_by_15000id_01\id_1__15000" --save_dir "H:\dataset\image\Danbooru\images_by_15000id_01" --extension "jpg png webp" --threshold 12 --gc_disable --preserve_own_folder --save_dir_duplicate "H:\dataset\duplicate_image\Danbooru\images_by_15000id_01" --process_group 8

Transparency Information

While all images have been converted to white backgrounds as transparency information can cause harmful noise in training with sd-scripts, I wanted to avoid losing transparency information while also avoiding dataset bloat. Therefore, I decided to save only the alpha channel information.
The alphachannel folder contains only images that were determined to have transparency information, converted to a black and white format.

Image example

alphachannel image sample

alphachannel image sample

Sample preprocessing command

python image_converter_pillow.py --dir "H:\dataset\raw\images\danbooru\images_by_15000id_02" --save_dir "H:\dataset\alphachannel\images_by_15000id_02" --extension png webp --recursive --preserve_own_folder --preserve_structure --format webp --quality 90 --resize 2048 --gc_disable --threads 22 --comp 4 --save_only_alphachannel --by_folder

Tags and Metadata

Metadata

Metadata is collected using gallery-dl's --write-metadata to gather original information from Danbooru.
Specifically, it is saved in the following format:

{
    "id": 1,
    "created_at": "2005-05-23T23:35:31.000-04:00",
    "uploader_id": 1,
    "score": 715,
    "source": "http://www.biwa.ne.jp/~kyogoku/nekotama.jpg",
    "md5": "d34e4cf0a437a5d65f8e82b7bcd02606",
    "last_comment_bumped_at": "2024-03-11T16:09:34.477-04:00",
    "rating": "s",
    "image_width": 459,
    "image_height": 650,
    "tag_string": "1girl 2000s_(style) white_border white_thighhighs",
    "fav_count": 1101,
    "file_ext": "jpg",
    "last_noted_at": null,
    "parent_id": 57501,
    "has_children": false,
    "approver_id": null,
    "tag_count_general": 61,
    "tag_count_artist": 1,
    "tag_count_character": 1,
    "tag_count_copyright": 2,
    "file_size": 127238,
    "up_score": 702,
    "down_score": -3,
    "is_pending": false,
    "is_flagged": false,
    "is_deleted": false,
    "tag_count": 69,
    "updated_at": "2024-02-23T23:16:23.261-05:00",
    "is_banned": false,
    "pixiv_id": null,
    "last_commented_at": "2024-05-23T13:44:46.633-04:00",
    "has_active_children": false,
    "bit_flags": 0,
    "tag_count_meta": 4,
    "has_large": false,
    "has_visible_children": false,
    "media_asset": {
        "id": 1,
        "created_at": "2005-05-23T23:35:31.000-04:00",
        "updated_at": "2023-02-23T03:15:45.265-05:00",
        "md5": "d34e4cf0a437a5d65f8e82b7bcd02606",
        "file_ext": "jpg",
        "file_size": 127238,
        "image_width": 459,
        "image_height": 650,
        "duration": null,
        "status": "active",
        "file_key": "wUufKEivb",
        "is_public": true,
        "pixel_hash": "9c877dd5674d7fa251ce2de0c956fd36",
        "variants": [
            {
                "type": "180x180",
                "url": "https://cdn.donmai.us/180x180/d3/4e/d34e4cf0a437a5d65f8e82b7bcd02606.jpg",
                "width": 127,
                "height": 180,
                "file_ext": "jpg"
            },
            {
                "type": "360x360",
                "url": "https://cdn.donmai.us/360x360/d3/4e/d34e4cf0a437a5d65f8e82b7bcd02606.jpg",
                "width": 254,
                "height": 360,
                "file_ext": "jpg"
            },
            {
                "type": "720x720",
                "url": "https://cdn.donmai.us/720x720/d3/4e/d34e4cf0a437a5d65f8e82b7bcd02606.webp",
                "width": 459,
                "height": 650,
                "file_ext": "webp"
            },
            {
                "type": "original",
                "url": "https://cdn.donmai.us/original/d3/4e/d34e4cf0a437a5d65f8e82b7bcd02606.jpg",
                "width": 459,
                "height": 650,
                "file_ext": "jpg"
            }
        ]
    },
    "tag_string_general": "1girl 2000s_(style) white_thighhighs",
    "tag_string_character": "kousaka_tamaki",
    "tag_string_copyright": "to_heart_(series) to_heart_2",
    "tag_string_artist": "kyogoku_shin",
    "tag_string_meta": "bad_id bad_link commentary translated",
    "file_url": "https://cdn.donmai.us/original/d3/4e/d34e4cf0a437a5d65f8e82b7bcd02606.jpg",
    "large_file_url": "https://cdn.donmai.us/original/d3/4e/d34e4cf0a437a5d65f8e82b7bcd02606.jpg",
    "preview_file_url": "https://cdn.donmai.us/180x180/d3/4e/d34e4cf0a437a5d65f8e82b7bcd02606.jpg",
    "filename": "d34e4cf0a437a5d65f8e82b7bcd02606",
    "extension": "jpg",
    "date": "2005-05-24 03:35:31",
    "tags": [
        "1girl",
        "white_thighhighs"
    ],
    "tags_artist": [
        "kyogoku_shin"
    ],
    "tags_character": [
        "kousaka_tamaki"
    ],
    "tags_copyright": [
        "to_heart_(series)",
        "to_heart_2"
    ],
    "tags_general": [
        "1girl",
        "2000s_(style)",
        "white_thighhighs"
    ],
    "tags_meta": [
        "bad_id",
        "bad_link",
        "commentary",
        "translated"
    ],
    "search_tags": "score:>-1 id:1..15000 filetype:png,jpg,webp filesize:10kb..5M",
    "category": "danbooru",
    "subcategory": "tag"
}

Tags

Format

Tags are converted from metadata to the following format:

tenmaso,rozen_maiden,suiseiseki,illustration,|||,1girl,brown_hair,corset,dress,drill_hair,frills,green_dress,green_eyes,hat,heterochromia,lolita_fashion,long_hair,long_sleeves,red_eyes,ribbon,simple_background,solo,twin_drills,twintails,very_long_hair,|||,rating_g

Tags are converted from metadata to the following format using these commands:

  • Pure tags converted from Danbooru metadata to plain text
  • illustration is added to all tags
  • The separator ||| is added to the beginning and end of the tag text, which can be used by specifying it in sd-scripts as follows: --keep_tokens_separator="|||"
  • Order | "Artist name → Work name → Character name → illustration,||| → Tag text → ||| → Rating"
Conversion Process

Tags are converted from metadata to plain text using data-kitchen/metadata_converter_danbooru.py and saved in the tag folder. A sample command for the conversion process is in the following format. For specific details about the command, please check the data-kitchen repository.

python metadata_converter_danbooru.py --metadata_order "tag_string_artist" "tag_string_copyright" "tag_string_character" "tag_string_general" "rating" --dir "H:\dataset\metadata\Danbooru\images_by_15000id_01" --save_dir "H:\dataset\tag\Danbooru\images_by_15000id_01" --insert_custom_text 3 "`illustration,|||`" 4 "|||" --recursive --preserve_own_folder --preserve_structure --gc_disable --by_folder

Captions

Currently, captions are not included for the following reasons:

  • There are limitations in computer and other resources for local processing
  • There are no open-source VLM models with good Japanese performance

CogVLM and Mini-CPM are excellent, but they seem to understand almost only English and can't perform multilingual OCR. GPT4o is truly perfect but it's paid.

If you want to know what this means, check it out below 🥺

👁‍🗨VLM Test Result Sample (Anime illustration)

▼Test01: OCR

Prompt for VLM

Please write a caption. It's a brief sentence that describes an image. Summarize it objectively and concisely, logically describing the main focus, actions, and context of the image. Start with the overall picture and then add specific details. Avoid personal opinions and non-essential details, and do not discuss the atmosphere of the scene or the emotions it may evoke. If there is text in the image, read it like OCR and describe it in the language it is written in (do not translate it into English unnecessarily). For background art, accurately describe objects and situations in the background. If there are no people, only describe the background. If there are characters, accurately describe features such as clothing and appearance. Summarize and describe this image in one paragraph. The base language for the description is English, but note that this does not apply to the OCR transcription function.

Image

※Japanese text: "勇気の鈴が りんりんりーん ♪ ふしぎな冒険 るんるんるーん ♪"


CogVLM2

A young woman with short, dark hair and red eyes is captured in a moment of singing into a microphone. She wears a traditional kimono adorned with floral patterns, suggesting a cultural or celebratory event. The background is simple, with soft, warm colors and Japanese text, which may indicate the lyrics or a poetic context for her performance.

→🤔

GLM 4v 9B
cuuupid/glm-4v-9b – Run with an API on Replicate

The image depicts an animated character with short, dark blue hair and red eyes holding a microphone, suggesting they are singing or speaking. The character is dressed in a traditional Japanese kimono with a floral pattern in shades of blue and purple. The background is plain white with Japanese text in a casual script, likely lyrics or a poem, to the right of the character

→🤔

GPT4o

The image depicts an anime-style character with short dark blue hair and red eyes, dressed in a traditional blue floral kimono. The character is holding a microphone and appears to be singing. Surrounding the character, there is Japanese text: "勇気の鈴が りんりんりーん ♪ ふしぎな冒険 るんるんるーん ♪".

→💯🎉😭🎉💯

なんのキャラクターか分かりますか?

ChatGPT
はい、このキャラクターは『アイドルマスター シャイニーカラーズ』に登場する杜野凛世(もりの りんぜ)です。彼女は283プロダクションに所属するアイドルの一人で、静かでおしとやかな性格が特徴です。

→💯🎉😭🎉💯


▼Test02: Understanding the characters

CogVLM2:EN

In a library setting, a young woman with short blue hair and glasses is engrossed in reading a green book. Beside her, a young woman with long brown hair tied in a ponytail leans in, her hand resting on the other woman's head, possibly in a gesture of comfort or to draw attention to something in the book.

→🤔

GPT4o

The image depicts two characters from the anime "Sailor Moon." On the left is Makoto Kino (Sailor Jupiter), with long brown hair tied in a ponytail and green eyes, wearing a school uniform with a green collar and lacing detail. She is resting her head on one hand and using her other hand to pat the head of Ami Mizuno (Sailor Mercury), who has short blue hair and is wearing glasses. Ami is reading a green book and also dressed in a school uniform with a blue collar. The background features bookshelves filled with colorful books.

→💯🎉😭🎉💯

json

The json folder contains training metadata json files that link tags and images.

Relative Path

The Json format with relative paths is as follows:

{
  "Danbooru\\images_by_15000id_01\\id_1__15000\\danbooru_1_d34e4cf0a437a5d65f8e82b7bcd02606.webp": {
    "tags": "kyogoku_shin,to_heart_(series),to_heart_2,kousaka_tamaki,illustration,|||,1girl,2000s_(style),white_thighhighs,|||,rating_s"
  },
  "Danbooru\\images_by_15000id_01\\id_1__15000\\danbooru_2_710fd9cba4ef37260f9152ffa9d154d8.webp": {
    "tags": "nakamura_hisashi,cardcaptor_sakura,comic_party,leaf_(studio),to_heart_(series),to_heart_2,trigun,card_master_peach,haga_reiko,kuhonbutsu_taishi,sendou_kazuki,takase_mizuki,yoshio_(leaf),yuzuhara_konomi,illustration,|||,2boys,2girls,ahoge,,|||,rating_s"
  }
}
Making dataset images readable with relative paths

⚠ Currently, sd-scripts does not read Json written with relative paths. The code needs to be modified as follows:

To modify the train_util.py script to correctly read the dataset based on relative paths, you need to modify the train_util.py script as follows. Specifically, when setting abs_path, add a process to convert the relative path to an absolute path, considering that the relative path is relative to subset.image_dir when using os.path.exists. This allows the script to correctly reference files in the specified dataset directory without depending on where the script is located.

Before modification:

                if os.path.exists(image_key):
                    abs_path = image_key
                else:
                    paths = glob_images(subset.image_dir, image_key)
                    if len(paths) > 0:
                        abs_path = paths[0]

After modification:

                # Combine paths to convert relative path to absolute path
                potential_path = os.path.join(subset.image_dir, image_key)
                if os.path.exists(potential_path):
                    abs_path = potential_path
                else:
                    # Use glob_images to find matching files in the directory
                    paths = glob_images(subset.image_dir, image_key)
                    if len(paths) > 0:
                        abs_path = paths[0]

With this change, if image_key is a relative path from subset.image_dir, it converts the path to an absolute path based on subset.image_dir and checks if it exists. Only if image_key doesn't exist directly, it uses the glob_images function to find matching files. This allows the input relative paths to function and correctly load the dataset.

Absolute Path

Currently, it seems that sd-scripts can correctly read images with absolute paths without modifying the code.
Therefore, I've also included Json written with absolute paths. The format is as follows:

{
  "H:\\Resources\\Resources_AI\\__Dataset\\forLeaningImages\\__Danbooru\\__BooruDiffusion\\dataset\\image\\Danbooru\\images_by_15000id_01\\id_1__15000\\danbooru_1_d34e4cf0a437a5d65f8e82b7bcd02606.webp": {
    "tags": "kyogoku_shin,to_heart_(series),to_heart_2,kousaka_tamaki,illustration,|||,1girl,2000s_(style),white_thighhighs,|||,rating_s"
  }
}

However, the paths listed are from the local Windows environment at the time of dataset construction and are not useful, so they need to be replaced as appropriate. For example, if you're placing it in a cloud environment (like Runpod), you'll need to replace it as follows:

  • Replace from: H:\\Resources\\Resources_AI\\__Dataset\\forLeaningImages\\__Danbooru\\__BooruDiffusion\\dataset\\image
  • Replace to: \\workspace\\__MyFolder\\image
Sample Command for Conversion Process

The sample command for the conversion process is in the following format. For specific details about the command, please check the data-kitchen repository.

python metadata_merger.py --dir_base "H:\dataset\Danbooru\image\images_by_15000id_01\id_1__15000" --dir_append_data "H:\dataset\Danbooru\tag\images_by_15000id_01\id_1__15000" --dir_save_json "H:\dataset\Danbooru\json\datasets_metadata.json" --append_data_key tags --save_full_path
Editing Method

The json for the dataset is extremely large, with the largest having 20 million lines and 4.2 billion characters of text, so please use a decent text editor when editing.

  • Recommended: Notepad++
  • Not recommended: VSCODE, EmEditor Free, Notepad, etc.

Usage

Download

I recommend using huggingface-cli for downloading. Please install huggingface-cli in advance so that it can be used.

pip install huggingface-hub

Download Everything

To download this entire dataset, execute the following:
If you're asked to log in to huggingface, enter your huggingface access token. If you don't have a huggingface access token, create one on huggingface.

huggingface-cli download WarriorMama777/PureDanbooru --repo-type dataset --local-dir "<download_directory_path>"

It's also possible with git, but not recommended as the total download size becomes bloated.

git lfs clone https://huggingface.co/WarriorMama777/PureDanbooru

Download Specific Directories

To download specific directories, use the following command:

huggingface-cli download WarriorMama777/PureDanbooru --repo-type dataset --local-dir "<download_directory_path>" --include <directory_to_download>
  • <repo_id> is the ID of the repository you want to download (e.g., username/model_name)
  • <repo_type> is the type of repository (model, dataset, or space)
  • <download_directory_path> is the directory path where you want to save the downloaded files
  • <directory_to_download> is the path of the directory you want to download within the repository

How to Decompress

The dataset is compressed into about 130 split tar files.
There are various methods to decompress tar files, but I've provided below a decompression method using the compression/decompression script from data-kitchen. By specifying .tar.001, it automatically recognizes the split compressed files and decompresses them.
For specific details about the command, please check the data-kitchen repository.

python packer.py --unpack --dir "./dataset_danbooru.tar.001"

OPTION

  • --dir_save "<unpack_directory_path>"

Usage Example

When actually using sd-scripts for training, it would be like this:
The following assumes that you've created a __MyFolder directory in workspace and downloaded and decompressed PureDanbooru there.
However, there's also a method using toml, so please research that on your own if you prefer.

accelerate launch --num_processes=4 --multi_gpu --num_machines=1 --gpu_ids=0,1,2,3 sdxl_train.py --pretrained_model_name_or_path "/workspace/stable-diffusion-webui/models/Stable-diffusion/sdxl.safetensors" --in_json "/workspace/__MyFolder/json/datasets_metadata_danbooru_images_by_15000id_01-02_hiddentag_relative-path.json" --train_data_dir "/workspace/__MyFolder/image" --output_dir "/workspace/__MyFolder/model" --precision "float" --save_precision "float" --mixed_precision "fp16" --xformers --gradient_checkpointing --enable_bucket --save_model_as "safetensors" --resolution 1024 --train_batch_size 16 --max_train_epochs 20 --save_every_n_epochs 2 --optimizer_type "prodigy" --learning_rate 1 --lr_scheduler_num_cycles 5 --lr_scheduler "cosine" --output_name "Finetuning_SDXL_PureDanbooru_v1_prodigy" --max_token_length 225 --shuffle_caption --seed 42 --logging_dir "/workspace/__MyFolder/log" --log_prefix=Finetuning_SDXL_PureDanbooru_v1_prodigy --fp8_base --optimizer_args "d_coef=0.8" "decouple=True" "weight_decay=0.01"  "use_bias_correction=True" "safeguard_warmup=True" "betas=0.9,0.99" "eps=1e-08" --keep_tokens_separator="|||" --noise_offset 0.05 --noise_offset_random_strength

Dataset structure

Directory structure

.
├── alphachannel
│   └── Danbooru
│       ├── images_by_15000id_01
│       │   ├── id_1__15000
│       │   ├── ~~~~~~~~~~~~
│       │   └── id_3330001__3345000
│       └── images_by_15000id_02
│           ├── id_3345001__3360000
│           ├── ~~~~~~~~~~~~
│           └── id_7425001__7440000
├── duplicate_image
│   ├── Danbooru
│   │   ├── images_by_15000id_01
│   │   │   ├── id_1__15000
│   │   │   ├── ~~~~~~~~~~~~
│   │   │   └── id_3330001__3345000
│   │   └── images_by_15000id_02
│   │       ├── id_3345001__3360000
│   │       ├── ~~~~~~~~~~~~
│   │       └── id_7425001__7440000
│   └── Gelbooru
│       ├── hidden_tag_01
│       ├── hidden_tag_02
│       └── hidden_tag_03
├── image
│   ├── Danbooru
│   │   ├── images_by_15000id_01
│   │   │   ├── id_1__15000
│   │   │   ├── ~~~~~~~~~~~~
│   │   │   └── id_3330001__3345000
│   │   └── images_by_15000id_02
│   │       ├── id_3345001__3360000
│   │       ├── ~~~~~~~~~~~~
│   │       └── id_7425001__7440000
│   └── Gelbooru
├── json
│   ├── datasets_metadata_danbooru_images_by_15000id_01-02_full-path.json
│   ├── datasets_metadata_danbooru_images_by_15000id_01-02_hiddentag_full-path.json
│   ├── datasets_metadata_danbooru_images_by_15000id_01-02_hiddentag_relative-path.json
│   └── datasets_metadata_danbooru_images_by_15000id_01-02_relative-path.json
├── metadata
│   ├── Danbooru
│   │   ├── images_by_15000id_01
│   │   │   ├── id_1__15000
│   │   │   ├── ~~~~~~~~~~~~
│   │   │   └── id_3330001__3345000
│   │   └── images_by_15000id_02
│   │       ├── id_3345001__3360000
│   │       ├──~~~~~~~~~~~~
│   │       └── id_7425001__7440000
│   └── Gelbooru
│       ├── hidden_tag_01
│       ├── hidden_tag_02
│       └── hidden_tag_03
└── tag
    ├── Danbooru
    │   ├── images_by_15000id_01
    │   │   ├── id_1__15000
    │   │   ├──~~~~~~~~~~~~
    │   │   └── id_3330001__3345000
    │   └── images_by_15000id_02
    │       ├── id_3345001__3360000
    │       ├── ~~~~~~~~~~~~
    │       └── id_7425001__7440000
    └── Gelbooru
        ├── hidden_tag_01
        ├── hidden_tag_02
        └── hidden_tag_03

Data Format

This is a simple dataset that just uploads tar-compressed data.
SQL🥃? Datasets🤗?? Dask🍡??? Croissant🥐??????? Parquet🤯?????????
I don't understand any of it.

License

creativeml-openrail-m

Citation

While not mandatory, if you wish to cite this dataset, you could use the following format:

WarriorMama777. (2024). "PureDanbooru" (Version 1.0). Hugging Face. https://huggingface.co/datasets/WarriorMama777/PureDanbooru

Acknowledgements

I'm grateful to Danbooru and the users who have diligently tagged on Danbooru over the years. I refrain from unilaterally sending thanks to the artists, but I respect each of their works.

Contact Information

Please use the discussion section of this huggingface repository.

Update History

Version Date Changes
v1.0.0 2024-07-07 Initial release

Disclaimer

※To prevent errors through translation, it is posted in the original text.

READ MORE: Disclaimer (JPN) 1. AIの学習等における機械学習時の著作物の利用については、日本国著作権法第三十条の四第二項「情報解析(多数の著作物その他の大量の情報から、当該情報を構成する言語、音、影像その他の要素に係る情報を抽出し、比較、分類その他の解析を行うことをいう。第四十七条の五第一項第二号において同じ。)の用に供する場合」を参照し行っております。 [著作権法 | e-Gov法令検索: デジタル庁](https://elaws.e-gov.go.jp/document?lawid=345AC0000000048#Mp-At_30) 2. 著作物の掲載にあたっては、私的使用や研究目的である場合、商品化の資料として使用する場合(但し、商品化されるものが著作物の主たる利用目的となる場合にはこの限りではない)、批評・論評・報道での利用である場合、パロディや二次創作としてオリジナリティを発揮する場合等の例外的な著作物の使用が認められるケースに該当すると考え掲載しています。 3. 当該学習データセットは、わいせつな視覚コンテンツを直ちに表示されないよう配慮されており、学習データセットによる投稿が公共の場においてわいせつな内容を表示することを意図するものではありません。 なお、著作権者の意に反する利用や不当な利益を得る利用は避けるべきであり、著作権保有者によって正当な理由をもって当該データセットの関係する過半数の関係者から申し立てされた場合、掲載は速やかに中止されることが保証されます。 また本人は、使用する機械学習データセット中に、著作権者の権利を十分に尊重していないと評価され得る可能性を持つ情報源からのデータが含まれ得ることを認識しており、開発者等関係者が依拠すべき法律の整備等の動向について適切な監視と管理の義務を負っています。 本人は、法律や倫理に反する行為を意図しておらず、著作権者を含むイラストレーター及びアーティスト等の権利を尊重し、人工知能の開発を進めることに努めます。
Downloads last month
2,554