diff --git a/.gitattributes b/.gitattributes index aa6595a8e277c0664a5a74187917ac6f62830b22..43f8d1e56fc46b2a09e53f65fe5b0eab56d1ca50 100644 --- a/.gitattributes +++ b/.gitattributes @@ -266,3 +266,24 @@ Jaune[[:space:]]lore/858927436157436889.jpg filter=lfs diff=lfs merge=lfs -text Jaune[[:space:]]lore/858932014592617696.jpg filter=lfs diff=lfs merge=lfs -text Jaune[[:space:]]lore/892d58c4-a7a5-47d9-a572-d642dd2bb2f7.jpeg filter=lfs diff=lfs merge=lfs -text Jaune[[:space:]]lore/e3263625-a500-4044-b7c8-b633119fa6f6.jpeg filter=lfs diff=lfs merge=lfs -text +Lora/Gwen_Tennyson_Ben_10_LoRA_Illustrious_Edition.preview.png filter=lfs diff=lfs merge=lfs -text +Lora/H1_hhh_1.0_style-ILXL.preview.png filter=lfs diff=lfs merge=lfs -text +Lora/JauneArcIL.jpg filter=lfs diff=lfs merge=lfs -text +Lora/Krekkov_Style-000009.preview.png filter=lfs diff=lfs merge=lfs -text +Lora/Nami_shocked_eye_IL_v1-000012.preview.png filter=lfs diff=lfs merge=lfs -text +Lora/SSAMBAteaIL-style.preview.png filter=lfs diff=lfs merge=lfs -text +Lora/Sans.preview.png filter=lfs diff=lfs merge=lfs -text +Lora/Shexyo_-_Illustrious_2025_style-000014.preview.png filter=lfs diff=lfs merge=lfs -text +Lora/Ssambatea[[:space:]]IL.preview.png filter=lfs diff=lfs merge=lfs -text +Lora/Xipa.preview.png filter=lfs diff=lfs merge=lfs -text +Lora/backlighting_il_2_d16.preview.png filter=lfs diff=lfs merge=lfs -text +Lora/fixed_point_v2.preview.png filter=lfs diff=lfs merge=lfs -text +Lora/gwen.preview.png filter=lfs diff=lfs merge=lfs -text +Lora/gwentenE28090illus13.QCtZ.preview.png filter=lfs diff=lfs merge=lfs -text +Lora/hinaIDidSurgeryAlongSlider_x215c.preview.png filter=lfs diff=lfs merge=lfs -text +Lora/illustriousXLv01_stabilizer_v1.121.preview.png filter=lfs diff=lfs merge=lfs -text +Lora/illustriousXLv11_stabilizer_v1.113.preview.png filter=lfs diff=lfs merge=lfs -text +Lora/in-dark.preview.png filter=lfs diff=lfs merge=lfs -text +Lora/krekkov-ByChiAi_.preview.png filter=lfs diff=lfs merge=lfs -text +Lora/theodyss.preview.png filter=lfs diff=lfs merge=lfs -text +Lora/touching_grass_v0.2.preview.png filter=lfs diff=lfs merge=lfs -text diff --git a/Lora/2Dfy DarkSky XL_v1.1 test.preview.png b/Lora/2Dfy DarkSky XL_v1.1 test.preview.png index 212668fd8e0b1d2344f3631e85bc95aac15bf593..ace13a8b45a99ebcbb5e43ebf6975db274cb1923 100644 --- a/Lora/2Dfy DarkSky XL_v1.1 test.preview.png +++ b/Lora/2Dfy DarkSky XL_v1.1 test.preview.png @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:275cb974481b8b902fb14fb50d14d923513a408392b6b120a63660e34e60ab14 -size 191086 +oid sha256:d5638c285f1a04651894e25713c55971c3dd68d1a291b285b6fee9bd943c30ec +size 175358 diff --git a/Lora/DC_v1_NAI-XL.preview.png b/Lora/DC_v1_NAI-XL.preview.png index f76e22645d9b6db090f46566df1be2a4a9cbe53c..0e076953fac9e021d06ffb9050f7a3bbfd9ca02d 100644 --- a/Lora/DC_v1_NAI-XL.preview.png +++ b/Lora/DC_v1_NAI-XL.preview.png @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:5d66295f25e7cd6f3d859d9ff3ed245f108f79611f0e415fc56b9d34a662eaeb -size 2672162 +oid sha256:df0e509dfbc086773224d2f9f78e2f7061f78a45b79af41347bbdbafbf105dbf +size 195053 diff --git a/Lora/Darky_Artstyle-000009.json b/Lora/Darky_Artstyle-000009.json new file mode 100644 index 0000000000000000000000000000000000000000..0e632a267e762224cbd5366177830c6bd8979883 --- /dev/null +++ b/Lora/Darky_Artstyle-000009.json @@ -0,0 +1,8 @@ +{ + "sha256": "B2DD5C77E9920CE3C107D8F86683053B00F97D5F712981129AB9B45D51D4B81D", + "modelId": 1238592, + "modelVersionId": 1395871, + "activation text": "", + "description": "A first attempt at recreating Dark artstyle", + "sd version": "Other" +} \ No newline at end of file diff --git a/Lora/Darky_Artstyle-000009.preview.png b/Lora/Darky_Artstyle-000009.preview.png new file mode 100644 index 0000000000000000000000000000000000000000..e2c21db717ff77759ec35c5c5e519326bb966e92 Binary files /dev/null and b/Lora/Darky_Artstyle-000009.preview.png differ diff --git a/Lora/Darky_Artstyle-000009.safetensors b/Lora/Darky_Artstyle-000009.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..07c13ec3f02dc41856828ba4b035b92a3636f072 --- /dev/null +++ b/Lora/Darky_Artstyle-000009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2dd5c77e9920ce3c107d8f86683053b00f97d5f712981129ab9b45d51d4b81d +size 228466948 diff --git a/Lora/Dishwasher1910_Style.safetensors b/Lora/Dishwasher1910_Style.safetensors index 90a952bf81ff95d020fd1eaa67457a76484ffade..096c4ed72aa52d51784c86df526a2e99e6ccc234 100644 --- a/Lora/Dishwasher1910_Style.safetensors +++ b/Lora/Dishwasher1910_Style.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7c112ab279fbfd32f5b62b742cf43ca52094a9e772ef5efded45fe39cdefd991 -size 228455716 +oid sha256:e2a887747a41b95c1e95f5a80e256c12968dbf12db1851ed348f502c24fa5344 +size 228486732 diff --git a/Lora/Gwen_Tennyson_Ben_10_LoRA_Illustrious_Edition.json b/Lora/Gwen_Tennyson_Ben_10_LoRA_Illustrious_Edition.json new file mode 100644 index 0000000000000000000000000000000000000000..680a6297ca1da350d64f913e9ea430d544cc11ed --- /dev/null +++ b/Lora/Gwen_Tennyson_Ben_10_LoRA_Illustrious_Edition.json @@ -0,0 +1,8 @@ +{ + "sha256": "BBA09033C25F2EA036703304F4C10338FA28BE64932B3664FCEE2A943205088F", + "modelId": 1484397, + "modelVersionId": 1679103, + "activation text": "gwentennyson, orange hair, short hair, green eyes, earrings, blue shirt, hairclip, white pants", + "description": "IMPORTANT: This LoRA is trained as a Epsilon-Pred model and is fully compatible with other V-Pred and Epsilon-Pred models. For the best results, make sure to use it with a V-Pred and Epsilon-Pred checkpoint.Trigger words:gwentennyson, orange hair, short hair, green eyes, earringsOutfit:blue shirt, hairclip, white pantsTested and used with WAI-SHUFFLE-NOOB:https://civitai.com/models/989367?modelVersionId=1202076 https://civitai.com/models/989367?modelVersionId=1202076For on-site generations, use my Tensor Art page: https://tensor.art/u/830771749061779884 https://tensor.art/u/830771749061779884Order a commission here!https://ko-fi.com/c/38aa4a973d https://ko-fi.com/c/38aa4a973dSupport my work by buying me a ko-fi:https://ko-fi.com/waifu_chef https://ko-fi.com/waifu_chef", + "sd version": "Other" +} \ No newline at end of file diff --git a/Lora/Gwen_Tennyson_Ben_10_LoRA_Illustrious_Edition.preview.png b/Lora/Gwen_Tennyson_Ben_10_LoRA_Illustrious_Edition.preview.png new file mode 100644 index 0000000000000000000000000000000000000000..5e2a29cdd5865a16d8a16aa2e665a55e265eb75c --- /dev/null +++ b/Lora/Gwen_Tennyson_Ben_10_LoRA_Illustrious_Edition.preview.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34506d0333b9c697cc140f9e2df2aa5d26d281dde5d6c7dabcd91ce77ea7c556 +size 198387 diff --git a/Lora/Gwen_Tennyson_Ben_10_LoRA_Illustrious_Edition.safetensors b/Lora/Gwen_Tennyson_Ben_10_LoRA_Illustrious_Edition.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ac5e7bd0fdd6ed78f8c3b5646ed568e9ccc25853 --- /dev/null +++ b/Lora/Gwen_Tennyson_Ben_10_LoRA_Illustrious_Edition.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bba09033c25f2ea036703304f4c10338fa28be64932b3664fcee2a943205088f +size 228450708 diff --git a/Lora/H1_hhh_1.0_style-ILXL.json b/Lora/H1_hhh_1.0_style-ILXL.json new file mode 100644 index 0000000000000000000000000000000000000000..2d38189d71cda4b548a85329583f2b81894536a6 --- /dev/null +++ b/Lora/H1_hhh_1.0_style-ILXL.json @@ -0,0 +1,8 @@ +{ + "sha256": "961B5E91F62C0B160D993CC4703BF8510B7A15554F9D1D653361CC7F7603DD12", + "modelId": 1501233, + "modelVersionId": 1698243, + "activation text": "", + "description": "Doesn't require any trigger words.Strength : 1.0", + "sd version": "Other" +} \ No newline at end of file diff --git a/Lora/H1_hhh_1.0_style-ILXL.preview.png b/Lora/H1_hhh_1.0_style-ILXL.preview.png new file mode 100644 index 0000000000000000000000000000000000000000..d0c3b0e65f0fdbaf224b456b3dab91902473f7d8 --- /dev/null +++ b/Lora/H1_hhh_1.0_style-ILXL.preview.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5f1fb6c6d4beca72ae7422ca12d20f16e93243e48562ce80cb6398f679b7b94 +size 304666 diff --git a/Lora/H1_hhh_1.0_style-ILXL.safetensors b/Lora/H1_hhh_1.0_style-ILXL.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..db2ccbe22377f8e4ff068605ff68d94065b9cd44 --- /dev/null +++ b/Lora/H1_hhh_1.0_style-ILXL.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:961b5e91f62c0b160d993cc4703bf8510b7a15554f9d1d653361cc7f7603dd12 +size 456499732 diff --git a/Lora/JauneArcIL.jpg b/Lora/JauneArcIL.jpg new file mode 100644 index 0000000000000000000000000000000000000000..21fc0a139d2dbc1f2fe9dcde3ce9ccb525b9ae62 --- /dev/null +++ b/Lora/JauneArcIL.jpg @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3440a5e18885fdd0a14b8f9945a44a8fac9d7fb1691f4748f2a81066984fa2a +size 1983048 diff --git a/Lora/JauneArcIL.json b/Lora/JauneArcIL.json new file mode 100644 index 0000000000000000000000000000000000000000..3a0326f1b18653ac34a9cc4079591cf5c6dfffe3 --- /dev/null +++ b/Lora/JauneArcIL.json @@ -0,0 +1,8 @@ +{ + "sha256": "D10CD7BDA9F946635038E518D66BFD6179BD4DF56FE1D6CAD25F400C14C03784", + "modelId": 560125, + "modelVersionId": 1467632, + "activation text": "imtdjaunearcil, 1boy, male, masculine, fit body, blonde hair, blue hair, short hair, armor, gloves, pants, belt, hood, fingerless gloves, brown gloves, jeans, denim, hoodie, hood down, shoulder armor, shoulders pads, boots", + "description": "Trigger: pyramidheadSDXLStrenght: 1 or 0.8Use Adetailer", + "sd version": "Other" +} \ No newline at end of file diff --git a/Lora/JauneArcIL.safetensors b/Lora/JauneArcIL.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a1a08ba73fc8b98d7ce081e07f17ce680ec8b676 --- /dev/null +++ b/Lora/JauneArcIL.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b06d2ad22685ed1365cfd6a42a278ec4d3483ed46e5a016c2c6fc8eb41fde7e +size 228461996 diff --git a/Lora/KarasuChanIllustriousXL_byKonan.json b/Lora/KarasuChanIllustriousXL_byKonan.json index 87090d638b26aa45faae3c2cbf10fdf856a03935..d49382f6f167e5c06e1fa8c0d5c1672b40a58fd1 100644 --- a/Lora/KarasuChanIllustriousXL_byKonan.json +++ b/Lora/KarasuChanIllustriousXL_byKonan.json @@ -3,6 +3,6 @@ "modelId": 813431, "modelVersionId": 909591, "activation text": "karasuchan, greyscale with colored background, hatching \\(texture\\), monochrome", - "description": "Illustrious is a fully trained SDXL model. This LoRA is intended to be used with Illustrious models. It may not work with other SDXL/PonyXL ressources.Trained on Illustrious-XL-v0.1 https://civitai.com/models/795765/illustrious-xl with 58 pictures.Best result with weight between : 0.8-1.Main prompts : karasuchanStyle prompts : greyscale with colored background, hatching \\(texture\\), monochromeReviews are really appreciated, i love to see the community use my work, that's why I share it.If you like my work, you can tip me here. https://ko-fi.com/konan49773Got a specific request ? I'm open for commission on my kofi https://ko-fi.com/konan49773/commissions or fiverr gig https://www.fiverr.com/konanai/create-lora-model-for-you *! If you provide enough data, OCs are acceptedIf you want to get updates on my projects as they go, you can follow me on X https://twitter.com/Konan92_AI", + "description": "Trained on Illustrious-XL-v0.1 https://civitai.com/models/795765/illustrious-xl with 58 pictures.Best result with weight between : 0.8-1.Main prompts : karasuchanStyle prompts : greyscale with colored background, hatching \\(texture\\), monochromeReviews are really appreciated, i love to see the community use my work, that's why I share it.If you like my work, you can tip me here. https://ko-fi.com/konan49773Got a specific request ? I'm open for commission on my kofi https://ko-fi.com/konan49773/commissions or fiverr gig https://www.fiverr.com/konanai/create-lora-model-for-you *! If you provide enough data, OCs are acceptedIf you want to get updates on my projects as they go, you can follow me on X https://twitter.com/Konan92_AI", "sd version": "Other" } \ No newline at end of file diff --git a/Lora/Krekkov_Style-000009.json b/Lora/Krekkov_Style-000009.json new file mode 100644 index 0000000000000000000000000000000000000000..29eac305f2f5b3764df19e33a18ef42274ecc6a7 --- /dev/null +++ b/Lora/Krekkov_Style-000009.json @@ -0,0 +1,8 @@ +{ + "sha256": "C7CCC5C328EA61776B4FEB512B9981A3F6FBBEC69FFD6134A10217CFC94F7B8F", + "modelId": 1481641, + "modelVersionId": 1675917, + "activation text": "", + "description": "Style of the artist \"Krekkov\"", + "sd version": "Other" +} \ No newline at end of file diff --git a/Lora/Krekkov_Style-000009.preview.png b/Lora/Krekkov_Style-000009.preview.png new file mode 100644 index 0000000000000000000000000000000000000000..f7b5bef903dedbed9614e48dcd58b49acfcb1ee9 --- /dev/null +++ b/Lora/Krekkov_Style-000009.preview.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f099ed33501af2a9ea3e0c9639cb5b9291dcb2f15a363f966f488ea628a5cdf3 +size 5569686 diff --git a/Lora/Krekkov_Style-000009.safetensors b/Lora/Krekkov_Style-000009.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7d410ddb7a89c08ce397f55f0344be3061475d74 --- /dev/null +++ b/Lora/Krekkov_Style-000009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7ccc5c328ea61776b4feb512b9981a3f6fbbec69ffd6134a10217cfc94f7b8f +size 228464964 diff --git a/Lora/Nami_shocked_eye_IL_v1-000012.json b/Lora/Nami_shocked_eye_IL_v1-000012.json new file mode 100644 index 0000000000000000000000000000000000000000..f3ad44b13ed17adf660da9e2efb404782ed7d370 --- /dev/null +++ b/Lora/Nami_shocked_eye_IL_v1-000012.json @@ -0,0 +1,8 @@ +{ + "sha256": "C1B3C39A3BCB5CEB5DD4068F386DD861FCCCC6303FE3EF555E0C2EF3A675DCDF", + "modelId": 1465951, + "modelVersionId": 1657970, + "activation text": "circular pupils, black pupils, wide eyes, simple eyes, no eye highlights, , scared, , surprised, , angry, , shaded face, , anime coloring", + "description": "\u30ef\u30f3\u30d4\u30fc\u30b9\u3067\u898b\u304b\u3051\u308b\u30d7\u30ec\u30a4\u30b9\u30c6\u30fc\u30b7\u30e7\u30f3\u306e\u30dc\u30bf\u30f3\u307f\u305f\u3044\u306a\u602f\u3048\u305f\u76ee\u3067\u3059\u3002\u30a2\u30cb\u30e1\u7cfb\u306e\u30c1\u30a7\u30c3\u30af\u30dd\u30a4\u30f3\u30c8\u3084\u30b9\u30bf\u30a4\u30ebLoRA\u3068\u306e\u76f8\u6027\u304c\u3044\u3044\u3067\u3059\u3002\u30d7\u30ed\u30f3\u30d7\u30c8\u7b49\u306f\u4ee5\u4e0b\u3092\u53c2\u7167\u3057\u3066\u304f\u3060\u3055\u3044\u3002Shocked eyes in One Piece like a button on a PlayStation.It goes well with anime-style checkpoints and style LoRAs.Strength: around 1Trigger Words: circular pupils, black pupils, wide eyes, simple eyes, no eye highlights, scared,Useful Prompts: angry/surprised, shaded face, anime coloringThank you.", + "sd version": "Other" +} \ No newline at end of file diff --git a/Lora/Nami_shocked_eye_IL_v1-000012.preview.png b/Lora/Nami_shocked_eye_IL_v1-000012.preview.png new file mode 100644 index 0000000000000000000000000000000000000000..0d52d20d622eb15203fdb27035e05985135d158f --- /dev/null +++ b/Lora/Nami_shocked_eye_IL_v1-000012.preview.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:141f1231b1f34145c417758360b377b346fbd0997e41b4270004e1247ea856ea +size 3004804 diff --git a/Lora/Nami_shocked_eye_IL_v1-000012.safetensors b/Lora/Nami_shocked_eye_IL_v1-000012.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..89fd0cad5d9879d625d60e620282acf18bd6518e --- /dev/null +++ b/Lora/Nami_shocked_eye_IL_v1-000012.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1b3c39a3bcb5ceb5dd4068f386dd861fcccc6303fe3ef555e0c2ef3a675dcdf +size 57430444 diff --git a/Lora/Nayuta IL.json b/Lora/Nayuta IL.json new file mode 100644 index 0000000000000000000000000000000000000000..959ae383e39e976cdfbb3beacc9e041bfc803a4d --- /dev/null +++ b/Lora/Nayuta IL.json @@ -0,0 +1,8 @@ +{ + "sha256": "4E61704E5065F8A7E2B9F511A644B5912DDBDDDDEA02DA60885ED76C34259618", + "modelId": 1294000, + "modelVersionId": 1460363, + "activation text": "nayuta \\(chainsaw man\\), black hair, single braid, medium hair, hair over one eye, ringed eyes, yellow eyes, , red sweater, turtleneck, long sleeves, black pants", + "description": "Strenght: 1 - 0.8Use Adetailer", + "sd version": "Other" +} \ No newline at end of file diff --git a/Lora/Nayuta IL.preview.png b/Lora/Nayuta IL.preview.png new file mode 100644 index 0000000000000000000000000000000000000000..2cae15d159b14dc4f30a90cf3bc15a28d0d0139c Binary files /dev/null and b/Lora/Nayuta IL.preview.png differ diff --git a/Lora/Nayuta IL.safetensors b/Lora/Nayuta IL.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2534580022a441fdab277edd3c0b11ba78ee296f --- /dev/null +++ b/Lora/Nayuta IL.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e61704e5065f8a7e2b9f511a644b5912ddbddddea02da60885ed76c34259618 +size 228473100 diff --git a/Lora/Nayuta_Illustrious.safetensors b/Lora/Nayuta_Illustrious.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f51f934ef27ea2b779ab6146b1cd84fe0461b016 --- /dev/null +++ b/Lora/Nayuta_Illustrious.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9280c33077750890f80c6bde53327c9fe045047b7c06ffb93e24316694b67173 +size 202695244 diff --git a/Lora/SSAMBAteaIL-style.json b/Lora/SSAMBAteaIL-style.json new file mode 100644 index 0000000000000000000000000000000000000000..5c6c9cf7614118908f5faa0b5500fd2923b18d33 --- /dev/null +++ b/Lora/SSAMBAteaIL-style.json @@ -0,0 +1,8 @@ +{ + "sha256": "F5E1113C8D53FACA5829EF2771FE559CF403CEA4239BC4DE911DAE3E433724D0", + "modelId": 1464383, + "modelVersionId": 1668825, + "activation text": "ssambatea", + "description": "Recommended for use on weights 0.8-1Triggered word- ssambateaWill remove if requested", + "sd version": "Other" +} \ No newline at end of file diff --git a/Lora/SSAMBAteaIL-style.preview.png b/Lora/SSAMBAteaIL-style.preview.png new file mode 100644 index 0000000000000000000000000000000000000000..4031239a99f7dde804cbd351c78ba45ab148d369 --- /dev/null +++ b/Lora/SSAMBAteaIL-style.preview.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcd33fed3a80f0024bdcb5904d9f12d0050677b03c27a835b29abf708b2fb91b +size 222243 diff --git a/Lora/SSAMBAteaIL-style.safetensors b/Lora/SSAMBAteaIL-style.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0d91b672b857c1cb38b0d4600e1495f4dbd6b376 --- /dev/null +++ b/Lora/SSAMBAteaIL-style.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5e1113c8d53faca5829ef2771fe559cf403cea4239bc4de911dae3e433724d0 +size 228461900 diff --git a/Lora/Sans.json b/Lora/Sans.json new file mode 100644 index 0000000000000000000000000000000000000000..f11b52377cb6d0b8450293aace743a8d457cb50e --- /dev/null +++ b/Lora/Sans.json @@ -0,0 +1,8 @@ +{ + "sha256": "A08DBB6F8F54FD2761ECD084E8A74DAB65FCE87F4A5864333583849C3A746BE1", + "modelId": 1362276, + "modelVersionId": 1539002, + "activation text": "s4ns, skeleton, , white shirt, blue jacket, black shorts, white socks, pink slippers", + "description": "Sans from UndertaleTrigger words: s4ns, skeletonmain outfit: white shirt, blue jacket, black shorts, white socks, pink slippers,", + "sd version": "Other" +} \ No newline at end of file diff --git a/Lora/Sans.preview.png b/Lora/Sans.preview.png new file mode 100644 index 0000000000000000000000000000000000000000..63866a70bdcee169b69dae9cd7ea89173d09fe9c --- /dev/null +++ b/Lora/Sans.preview.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:050c6561b141a26c23d84e2977265eeb523f21b260268095f46b7ee6807ac9de +size 183697 diff --git a/Lora/Sans.safetensors b/Lora/Sans.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3a67845e82333e0f3bca1e8bdd1f3cb717473c44 --- /dev/null +++ b/Lora/Sans.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a08dbb6f8f54fd2761ecd084e8a74dab65fce87f4a5864333583849c3a746be1 +size 228454812 diff --git a/Lora/Shexyo_-_Illustrious_2025_style-000014.json b/Lora/Shexyo_-_Illustrious_2025_style-000014.json new file mode 100644 index 0000000000000000000000000000000000000000..a04868551218ad65b5e0c3875df722423d8f73b1 --- /dev/null +++ b/Lora/Shexyo_-_Illustrious_2025_style-000014.json @@ -0,0 +1,8 @@ +{ + "sha256": "05B85F09591DD58B5C1559A8B006A7A6F97B350E6E1ECD418BDE7D4F5108A24A", + "modelId": 1516534, + "modelVersionId": 1715751, + "activation text": "", + "description": "There are already few shexyo loras, but his style is changed, so here is another one. Trained only on new (2025) images.Made a bounty: https://civitai.com/bounties/8003/shexyo-mixplin-il-loras-test-multiple-winners https://civitai.com/bounties/8003/shexyo-mixplin-il-loras-test-multiple-winners", + "sd version": "Other" +} \ No newline at end of file diff --git a/Lora/Shexyo_-_Illustrious_2025_style-000014.preview.png b/Lora/Shexyo_-_Illustrious_2025_style-000014.preview.png new file mode 100644 index 0000000000000000000000000000000000000000..16f221387b5312a222a7da5b644efe1e87f39694 --- /dev/null +++ b/Lora/Shexyo_-_Illustrious_2025_style-000014.preview.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2391dacd1f5eda8071fcc542f62bbd434aaba6488b7ae8441c9cafb67afff8a +size 233317 diff --git a/Lora/Shexyo_-_Illustrious_2025_style-000014.safetensors b/Lora/Shexyo_-_Illustrious_2025_style-000014.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a3f83d7c6bbc349409aacd36fba59fdf2d23dc11 --- /dev/null +++ b/Lora/Shexyo_-_Illustrious_2025_style-000014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05b85f09591dd58b5c1559a8b006a7a6f97b350e6e1ecd418bde7d4f5108a24a +size 114443420 diff --git a/Lora/Ssambatea IL.json b/Lora/Ssambatea IL.json new file mode 100644 index 0000000000000000000000000000000000000000..3a30e5ca90f786cdaf3e3be746651c900f1574e0 --- /dev/null +++ b/Lora/Ssambatea IL.json @@ -0,0 +1,8 @@ +{ + "sha256": "E45E113D7B3539909898E24B1E8F952E8A1C7FAB3BD5FB8858B58AC0897ECF12", + "modelId": 1469906, + "modelVersionId": 1662568, + "activation text": "ssambstyle, monochrome, motion_lines", + "description": "If you like my work you can drop a positive review and follow me, it's free and it helps me a lot :DYou can also buy me a coffee to support me :Dhttps://ko-fi.com/shadowxart https://ko-fi.com/shadowxart-Commissions:https://ko-fi.com/shadowxart/commissions https://ko-fi.com/shadowxart/commissionsExclusive Models:https://tensor.art/u/650355879652217325/models https://tensor.art/u/650355879652217325/modelsThanks :)-Support the Artist:https://x.com/SSAMBAtea/status/1905897850153951544 https://x.com/SSAMBAtea/status/1905897850153951544-Trigger Word:ssambstyleRecommended Prompts:monochrome, motion_lines", + "sd version": "Other" +} \ No newline at end of file diff --git a/Lora/Ssambatea IL.preview.png b/Lora/Ssambatea IL.preview.png new file mode 100644 index 0000000000000000000000000000000000000000..d1f35a11b8deea20485a9d4cabbfdb78c8a4503d --- /dev/null +++ b/Lora/Ssambatea IL.preview.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81c6d2c44c83a1dd7fbbcd616389c30e750e83ca9539d564c66f87cdae378d4b +size 256474 diff --git a/Lora/Ssambatea IL.safetensors b/Lora/Ssambatea IL.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..95eb3800336d358af05d41448134acb0b0c74105 --- /dev/null +++ b/Lora/Ssambatea IL.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e45e113d7b3539909898e24b1e8f952e8a1c7fab3bd5fb8858b58ac0897ecf12 +size 228496596 diff --git a/Lora/StS_Age_Slider_Illustrious_v1.json b/Lora/StS_Age_Slider_Illustrious_v1.json index 45eafc82531ca234ae2a6de69bf6e629443034e5..97476fdc73ebe1c466f3cff7b42cf66ecda57982 100644 --- a/Lora/StS_Age_Slider_Illustrious_v1.json +++ b/Lora/StS_Age_Slider_Illustrious_v1.json @@ -3,6 +3,6 @@ "modelId": 1025710, "modelVersionId": 1150298, "activation text": "", - "description": "\ud83d\udc47\ud83d\udc40 Read me! \ud83d\udc47\ud83d\udc40This is a slider for Illustrious XL, trained on SweetMix https://civitai.com/models/18927/sweet-mix. The purpose of this slider is to allow control of the age of depicted person(s) in generated images.The SCALED version in the same LoRA but with the age representation in +/- 2 input weight instead of the non-Scaled version's +/- 5 input weight for full age representation.Do not ask me to make this LoRA available for CivitAI's on-site generator. Per CivitAI's Terms of Service, Age adjusting LoRAs can not be used with CivitAI's on-site generator. This is not something I can change. If you want to use this LoRA with an online generation service, it is also available via Tensor Art https://tensor.art/models/823220457818842920.~ How to use? ~ This is a bipolar slider LoRA. That means it supports both positive and negative input weights. General safe weighting is -5 to 5 , although you can push to +/- 6 with some oddities. No activation tag required. This LoRA is not trained for NoobAI V-Pred models.If you are using this LoRA in combination with a character LoRA, adding supporting tags can be beneficial to affect age. Since character LoRAs often have a set character age trained, it can be difficult to change that age depending on how intensely the character LoRA wants to maintain the character's \"correct\" age. To help overcome this, I suggest you use tags like aged up, aged down, petite , mature female, etc... as needed to help change the character's age. If you run into issues with using this LoRA, please feel free to send me a message on CivitAI, or leave a comment so that I can fix issues that may arise. ~ Known issues ~ At high input weights (> 5), the image subject may have male facial hair. Putting facial hair , mustache , old man , etc... in the negative prompt largely mitigates this.Very low input weights ( < 4.5) may de-saturate the image. As a temporary workaround, I recommend using a style LoRA to alleviate this. (I like this one a lot https://civitai.com/models/478058/granblue-fantasy-style-for-pony-and-illustrious?modelVersionId=1032397) ~ Changelog ~December 10, 2024: Initial release with Early Access. December 11, 2024: Early Access goal met. Removed description disclaimer. A copy of it can be found here: https://pastebin.com/F9Cq5b5Q https://pastebin.com/F9Cq5b5Q . Updated description. December 12, 2024: Updated description with tips on how to best use the age slider with character LoRAs. February 19, 2025: Updated the TensorArt Model link to point to the SCALED version on TensorArt as opposed to the non-scaled version on TensorARt", + "description": "\ud83d\udc47\ud83d\udc40 Read me! \ud83d\udc47\ud83d\udc40This is a slider for Illustrious XL, trained on SweetMix https://civitai.com/models/18927/sweet-mix. The purpose of this slider is to allow control of the age of depicted person(s) in generated images.The SCALED version is the v1.0 LoRA but with the age representation in +/- 2 input weight instead of the non-Scaled version's +/- 5 input weight for full age representation.[[ The REALISM version of this slider was removed, and I refunded everyone who bought the download for it what they paid + 500 buzz. I greatly appreciate your support, but CivitAI can not host a realism version of this slider. Consequently, it is now exclusive to TensorArt https://tensor.art/models/859993487842513392. ]]Do not ask me to make this LoRA available for CivitAI's on-site generator. Per CivitAI's Terms of Service, Age adjusting LoRAs can not be used with CivitAI's on-site generator. This is not something I can change. If you want to use this LoRA with an online generation service, it is also available via Tensor Art https://tensor.art/models/823220457818842920.~ How to use v1.0? ~ This is a bipolar slider LoRA. That means it supports both positive and negative input weights. General safe weighting is -5 to 5 , although you can push to +/- 6 with some oddities. No activation tag required. This LoRA is not trained for NoobAI V-Pred models.If you are using this LoRA in combination with a character LoRA, adding supporting tags can be beneficial to affect age. Since character LoRAs often have a set character age trained, it can be difficult to change that age depending on how intensely the character LoRA wants to maintain the character's \"correct\" age. To help overcome this, I suggest you use tags like aged up, aged down, petite , mature female, etc... as needed to help change the character's age. If you run into issues with using this LoRA, please feel free to send me a message on CivitAI, or leave a comment so that I can fix issues that may arise. ~ Known issues (v1.0) ~ At high input weights (> 5), the image subject may have male facial hair. Putting facial hair , mustache , old man , etc... in the negative prompt largely mitigates this.Very low input weights ( < 4.5) may de-saturate the image. As a temporary workaround, I recommend using a style LoRA to alleviate this. (I like this one a lot https://civitai.com/models/478058/granblue-fantasy-style-for-pony-and-illustrious?modelVersionId=1032397) ~ Changelog ~December 10, 2024: Initial release with Early Access. December 11, 2024: Early Access goal met. Removed description disclaimer. A copy of it can be found here: https://pastebin.com/F9Cq5b5Q https://pastebin.com/F9Cq5b5Q . Updated description. December 12, 2024: Updated description with tips on how to best use the age slider with character LoRAs. February 19, 2025: Updated the TensorArt Model link to point to the SCALED version on TensorArt as opposed to the non-scaled version on TensorArtMay 5, 2025: Released v1.1 REALISM version in Early Access. Updated description. CivitAI removed v1.1 Realism. Refunded everyone who purchased it. Updated description.May 10, 2025: Updated description to link directly to the \"v1.1 - REALISM\" Tensor Art model page.", "sd version": "Other" } \ No newline at end of file diff --git a/Lora/Xipa.json b/Lora/Xipa.json new file mode 100644 index 0000000000000000000000000000000000000000..636085d64dfabf98659e8bac20eaac81e62d73d7 --- /dev/null +++ b/Lora/Xipa.json @@ -0,0 +1,8 @@ +{ + "sha256": "285BFCD75240DE557CE4A88EDE5BA33893BEEB6FF1EF8F649697AD49F29E6162", + "modelId": 1455005, + "modelVersionId": 1645166, + "activation text": "xipa", + "description": "- Discord: CLICK ME https://discord.com/invite/M3JefxVc2wXipa's styling loRA for Illustrious. It was trained over Illustrious-XL - v0.1 https://civitai.com/models/795765?modelVersionId=889818 and tested on WAI-NSFW-illustrious-SDXL - v11.0 https://civitai.com/models/827184/wai-nsfw-illustrious-sdxl?modelVersionId=1410435 (all example images were generated using this model). The model works fine by default and doesn't usually affect the image much, though any review is appreciated.Trigger Word: xipaI recommend using the trigger word at the beginning of the prompt to avoid problems.All images were generated using reForge and applying Hires.fix (x1.5) and ADetailer (over the face).The model MAY generate artifacts in the eyes (especially if they are squinted or you are using Illustrious v0.1 as your model). The easiest way to fix this is to use aDetailer, Inpaint the eyes, or choose a better model like NTRMix XIII, WAI v11, etc.If you would like to support me in continuing to invest time in creating LoRAs, donations are always welcome>~< SmileyTatsu | Patreon https://www.patreon.com/c/SmileyTatsuI may add the option to request models if I see it as optimal. For now, you can request whatever you want, and if I'm interested, I'll probably take a look at it.", + "sd version": "Other" +} \ No newline at end of file diff --git a/Lora/Xipa.preview.png b/Lora/Xipa.preview.png new file mode 100644 index 0000000000000000000000000000000000000000..dbd55f29902d67fdfaf7929e98bb9fcd9f909330 --- /dev/null +++ b/Lora/Xipa.preview.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9026d59e42b9eb93c55245cb1f8afc7e2e5bb36d4ba3f1f24bf26f98211cd33c +size 2307508 diff --git a/Lora/Xipa.safetensors b/Lora/Xipa.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e7fc91823b0090d8bb3d41a0dfa76434c8dfbde8 --- /dev/null +++ b/Lora/Xipa.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:285bfcd75240de557ce4a88ede5ba33893beeb6ff1ef8f649697ad49f29e6162 +size 228480316 diff --git a/Lora/backlighting_il_2_d16.json b/Lora/backlighting_il_2_d16.json new file mode 100644 index 0000000000000000000000000000000000000000..dae26e1e49490a8a4943de777d1db15683b8f3c7 --- /dev/null +++ b/Lora/backlighting_il_2_d16.json @@ -0,0 +1,8 @@ +{ + "sha256": "239053449CBDC0E8552F6ACE4A775795A3D3B260B149D3EF5DF4099DDF9AD023", + "modelId": 1480730, + "modelVersionId": 1674865, + "activation text": "backlighting, bokeh, lens flare", + "description": "Trigger base: backlightingHelpful words: bokeh, lens flareHint: Instead of using a slider LoRA, you can use prompts like [blue theme::0.1] (webui syntax) to effectively change the color temperature.", + "sd version": "Other" +} \ No newline at end of file diff --git a/Lora/backlighting_il_2_d16.preview.png b/Lora/backlighting_il_2_d16.preview.png new file mode 100644 index 0000000000000000000000000000000000000000..80e7c2e244676120446d25b73c91235d003b3c50 --- /dev/null +++ b/Lora/backlighting_il_2_d16.preview.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e78233618981679f6864eca015991a2920265f37d72c72842e614845201921b +size 331824 diff --git a/Lora/backlighting_il_2_d16.safetensors b/Lora/backlighting_il_2_d16.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f506ae9230b203595d69290dbecdd29639a3f22b --- /dev/null +++ b/Lora/backlighting_il_2_d16.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:239053449cbdc0e8552f6ace4a775795a3d3b260b149d3ef5df4099ddf9ad023 +size 114444104 diff --git a/Lora/dust.json b/Lora/dust.json new file mode 100644 index 0000000000000000000000000000000000000000..72530f70b71900bb9d9cb2903e0c0a8ff5395420 --- /dev/null +++ b/Lora/dust.json @@ -0,0 +1,5 @@ +{ + "sha256": "8977704BD2497266484C02733277F9D36372F72E6AC92F1936A72682024BEBE7", + "modelId": "Model not found", + "modelVersionId": "Model not found" +} \ No newline at end of file diff --git a/Lora/dust.safetensors b/Lora/dust.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8f330ccb5aa96614e16fd96b756587a85471b236 --- /dev/null +++ b/Lora/dust.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8977704bd2497266484c02733277f9d36372f72e6ac92f1936a72682024bebe7 +size 256056360 diff --git a/Lora/eyelashext_v10.json b/Lora/eyelashext_v10.json index c6d3ba9be655940103421ca3842d4c8a75f575cb..54c4482adc5ab90c81e99c20a11b4e8b9e757e26 100644 --- a/Lora/eyelashext_v10.json +++ b/Lora/eyelashext_v10.json @@ -3,6 +3,6 @@ "modelId": 1428936, "modelVersionId": 1615133, "activation text": "", - "description": "(\u65e5\u672c\u8a9e\u8aac\u660e\u306f\u5f8c\u534a\u306b\u3042\u308a\u307e\u3059)The popular \"Hotaru's LoRA series (for SD1)\" is now also available for SDXL! More will be released gradually on CivitAI and HuggingFace https://huggingface.co/JujoHotaru/lora/blob/main/sdxl/README.md.This LoRA can be used to increase or decrease a character's eyelashes.This LoRA is compatible with Pony / Illustrious based checkpoints.This LoRA is suitable for 2D-2.5D illustrations only and not suitable for photorealistic checkpoints. My \"Breed\" series checkpoints https://civitai.com/user/JujoHotaru/models?sort=Newest&baseModels=Pony&types=Checkpoint will make good outputs. Sample images are generated with \"Breed\" series listed on \"Suggested Resources\" section.This LoRA is developed by a new training method called \"ADDifT https://note.com/hakomikan/n/n716397e39d56\" (Japanese written article), implemented in TrainTrain extension https://github.com/hako-mikan/sd-webui-traintrain.UsageIt works by simply enabling LoRA. No extra prompts are necessary.Positive weight increases eyelashes while negative weight decreases eyelashes.More various other SD1/SDXL LoRA's and checkpoints are available on my HuggingFace repository https://huggingface.co/JujoHotaru or CivitAI models list https://civitai.com/user/JujoHotaru/models. Please check it out.SD1\u3067\u3054\u597d\u8a55\u3044\u305f\u3060\u3044\u3066\u3044\u305f\u5341\u6761\u86cd\u306eLoRA\u30b7\u30ea\u30fc\u30ba\u304c\u3001SDXL\u5bfe\u5fdc\u3084\u65b0\u4f5c\u3082\u52a0\u3048\u3066\u518d\u767b\u5834\u3057\u307e\u3059\u3002HuggingFace https://huggingface.co/JujoHotaru/lora/blob/main/sdxl/README.md\u304a\u3088\u3073CivitAI\u306b\u3066\u9806\u6b21\u516c\u958b\u3057\u3066\u3044\u304d\u307e\u3059\u3002\u30ad\u30e3\u30e9\u30af\u30bf\u30fc\u306e\u776b\u6bdb\u3092\u5897\u52a0\u3055\u305b\u305f\u308a\u6e1b\u5c11\u3055\u305b\u305f\u308a\u3067\u304d\u307e\u3059\u3002Pony\u7cfb\u30fbIllustrious\u7cfb\u306e\u30c7\u30fc\u30bf\u30e2\u30c7\u30eb\u3067\u52d5\u4f5c\u78ba\u8a8d\u3057\u3066\u3044\u307e\u3059\u304c\u3001\u4e00\u90e8\u306e\u30c7\u30fc\u30bf\u30e2\u30c7\u30eb\u3067\u306f\u3046\u307e\u304f\u518d\u73fe\u3055\u308c\u306a\u3044\u3053\u3068\u304c\u3042\u308a\u307e\u3059\u30022D\u30fb2.5D\u30a4\u30e9\u30b9\u30c8\u7cfb\u306e\u30c7\u30fc\u30bf\u30e2\u30c7\u30eb\u7528\u3067\u3001\u5b9f\u5199\u7cfb\u306b\u306f\u4e0d\u5411\u304d\u3067\u3059\u3002\u62d9\u4f5c\u30c7\u30fc\u30bf\u30e2\u30c7\u30eb\u300cBreed\u30b7\u30ea\u30fc\u30ba https://civitai.com/user/JujoHotaru/models?sort=Newest&baseModels=Pony&types=Checkpoint\u300d\u3068\u7d44\u307f\u5408\u308f\u305b\u308b\u3068\u3001\u9ad8\u3044\u52b9\u679c\u3092\u767a\u63ee\u3057\u307e\u3059\u3002\u30b5\u30f3\u30d7\u30eb\u753b\u50cf\u3082Breed\u30b7\u30ea\u30fc\u30ba\uff08\"Suggested Resources\"\u30bb\u30af\u30b7\u30e7\u30f3\u306b\u63b2\u8f09\uff09\u3067\u751f\u6210\u3055\u308c\u3066\u3044\u307e\u3059\u3002\u3053\u306eLoRA\u306f\u30012025\u5e743\u6708\u767a\u8868\u306e\u65b0\u3057\u3044LoRA\u5b66\u7fd2\u65b9\u5f0f\u3067\u3042\u308b\u300cADDifT https://note.com/hakomikan/n/n716397e39d56\u300d\uff08TrainTrain\u62e1\u5f35\u6a5f\u80fd https://github.com/hako-mikan/sd-webui-traintrain\u3067\u5229\u7528\u53ef\u80fd\uff09\u3092\u7528\u3044\u3066\u958b\u767a\u3055\u308c\u3066\u3044\u307e\u3059\u3002\u4f7f\u3044\u65b9LoRA\u3092\u6709\u52b9\u306b\u3059\u308b\u3060\u3051\u3067\u767a\u52d5\u3057\u307e\u3059\u3002\u968e\u5c64\u8abf\u6574\u6e08\u307f\u3067\u3059\u306e\u3067\u3001\u57fa\u672c\u7684\u306b\u306f\u968e\u5c64\u6307\u5b9a\u305b\u305a\u5f37\u5ea6\u6307\u5b9a\u306e\u307f\u3067\u5927\u4e08\u592b\u3067\u3059\u3002\u30d7\u30e9\u30b9\u5f37\u5ea6\u3067\u776b\u6bdb\u304c\u5897\u52a0\u3001\u30de\u30a4\u30ca\u30b9\u5f37\u5ea6\u3067\u776b\u6bdb\u304c\u6e1b\u5c11\u3057\u307e\u3059\u3002\u4ed6\u306b\u3082\u3055\u307e\u3056\u307e\u306aSD1/SDXL\u7528LoRA\u304a\u3088\u3073\u30c7\u30fc\u30bf\u30e2\u30c7\u30eb\u3092\u516c\u958b\u3057\u3066\u3044\u307e\u3059\u306e\u3067\u3001HuggingFace\u30ea\u30dd\u30b8\u30c8\u30ea https://huggingface.co/JujoHotaru\u307e\u305f\u306fCivitAI\u306e\u914d\u5e03\u30e2\u30c7\u30eb\u30ea\u30b9\u30c8 https://civitai.com/user/JujoHotaru/models\u3092\u3054\u89a7\u304f\u3060\u3055\u3044\u3002", + "description": "(\u65e5\u672c\u8a9e\u8aac\u660e\u306f\u5f8c\u534a\u306b\u3042\u308a\u307e\u3059)The popular \"Hotaru's LoRA series (for SD1)\" is now also available for SDXL! More will be released gradually on CivitAI and HuggingFace https://huggingface.co/JujoHotaru/lora/blob/main/sdxl/README.md.This LoRA can be used to increase or decrease character's eyelashes.This LoRA is compatible with Pony / Illustrious based checkpoints.This LoRA is suitable for 2D-2.5D illustrations only and not suitable for photorealistic checkpoints. My \"Breed\" series checkpoints https://civitai.com/user/JujoHotaru/models?sort=Newest&baseModels=Pony&types=Checkpoint will make good outputs. Sample images are generated with \"Breed\" series listed on \"Suggested Resources\" section.This LoRA is developed by a new training method called \"ADDifT https://note.com/hakomikan/n/n716397e39d56\" (Japanese written article), implemented in TrainTrain extension https://github.com/hako-mikan/sd-webui-traintrain.UsageIt works by simply enabling LoRA. No extra prompts are necessary.Positive weight increases eyelashes while negative weight decreases eyelashes.More various other SD1/SDXL LoRA's and checkpoints are available on my HuggingFace repository https://huggingface.co/JujoHotaru or CivitAI models list https://civitai.com/user/JujoHotaru/models. Please check it out.SD1\u3067\u3054\u597d\u8a55\u3044\u305f\u3060\u3044\u3066\u3044\u305f\u5341\u6761\u86cd\u306eLoRA\u30b7\u30ea\u30fc\u30ba\u304c\u3001SDXL\u5bfe\u5fdc\u3084\u65b0\u4f5c\u3082\u52a0\u3048\u3066\u518d\u767b\u5834\u3057\u307e\u3059\u3002HuggingFace https://huggingface.co/JujoHotaru/lora/blob/main/sdxl/README.md\u304a\u3088\u3073CivitAI\u306b\u3066\u9806\u6b21\u516c\u958b\u3057\u3066\u3044\u304d\u307e\u3059\u3002\u30ad\u30e3\u30e9\u30af\u30bf\u30fc\u306e\u776b\u6bdb\u3092\u5897\u52a0\u3055\u305b\u305f\u308a\u6e1b\u5c11\u3055\u305b\u305f\u308a\u3067\u304d\u307e\u3059\u3002Pony\u7cfb\u30fbIllustrious\u7cfb\u306e\u30c7\u30fc\u30bf\u30e2\u30c7\u30eb\u3067\u52d5\u4f5c\u78ba\u8a8d\u3057\u3066\u3044\u307e\u3059\u304c\u3001\u4e00\u90e8\u306e\u30c7\u30fc\u30bf\u30e2\u30c7\u30eb\u3067\u306f\u3046\u307e\u304f\u518d\u73fe\u3055\u308c\u306a\u3044\u3053\u3068\u304c\u3042\u308a\u307e\u3059\u30022D\u30fb2.5D\u30a4\u30e9\u30b9\u30c8\u7cfb\u306e\u30c7\u30fc\u30bf\u30e2\u30c7\u30eb\u7528\u3067\u3001\u5b9f\u5199\u7cfb\u306b\u306f\u4e0d\u5411\u304d\u3067\u3059\u3002\u62d9\u4f5c\u30c7\u30fc\u30bf\u30e2\u30c7\u30eb\u300cBreed\u30b7\u30ea\u30fc\u30ba https://civitai.com/user/JujoHotaru/models?sort=Newest&baseModels=Pony&types=Checkpoint\u300d\u3068\u7d44\u307f\u5408\u308f\u305b\u308b\u3068\u3001\u9ad8\u3044\u52b9\u679c\u3092\u767a\u63ee\u3057\u307e\u3059\u3002\u30b5\u30f3\u30d7\u30eb\u753b\u50cf\u3082Breed\u30b7\u30ea\u30fc\u30ba\uff08\"Suggested Resources\"\u30bb\u30af\u30b7\u30e7\u30f3\u306b\u63b2\u8f09\uff09\u3067\u751f\u6210\u3055\u308c\u3066\u3044\u307e\u3059\u3002\u3053\u306eLoRA\u306f\u30012025\u5e743\u6708\u767a\u8868\u306e\u65b0\u3057\u3044LoRA\u5b66\u7fd2\u65b9\u5f0f\u3067\u3042\u308b\u300cADDifT https://note.com/hakomikan/n/n716397e39d56\u300d\uff08TrainTrain\u62e1\u5f35\u6a5f\u80fd https://github.com/hako-mikan/sd-webui-traintrain\u3067\u5229\u7528\u53ef\u80fd\uff09\u3092\u7528\u3044\u3066\u958b\u767a\u3055\u308c\u3066\u3044\u307e\u3059\u3002\u4f7f\u3044\u65b9LoRA\u3092\u6709\u52b9\u306b\u3059\u308b\u3060\u3051\u3067\u767a\u52d5\u3057\u307e\u3059\u3002\u968e\u5c64\u8abf\u6574\u6e08\u307f\u3067\u3059\u306e\u3067\u3001\u57fa\u672c\u7684\u306b\u306f\u968e\u5c64\u6307\u5b9a\u305b\u305a\u5f37\u5ea6\u6307\u5b9a\u306e\u307f\u3067\u5927\u4e08\u592b\u3067\u3059\u3002\u30d7\u30e9\u30b9\u5f37\u5ea6\u3067\u776b\u6bdb\u304c\u5897\u52a0\u3001\u30de\u30a4\u30ca\u30b9\u5f37\u5ea6\u3067\u776b\u6bdb\u304c\u6e1b\u5c11\u3057\u307e\u3059\u3002\u4ed6\u306b\u3082\u3055\u307e\u3056\u307e\u306aSD1/SDXL\u7528LoRA\u304a\u3088\u3073\u30c7\u30fc\u30bf\u30e2\u30c7\u30eb\u3092\u516c\u958b\u3057\u3066\u3044\u307e\u3059\u306e\u3067\u3001HuggingFace\u30ea\u30dd\u30b8\u30c8\u30ea https://huggingface.co/JujoHotaru\u307e\u305f\u306fCivitAI\u306e\u914d\u5e03\u30e2\u30c7\u30eb\u30ea\u30b9\u30c8 https://civitai.com/user/JujoHotaru/models\u3092\u3054\u89a7\u304f\u3060\u3055\u3044\u3002", "sd version": "Other" } \ No newline at end of file diff --git a/Lora/fixed_point_v2.json b/Lora/fixed_point_v2.json new file mode 100644 index 0000000000000000000000000000000000000000..2f2101c695ad05b3cc80599b96ad79715f6d5173 --- /dev/null +++ b/Lora/fixed_point_v2.json @@ -0,0 +1,8 @@ +{ + "sha256": "9D960C951C959447EA5698EADBFF079ABFD348032195D313AD8A8A0D414AC4B9", + "modelId": 1332845, + "modelVersionId": 1598281, + "activation text": "fixedpoint, , fixedpoint, ceilingview, fixedpoint, sideview, fixedpoint, roomview", + "description": "This is a concept LoRA to manipulate the camera angle. It provides a fixed perspective shot of the image. Intended for NSFW content but is not limited to that. Please do post pictures below, as I'm interested to see what everyone is able to make with this tool.V1My first attempt at creating a concept LoRA and something I have been collecting images for a while as I come across them. Felt like I had enough to give it a shot and this is the result. I will need to collect more to update it in the future. Requires ADetailer and HiResFix to get good outputs. If prompting more than one subject inpainting will likely be required to fix it up.V2I have expanded the size of the dataset used for training and have also categorized a section of the images to attempt to provide trigger words to manipulate the camera further. I was rough with it due to the sheer quantity of images used and limited time to spend pruning and cleaning up the tags. Due to that it could be improved, but I did manage to get part of the control that I wanted.V3Removed some images and added new sources to training dataset to attempt to have the LoRA alter style of output as much as V2 or V1. Toyed around with tag weights to try and add further control. V3 is not strictly better than V2.", + "sd version": "Other" +} \ No newline at end of file diff --git a/Lora/fixed_point_v2.preview.png b/Lora/fixed_point_v2.preview.png new file mode 100644 index 0000000000000000000000000000000000000000..81d88e8a5a5006a4e62a00256bbb07da0c799dc5 --- /dev/null +++ b/Lora/fixed_point_v2.preview.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8630c8e5ef03ff649291e6ca4b273752781099e4e4102b14650bac4e4075a8de +size 956774 diff --git a/Lora/fixed_point_v2.safetensors b/Lora/fixed_point_v2.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b9ea73e102c23f1b61197a69317058bac1835c27 --- /dev/null +++ b/Lora/fixed_point_v2.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d960c951c959447ea5698eadbff079abfd348032195d313ad8a8a0d414ac4b9 +size 228484636 diff --git a/Lora/gwen.json b/Lora/gwen.json new file mode 100644 index 0000000000000000000000000000000000000000..07257f91ad32d835c3d7910cf1c45af3a7b319e9 --- /dev/null +++ b/Lora/gwen.json @@ -0,0 +1,8 @@ +{ + "sha256": "BE1399DE88B888D587BF055243D0AC8DBF2A60D8A8545C2ECDD7E5880BCB0EB2", + "modelId": 1162535, + "modelVersionId": 1307714, + "activation text": "western comics (style), gwen, green eyes, orange hair, short hair, hairclip, stud earrings, hair ornament, jewelry, very small breasts, western comics (style), gwen, green eyes, orange hair, short hair, hairclip, stud earrings, hair ornament, jewelry, very small breasts, shirt, blue shirt, animal print, raglan sleeves, capri pants, pants, shoes", + "description": "Gwen Tennyson from Ben 10 parody\u2757 All my previews are made with: Euler a, 25 steps and CFG scale at 7", + "sd version": "Other" +} \ No newline at end of file diff --git a/Lora/gwen.preview.png b/Lora/gwen.preview.png new file mode 100644 index 0000000000000000000000000000000000000000..b8f87fd1195ed877b11f1ebe41719b397e820e3b --- /dev/null +++ b/Lora/gwen.preview.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c139bdb862c3117399357cc531921a47f60ad9d6e8c02dfc106dd1d9259a1ed +size 975141 diff --git a/Lora/gwen.safetensors b/Lora/gwen.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ba1311cb9e751737b14efb5a562d9c5ce41dcacf --- /dev/null +++ b/Lora/gwen.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be1399de88b888d587bf055243d0ac8dbf2a60d8a8545c2ecdd7e5880bcb0eb2 +size 228457636 diff --git a/Lora/gwentenE28090illus13.QCtZ.json b/Lora/gwentenE28090illus13.QCtZ.json new file mode 100644 index 0000000000000000000000000000000000000000..97e26d50f11ca8bebc43913f1b2ff338ac569424 --- /dev/null +++ b/Lora/gwentenE28090illus13.QCtZ.json @@ -0,0 +1,5 @@ +{ + "sha256": "50BF9B1FF87BA13C6FC16C1D9520CAA88296FB2906857B4B26605BA8B97A1C40", + "modelId": 23594, + "modelVersionId": 1627455 +} \ No newline at end of file diff --git a/Lora/gwentenE28090illus13.QCtZ.preview.png b/Lora/gwentenE28090illus13.QCtZ.preview.png new file mode 100644 index 0000000000000000000000000000000000000000..377ba8044c02466e41698e34568e010306da6dc7 --- /dev/null +++ b/Lora/gwentenE28090illus13.QCtZ.preview.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbd2fa8d5557828194b235dcb2b639de4592acdd8851d76a645245fbb6a28a4e +size 2410338 diff --git a/Lora/gwentenE28090illus13.QCtZ.safetensors b/Lora/gwentenE28090illus13.QCtZ.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..51d96aa92b6ba1caad993bc9809f5e3503ea8e74 --- /dev/null +++ b/Lora/gwentenE28090illus13.QCtZ.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50bf9b1ff87ba13c6fc16c1d9520caa88296fb2906857b4b26605ba8b97a1c40 +size 50940956 diff --git a/Lora/hinaIDidSurgeryAlongSlider_x215c.json b/Lora/hinaIDidSurgeryAlongSlider_x215c.json new file mode 100644 index 0000000000000000000000000000000000000000..c884388bd135a5ebc4e953b26f28d26226f22c9c --- /dev/null +++ b/Lora/hinaIDidSurgeryAlongSlider_x215c.json @@ -0,0 +1,8 @@ +{ + "sha256": "80FA29D7AFCF786B91006B394A8941E54ADA371470D2EA227FA718ECAA15F0D8", + "modelId": 100060, + "modelVersionId": 1657469, + "activation text": "", + "description": "\u66f4\u591a\u8a0a\u606f\u8acb\u53c3\u8003\u6bcf\u500b\u6a21\u578b\u7248\u672c\u5167\u7684 About this Version.For information about each version of the model, please refer to About this Version for each model version.\u5404\u30e2\u30c7\u30eb\u306e\u30d0\u30fc\u30b8\u30e7\u30f3\u306b\u3064\u3044\u3066\u306f\u3001\u5404\u30e2\u30c7\u30eb\u306e\u30d0\u30fc\u30b8\u30e7\u30f3\u306b\u3064\u3044\u3066\u3092\u53c2\u7167\u3057\u3066\u304f\u3060\u3055\u3044\u3002\uac01 \ubaa8\ub378 \ubc84\uc804\uc5d0 \ub300\ud55c \uc790\uc138\ud55c \ub0b4\uc6a9\uc740 \uac01 \ubaa8\ub378 \ubc84\uc804\uc5d0 \ub300\ud55c \uc774 \ubc84\uc804 \uc815\ubcf4\ub97c \ucc38\uc870\ud558\uc138\uc694.Support me on Ko-fi https://ko-fi.com/hinablue https://ko-fi.com/hinablue", + "sd version": "Other" +} \ No newline at end of file diff --git a/Lora/hinaIDidSurgeryAlongSlider_x215c.preview.png b/Lora/hinaIDidSurgeryAlongSlider_x215c.preview.png new file mode 100644 index 0000000000000000000000000000000000000000..6215757bc960fa1e4dba85b6961a204498ac5917 --- /dev/null +++ b/Lora/hinaIDidSurgeryAlongSlider_x215c.preview.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9d589a07c38966f601a22e97b13ab344140c4a513ffc65f83c7449a2a333108 +size 682598 diff --git a/Lora/hinaIDidSurgeryAlongSlider_x215c.safetensors b/Lora/hinaIDidSurgeryAlongSlider_x215c.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6ec3fde6643a543a92daff68e74d537620f7c7ae --- /dev/null +++ b/Lora/hinaIDidSurgeryAlongSlider_x215c.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80fa29d7afcf786b91006b394a8941e54ada371470d2ea227fa718ecaa15f0d8 +size 108857324 diff --git a/Lora/hollowPurpleLoRA-1.json b/Lora/hollowPurpleLoRA-1.json new file mode 100644 index 0000000000000000000000000000000000000000..d36aabfbe14c62e067494217f9dbede25b19d6d0 --- /dev/null +++ b/Lora/hollowPurpleLoRA-1.json @@ -0,0 +1,8 @@ +{ + "sha256": "93CAF8B1302AA003CDA18FA86E1A89B1F5513FBE23D74717F6CB78DBD1F028AE", + "modelId": 1482654, + "modelVersionId": 1677077, + "activation text": "memehollowpurple, meme", + "description": "Throughout Heaven and Earth, I alone am the honored one.Another awesome JJK meme lora againThis was fun, though I couldn't get it to work better on Noob VPRED..What does this LoRA includes:Gojo's hollow purple frame from the anime \u2714Manga version \u274cToji Fushiguro frames \u274cI recommend you to put scanlines on the negative!!Have fufnfdnfdfjhhs", + "sd version": "Other" +} \ No newline at end of file diff --git a/Lora/hollowPurpleLoRA-1.preview.png b/Lora/hollowPurpleLoRA-1.preview.png new file mode 100644 index 0000000000000000000000000000000000000000..7cbc8d7bdf3e1fa4858b5a83ae9da4bd087a2e28 Binary files /dev/null and b/Lora/hollowPurpleLoRA-1.preview.png differ diff --git a/Lora/hollowPurpleLoRA-1.safetensors b/Lora/hollowPurpleLoRA-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..918b7a5fea9a3e7cd536da6e482547afc9f94870 --- /dev/null +++ b/Lora/hollowPurpleLoRA-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93caf8b1302aa003cda18fa86e1a89b1f5513fbe23d74717f6cb78dbd1f028ae +size 232469736 diff --git a/Lora/illustriousXLv01_stabilizer_v1.121.json b/Lora/illustriousXLv01_stabilizer_v1.121.json new file mode 100644 index 0000000000000000000000000000000000000000..1e9e0171a76ef061d254086f14e2842a6296bfc2 --- /dev/null +++ b/Lora/illustriousXLv01_stabilizer_v1.121.json @@ -0,0 +1,8 @@ +{ + "sha256": "D8FC4B0E9E6705B6905FAC5DB936610677165A66D5A6548E619E6FF00E2BDA39", + "modelId": 971952, + "modelVersionId": 1674551, + "activation text": "", + "description": "Trained on a normal and natural dataset. For natural lighting, textures, details...The dataset only has high resolution images. Zero AI image. So you can get texture and details beyond pixel level. Instead of a weird smooth feeling. FYI, all cover images directly come from a1111, no upscale, no inpainting. If you think they are, then this LoRA did its job well.Recent updates:(5/7/2025) Note: 90% \"illustrious\" models are actually NoobAI and you may need to use NoobAI LoRA instead.I was also surprised. I tested 13 popular models labeled as illustrious, using some tags that only NoobAI knows (new characters from new games after illustrious was trained).1 realistic model does not respond to those tags.Other 12 models know those tags VERY well and output almost same images just like NoobAI.So they are actually NoobAI, or mainly (>80% merged). And should use NoobAI LoRA as well. Remainer: There is a huge training gap of millions of images and steps between illustrious and NoobAI. So using illus LoRA on NoobAI is doable but not ideal.You can use this \"1girl,ellen joe,red eyes,upper body,masterpiece\" to test your base model. \"ellen joe\" is a new characters. If your base model is firmly based on illustrious, it will output a random person, otherwise, your base model is NoobAI.(5/9/2025): nbep11 v0.205:A quick fix of brightness and color issues in v0.198. Now it should not change brightness and colors so dramatically like a real photograph. v0.198 isn't bad, just creative, but too creative.(5/7/2025): nbep11 v0.198:Added more dark images. Less deformed body, background in dark environment. Removed color and contrast enhancement. Because it's not needed anymore. Use Contrast Controller https://civitai.com/models/1523055/contrast-controller-sdxl instead..........See more in the update log section..........(3/2/2025): You can find the REAL me at TensorArt https://tensor.art/u/791762176019958222 now. I've reclaimed all my models that were duped and faked by other accounts.StabilizerJust a personal fun coding project. Trained on ~2k normal and natural images.The goal of this LoRA is just to make the image look better, better contrast, lighting, character details... It doesn't focus on unique art style.It has relatively weaker effects than other LoRA, and won't dramatically change the image composition.Cover images are the direct outputs from the vanilla (not finetuned) base model in a1111-sd-webui, no inpaint fixes, even no negative prompt. They demonstrate the effect of the LoRA, not clickbait.Share merges using this LoRA is prohibited. FYI, there are hidden trigger words to print invisible watermark. It works well even if the merge strength is 0.05. I coded the watermark and detector myself. I don't want to use it, but I can.Remember to leave feedback in comment section. So everyone can see it. Don't write feedback in Civitai review system, it was so poorly designed, literally nobody can find and see the review.Have fun.How to useJust apply it. No trigger words needed. Also it does not patch text encoders. So you don't have to set the patch strength for text encoder (in comfyui, etc.).Version prefix:illus01 = Trained on illustriousXL v0.1nbep11 = Trained on NoobAI e-pred v1.1 (compatible with v-pred)NOTE (5/8/2025): 90% \"illustrious\" models now are actually NoobAI and you should use NoobAI LoRA instead. Because illustriousXL v0.1 was so poorly trained. Most (90%) models that labeled as \"illustrious\" are actually or mainly NoobAI. You can test your model with \"1girl,ellen joe,red eyes,upper body,masterpiece\". \"ellen joe\" is a new characters. If your base model is firmly based on illustrious, it will output a random person, otherwise, your base model is NoobAI. Remainer: There is a huge training gap of millions of images and steps between illustrious and NoobAI. So using illus LoRA on NoobAI is doable but not ideal.DatasetOnly normal good looking things. No crazy art style. Not small (~2k images).Every image is hand-picked by me. No AI images, no watermarks, etc.There are 2 main dataset in the latest version:a 2D/anime dataset with ~1k images. Character-focus. Natural poses. Natural body proportions. No exaggerated art, chibi, jojo pose, etc.a real world photographs dataset with ~1k images. Contains nature, indoors, animals, buildings...many things, except human.Why real world images? You can get better background, lighting, pixel level details/textures. There is no human in dataset so it won't affect characters.You can read more about this sub dataset and why I added it, at here: Touching Grass https://civitai.com/models/1429923/natural-details-enhancer-touching-grass. There is also a LoRA that was only trained on this photograph dataset. If you want something pure.Other toolsSome ideas that was going to, or used to, be part of the Stabilizer. Now they are separated LoRAs. For better flexibility. Collection link: https://civitai.com/collections/8274233 https://civitai.com/collections/8274233.Touching Grass https://civitai.com/models/1429923: Trained on and only on the ~1k photographs dataset (No anime dataset). Has stronger effect. Useful for gigachad users who like pure concepts and like to balance weights themselves.Dark https://civitai.com/models/1541866: Can reduce the bias of high brightness in anime models, or make them more bias to dark. Useful for very dark objects, photography-ish lighting effect. Trained on low brightness images in Touching Grass. So it will also make the base model more natural (lighting, details etc.).It's also a bootstrap for the \"Stabilizer\" and \"Touching Grass\" at early sampling steps. Use this LoRA can active their full dark image dataset.Example on WAI v13.Contrast Controller https://civitai.com/models/1523055/contrast-controller-sdxl: Control the contrast like using a slider in your monitor. Unlike other trained \"contrast enhancer\", the effect of this LoRA is stable, linear, and has zero side effect on style. (Not an exaggeration, it's really mathematically zero and linear. It was not from training.) Example on WAI v13.Style Strength Controller https://civitai.com/models/1519509/style-strength-controller-il: Or overfitting effect reducer. Also not from training, so zero side effect on style and mathematically linear effects. Can reduce all kinds of overfitting effects (bias on objects, brightness, etc.).Effect test on Hassaku XL: The prompt has keyword \"dark\", but the model almost ignored it. Notice that: at strength 0.25 this LoRA reduces the bias of high brightness, and a weird smooth feeling on every surfaces, so the image feels more natural.Differences between Stabilizer:Stabilizer affects style. Because it was trained on real world data. It can \"reduce\" overfitting effects about texture, details and backgrounds, by adding them back.Style Controller was not from training. It is more like \"undo\" the training for base model, so it will less-overfitted. It does not affect style. And can reduce all overfitting effects, like bias on brightness, objects.FAQEffect is very weak even at strength 1.This LoRA does have weaker effects, because it was not overtrained/overfitted. So if your base model (or other LoRAs) has very strong effects. It will easily overlap this LoRA.If you insist on overlapping existing strong style models, adding more details, try \"Touching Grass https://civitai.com/models/1429923\". It was trained very hard and has much stronger effects. For advance users who like to balance style weights themselves.Personally I would avoid using such base model/LoRAs, as they are always problematic.I got realistic faces on my anime characters.Don't blame this LoRA, it has zero knowledge of realistic faces. Although it contains real world images, there is no realistic human in dataset. (See the \"dataset\" section above). Most likely your base model was mixed with other realistic models, probably for better texture and lighting as well. It was already polluted. This LoRA may just active the polluted part because the training datasets are similar (both are from real world).Older versionsNew version == new stuffs and new attempt != better version for you base model.You can check the \"Update log\" section to find old versions. It's ok to use different versions together just like mixing base models. As long as the sum of strengths does not > 1.Update log(4/25/2025): nbep11 v0.172.Same new things in illus01 v1.93 ~ v1.121. Summary: New photographs dataset \"Touching Grass https://civitai.com/models/1429923/natural-details-enhancer-touching-grass\". Better natural texture, background, lighting. Weaker character effects for better compatibility.Better color accuracy and stability. (Comparing to nbep11 v0.160)(4/17/2025): illus01 v1.121.Rolled back to illustrious v0.1. illustrious v1.0 and newer versions were trained with AI images deliberately (maybe 30% of its dataset). Which is not ideal for LoRA training. I didn't notice until I read its paper.Lower character style effect. Back to v1.23 level. Characters will have less details from this LoRA, but should have better compatibility. This is a trade-off.Other things just same as below (v1.113).(4/10/2025): illus11 v1.113.Update: use this version only if you know your base model is based on Illustrious v1.1. Otherwise, use illus01 v1.121.Trained on Illustrious v1.1.New dataset \"Touching Grass https://civitai.com/models/1429923/natural-details-enhancer-touching-grass\" added. Better natural texture, lighting and depth of field effect. Better background structural stability. Less deformed background, like deformed rooms, buildings.Full natural language captions from LLM.(3/30/2025): illus01 v1.93.v1.72 was trained too hard. So I reduced it overall strength. Should have better compatibility.(3/22/2025): nbep11 v0.160.Same stuffs in illus v1.72.(3/15/2025): illus01 v1.72Same new texture and lighting dataset as mentioned in ani40z v0.4 below. More natural lighting and natural textures.Added a small ~100 images dataset for hand enhancement, focusing on hand(s) with different tasks, like holding a glass or cup or something.Removed all \"simple background\" images from dataset. -200 images.Switched training tool from kohya to onetrainer. Changed LoRA architecture to DoRA.(3/4/2025) ani40z v0.4Trained on Animagine XL 4.0 ani40zero.Added ~1k dataset focusing on natural dynamic lighting and real world texture. More natural lighting and natural textures.Above: Added more real world images. More natural texture and details..ani04 v0.1Init version for Animagine XL 4.0. Mainly to fix Animagine 4.0 brightness issues. Better and higher contrast.illus01 v1.23nbep11 v0.138Added some furry/non-human/other images to balance the dataset.nbep11 v0.129bad version, effect is too weak, just ignore itnbep11 v0.114Implemented \"Full range colors\". It will automatically balance the things towards \"normal and good looking\". Think of this as the \"one-click photo auto enhance\" button in most of photo editing tools. One downside of this optimization: It prevents high bias. For example, you want 95% of the image to be black, and 5% bright, instead of 50/50%Added a little bit realistic data. More vivid details, lighting, less flat colors.illus01 v1.7nbep11 v0.96More training images.Then finetuned again on a small \"wallpaper\" dataset (Real wallpapers, the highest quality I could find. ~100 images). More improvements in details (noticeable in skin, hair) and contrast.Above: Has a weak default style.nbep11 v0.58More images. Change the training parameters as close as to NoobAI base model.illus01 v1.3nbep11 v0.30More images.nbep11 v0.11: Trained on NoobAI epsilon pred v1.1.Improved dataset tags. Improved LoRA structure and weight distribution. Should be more stable and have less impact on image composition.illus01 v1.1Trained on illustriousXL v0.1.nbep10 v0.10Trained on NoobAI epsilon pred v1.0.", + "sd version": "Other" +} \ No newline at end of file diff --git a/Lora/illustriousXLv01_stabilizer_v1.121.preview.png b/Lora/illustriousXLv01_stabilizer_v1.121.preview.png new file mode 100644 index 0000000000000000000000000000000000000000..f96f06a6e70684767a48c081c5fd984440278376 --- /dev/null +++ b/Lora/illustriousXLv01_stabilizer_v1.121.preview.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d035dca617378d5177992eaba6d71597fb76485eb13d3171752b1a5c8959e53 +size 119608 diff --git a/Lora/illustriousXLv01_stabilizer_v1.121.safetensors b/Lora/illustriousXLv01_stabilizer_v1.121.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..369f737c580e94db2985c2d654b06ad5641b86ea --- /dev/null +++ b/Lora/illustriousXLv01_stabilizer_v1.121.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8fc4b0e9e6705b6905fac5db936610677165a66d5a6548e619e6ff00e2bda39 +size 88008084 diff --git a/Lora/illustriousXLv11_stabilizer_v1.113.json b/Lora/illustriousXLv11_stabilizer_v1.113.json new file mode 100644 index 0000000000000000000000000000000000000000..a68174785269719c4a081310b8c443d1f0326b9d --- /dev/null +++ b/Lora/illustriousXLv11_stabilizer_v1.113.json @@ -0,0 +1,8 @@ +{ + "sha256": "328CC385DF7E7D444C2F3051396F5B79FBEF664AC78CACE16D1A8A5489C569CA", + "modelId": 971952, + "modelVersionId": 1645427, + "activation text": "", + "description": "Trained on a normal and natural dataset. For natural lighting, textures, details...The dataset only has high resolution images. Zero AI image. So you can get texture and details beyond pixel level. Instead of a weird smooth feeling. FYI, all cover images directly come from a1111, no upscale, no inpainting. If you think they are, then this LoRA did its job well.Recent updates:(5/7/2025) Note: 90% \"illustrious\" models are actually NoobAI and you may need to use NoobAI LoRA instead.I was also surprised. I tested 13 popular models labeled as illustrious, using some tags that only NoobAI knows (new characters from new games after illustrious was trained).1 realistic model does not respond to those tags.Other 12 models know those tags VERY well and output almost same images just like NoobAI.So they are actually NoobAI, or mainly (>80% merged). And should use NoobAI LoRA as well. Remainer: There is a huge training gap of millions of images and steps between illustrious and NoobAI. So using illus LoRA on NoobAI is doable but not ideal.You can use this \"1girl,ellen joe,red eyes,upper body,masterpiece\" to test your base model. \"ellen joe\" is a new characters. If your base model is firmly based on illustrious, it will output a random person, otherwise, your base model is NoobAI.(5/9/2025): nbep11 v0.205:A quick fix of brightness and color issues in v0.198. Now it should not change brightness and colors so dramatically like a real photograph. v0.198 isn't bad, just creative, but too creative.(5/7/2025): nbep11 v0.198:Added more dark images. Less deformed body, background in dark environment. Removed color and contrast enhancement. Because it's not needed anymore. Use Contrast Controller https://civitai.com/models/1523055/contrast-controller-sdxl instead..........See more in the update log section..........(3/2/2025): You can find the REAL me at TensorArt https://tensor.art/u/791762176019958222 now. I've reclaimed all my models that were duped and faked by other accounts.StabilizerJust a personal fun coding project. Trained on ~2k normal and natural images.The goal of this LoRA is just to make the image look better, better contrast, lighting, character details... It doesn't focus on unique art style.It has relatively weaker effects than other LoRA, and won't dramatically change the image composition.Cover images are the direct outputs from the vanilla (not finetuned) base model in a1111-sd-webui, no inpaint fixes, even no negative prompt. They demonstrate the effect of the LoRA, not clickbait.Share merges using this LoRA is prohibited. FYI, there are hidden trigger words to print invisible watermark. It works well even if the merge strength is 0.05. I coded the watermark and detector myself. I don't want to use it, but I can.Remember to leave feedback in comment section. So everyone can see it. Don't write feedback in Civitai review system, it was so poorly designed, literally nobody can find and see the review.Have fun.How to useJust apply it. No trigger words needed. Also it does not patch text encoders. So you don't have to set the patch strength for text encoder (in comfyui, etc.).Version prefix:illus01 = Trained on illustriousXL v0.1nbep11 = Trained on NoobAI e-pred v1.1 (compatible with v-pred)NOTE (5/8/2025): 90% \"illustrious\" models now are actually NoobAI and you should use NoobAI LoRA instead. Because illustriousXL v0.1 was so poorly trained. Most (90%) models that labeled as \"illustrious\" are actually or mainly NoobAI. You can test your model with \"1girl,ellen joe,red eyes,upper body,masterpiece\". \"ellen joe\" is a new characters. If your base model is firmly based on illustrious, it will output a random person, otherwise, your base model is NoobAI. Remainer: There is a huge training gap of millions of images and steps between illustrious and NoobAI. So using illus LoRA on NoobAI is doable but not ideal.DatasetOnly normal good looking things. No crazy art style. Not small (~2k images).Every image is hand-picked by me. No AI images, no watermarks, etc.There are 2 main dataset in the latest version:a 2D/anime dataset with ~1k images. Character-focus. Natural poses. Natural body proportions. No exaggerated art, chibi, jojo pose, etc.a real world photographs dataset with ~1k images. Contains nature, indoors, animals, buildings...many things, except human.Why real world images? You can get better background, lighting, pixel level details/textures. There is no human in dataset so it won't affect characters.You can read more about this sub dataset and why I added it, at here: Touching Grass https://civitai.com/models/1429923/natural-details-enhancer-touching-grass. There is also a LoRA that was only trained on this photograph dataset. If you want something pure.Other toolsSome ideas that was going to, or used to, be part of the Stabilizer. Now they are separated LoRAs. For better flexibility. Collection link: https://civitai.com/collections/8274233 https://civitai.com/collections/8274233.Touching Grass https://civitai.com/models/1429923: Trained on and only on the ~1k photographs dataset (No anime dataset). Has stronger effect. Useful for gigachad users who like pure concepts and like to balance weights themselves.Dark https://civitai.com/models/1541866: Can reduce the bias of high brightness in anime models, or make them more bias to dark. Useful for very dark objects, photography-ish lighting effect. Trained on low brightness images in Touching Grass. So it will also make the base model more natural (lighting, details etc.).It's also a bootstrap for the \"Stabilizer\" and \"Touching Grass\" at early sampling steps. Use this LoRA can active their full dark image dataset.Example on WAI v13.Contrast Controller https://civitai.com/models/1523055/contrast-controller-sdxl: Control the contrast like using a slider in your monitor. Unlike other trained \"contrast enhancer\", the effect of this LoRA is stable, linear, and has zero side effect on style. (Not an exaggeration, it's really mathematically zero and linear. It was not from training.) Example on WAI v13.Style Strength Controller https://civitai.com/models/1519509/style-strength-controller-il: Or overfitting effect reducer. Also not from training, so zero side effect on style and mathematically linear effects. Can reduce all kinds of overfitting effects (bias on objects, brightness, etc.).Effect test on Hassaku XL: The prompt has keyword \"dark\", but the model almost ignored it. Notice that: at strength 0.25 this LoRA reduces the bias of high brightness, and a weird smooth feeling on every surfaces, so the image feels more natural.Differences between Stabilizer:Stabilizer affects style. Because it was trained on real world data. It can \"reduce\" overfitting effects about texture, details and backgrounds, by adding them back.Style Controller was not from training. It is more like \"undo\" the training for base model, so it will less-overfitted. It does not affect style. And can reduce all overfitting effects, like bias on brightness, objects.FAQEffect is very weak even at strength 1.This LoRA does have weaker effects, because it was not overtrained/overfitted. So if your base model (or other LoRAs) has very strong effects. It will easily overlap this LoRA.If you insist on overlapping existing strong style models, adding more details, try \"Touching Grass https://civitai.com/models/1429923\". It was trained very hard and has much stronger effects. For advance users who like to balance style weights themselves.Personally I would avoid using such base model/LoRAs, as they are always problematic.I got realistic faces on my anime characters.Don't blame this LoRA, it has zero knowledge of realistic faces. Although it contains real world images, there is no realistic human in dataset. (See the \"dataset\" section above). Most likely your base model was mixed with other realistic models, probably for better texture and lighting as well. It was already polluted. This LoRA may just active the polluted part because the training datasets are similar (both are from real world).Older versionsNew version == new stuffs and new attempt != better version for you base model.You can check the \"Update log\" section to find old versions. It's ok to use different versions together just like mixing base models. As long as the sum of strengths does not > 1.Update log(4/25/2025): nbep11 v0.172.Same new things in illus01 v1.93 ~ v1.121. Summary: New photographs dataset \"Touching Grass https://civitai.com/models/1429923/natural-details-enhancer-touching-grass\". Better natural texture, background, lighting. Weaker character effects for better compatibility.Better color accuracy and stability. (Comparing to nbep11 v0.160)(4/17/2025): illus01 v1.121.Rolled back to illustrious v0.1. illustrious v1.0 and newer versions were trained with AI images deliberately (maybe 30% of its dataset). Which is not ideal for LoRA training. I didn't notice until I read its paper.Lower character style effect. Back to v1.23 level. Characters will have less details from this LoRA, but should have better compatibility. This is a trade-off.Other things just same as below (v1.113).(4/10/2025): illus11 v1.113.Update: use this version only if you know your base model is based on Illustrious v1.1. Otherwise, use illus01 v1.121.Trained on Illustrious v1.1.New dataset \"Touching Grass https://civitai.com/models/1429923/natural-details-enhancer-touching-grass\" added. Better natural texture, lighting and depth of field effect. Better background structural stability. Less deformed background, like deformed rooms, buildings.Full natural language captions from LLM.(3/30/2025): illus01 v1.93.v1.72 was trained too hard. So I reduced it overall strength. Should have better compatibility.(3/22/2025): nbep11 v0.160.Same stuffs in illus v1.72.(3/15/2025): illus01 v1.72Same new texture and lighting dataset as mentioned in ani40z v0.4 below. More natural lighting and natural textures.Added a small ~100 images dataset for hand enhancement, focusing on hand(s) with different tasks, like holding a glass or cup or something.Removed all \"simple background\" images from dataset. -200 images.Switched training tool from kohya to onetrainer. Changed LoRA architecture to DoRA.(3/4/2025) ani40z v0.4Trained on Animagine XL 4.0 ani40zero.Added ~1k dataset focusing on natural dynamic lighting and real world texture. More natural lighting and natural textures.Above: Added more real world images. More natural texture and details..ani04 v0.1Init version for Animagine XL 4.0. Mainly to fix Animagine 4.0 brightness issues. Better and higher contrast.illus01 v1.23nbep11 v0.138Added some furry/non-human/other images to balance the dataset.nbep11 v0.129bad version, effect is too weak, just ignore itnbep11 v0.114Implemented \"Full range colors\". It will automatically balance the things towards \"normal and good looking\". Think of this as the \"one-click photo auto enhance\" button in most of photo editing tools. One downside of this optimization: It prevents high bias. For example, you want 95% of the image to be black, and 5% bright, instead of 50/50%Added a little bit realistic data. More vivid details, lighting, less flat colors.illus01 v1.7nbep11 v0.96More training images.Then finetuned again on a small \"wallpaper\" dataset (Real wallpapers, the highest quality I could find. ~100 images). More improvements in details (noticeable in skin, hair) and contrast.Above: Has a weak default style.nbep11 v0.58More images. Change the training parameters as close as to NoobAI base model.illus01 v1.3nbep11 v0.30More images.nbep11 v0.11: Trained on NoobAI epsilon pred v1.1.Improved dataset tags. Improved LoRA structure and weight distribution. Should be more stable and have less impact on image composition.illus01 v1.1Trained on illustriousXL v0.1.nbep10 v0.10Trained on NoobAI epsilon pred v1.0.", + "sd version": "Other" +} \ No newline at end of file diff --git a/Lora/illustriousXLv11_stabilizer_v1.113.preview.png b/Lora/illustriousXLv11_stabilizer_v1.113.preview.png new file mode 100644 index 0000000000000000000000000000000000000000..6c9be67661f2be060d14211e62f230c673e7ff7a --- /dev/null +++ b/Lora/illustriousXLv11_stabilizer_v1.113.preview.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58a4736c19696676151824d0ab1a04ec22c6f7eb35783f3932656f0ad0fefb47 +size 2120188 diff --git a/Lora/illustriousXLv11_stabilizer_v1.113.safetensors b/Lora/illustriousXLv11_stabilizer_v1.113.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d447ae5eb8a7fd31916637787eac4f425aa0f226 --- /dev/null +++ b/Lora/illustriousXLv11_stabilizer_v1.113.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:328cc385df7e7d444c2f3051396f5b79fbef664ac78cace16d1a8a5489c569ca +size 109287636 diff --git a/Lora/in-dark.json b/Lora/in-dark.json new file mode 100644 index 0000000000000000000000000000000000000000..51cf41df21c4a0d4eadffe0d5abc177677e08760 --- /dev/null +++ b/Lora/in-dark.json @@ -0,0 +1,8 @@ +{ + "sha256": "890594E3FCE68FB8F48BB313DD12F3FF3E757D0121C235DDA7825A6D1B3117E7", + "modelId": 1529722, + "modelVersionId": 1730762, + "activation text": "in dark", + "description": "This LoRA for enhancing the depiction of light in darkness.", + "sd version": "Other" +} \ No newline at end of file diff --git a/Lora/in-dark.preview.png b/Lora/in-dark.preview.png new file mode 100644 index 0000000000000000000000000000000000000000..d2476f243351188d871fdd2b66a5a46b32a74cd2 --- /dev/null +++ b/Lora/in-dark.preview.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:213fe09508f5581be1c220dd7afa4a6f55c0d5ee3b5173fcfe69d8ba418de5a6 +size 100517 diff --git a/Lora/in-dark.safetensors b/Lora/in-dark.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dbd99e325f1aefaad745e7dc4a118ff43071d20c --- /dev/null +++ b/Lora/in-dark.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:890594e3fce68fb8f48bb313dd12f3ff3e757d0121c235dda7825a6d1b3117e7 +size 172085760 diff --git a/Lora/krekkov-ByChiAi_.json b/Lora/krekkov-ByChiAi_.json new file mode 100644 index 0000000000000000000000000000000000000000..b315f6524bb6e2e3c74851607f26246a02e2f143 --- /dev/null +++ b/Lora/krekkov-ByChiAi_.json @@ -0,0 +1,8 @@ +{ + "sha256": "CCA80B9DEEF14DDE2132789ED2F824B2684AF363F0C03E587852CCB100C9B0D2", + "modelId": 1449434, + "modelVersionId": 1638755, + "activation text": "", + "description": "Any review or criticism is welcome since I want to continue training styles!!You can support me or ask for a commission on ko-fi!!https://ko-fi.com/chiaiartist https://ko-fi.com/chiaiartist", + "sd version": "Other" +} \ No newline at end of file diff --git a/Lora/krekkov-ByChiAi_.preview.png b/Lora/krekkov-ByChiAi_.preview.png new file mode 100644 index 0000000000000000000000000000000000000000..f4b5608e86cc2e5cb94075d3d66b6b9bd88e9ad1 --- /dev/null +++ b/Lora/krekkov-ByChiAi_.preview.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c17a8fe77a0d14ac4fa45ca01d7e38a86dd8302ad25e4af3ce8a6282b1b4f523 +size 5226638 diff --git a/Lora/krekkov-ByChiAi_.safetensors b/Lora/krekkov-ByChiAi_.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1d2c4cbb65b4c6a166e4cc612a7e799d0b56cff9 --- /dev/null +++ b/Lora/krekkov-ByChiAi_.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cca80b9deef14dde2132789ed2f824b2684af363f0c03e587852ccb100c9b0d2 +size 114851776 diff --git a/Lora/mrpoarty-000007.json b/Lora/mrpoarty-000007.json new file mode 100644 index 0000000000000000000000000000000000000000..21afc01e5cb0718f5d6476c6b5e6006f9201f3f1 --- /dev/null +++ b/Lora/mrpoarty-000007.json @@ -0,0 +1,5 @@ +{ + "sha256": "E087CC4754DF9CCE4D12BC8DCF3D742998F1590FD9CA2D1E793B13704B6D5BEE", + "modelId": "Model not found", + "modelVersionId": "Model not found" +} \ No newline at end of file diff --git a/Lora/mrpoarty-000007.safetensors b/Lora/mrpoarty-000007.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5896eb6c6cf613500d3bfffcc8f0755070f062d6 --- /dev/null +++ b/Lora/mrpoarty-000007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e087cc4754df9cce4d12bc8dcf3d742998f1590fd9ca2d1e793b13704b6d5bee +size 228463028 diff --git a/Lora/theodyss.json b/Lora/theodyss.json new file mode 100644 index 0000000000000000000000000000000000000000..b0b71d33c6cc445c6c8aa7d364f6704bbdd53f9e --- /dev/null +++ b/Lora/theodyss.json @@ -0,0 +1,8 @@ +{ + "sha256": "16BA94278520958A853354A034F1C84C41964607FD6561C9E708D9EC86CC6F89", + "modelId": 577041, + "modelVersionId": 1675885, + "activation text": "xothdys", + "description": "Will remove if requested", + "sd version": "Other" +} \ No newline at end of file diff --git a/Lora/theodyss.preview.png b/Lora/theodyss.preview.png new file mode 100644 index 0000000000000000000000000000000000000000..af66432d2747e99fb9737476b9a504f87873b044 --- /dev/null +++ b/Lora/theodyss.preview.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df2a385afdfd330775a24446f111b82818d99c96588f3a5772be32298d0cd183 +size 171440 diff --git a/Lora/theodyss.safetensors b/Lora/theodyss.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fce52e8ace9e9f4de740f6a5c966857a5b4bddb3 --- /dev/null +++ b/Lora/theodyss.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16ba94278520958a853354a034f1c84c41964607fd6561c9e708d9ec86cc6f89 +size 228467380 diff --git a/Lora/touching_grass_v0.2.json b/Lora/touching_grass_v0.2.json new file mode 100644 index 0000000000000000000000000000000000000000..a49c3a1d0dce165312d5bb800516fdb40edd6d16 --- /dev/null +++ b/Lora/touching_grass_v0.2.json @@ -0,0 +1,8 @@ +{ + "sha256": "75CF389D6C6B135B54F3715E36B9578BFB70C363ED9D5A7ECBE33FB3B3710EE7", + "modelId": 1429923, + "modelVersionId": 1666165, + "activation text": "", + "description": "Project: Touching GrassThe best LoRA for grass details.Trained on real world high-res photographs. The best data source I can think of for natural lighting, contrast and detail improvements.Why does this LoRA exist?To bring texture and lighting and background from reality to anime models.What is the difference between this and the Stabilizer LoRA https://civitai.com/models/971952?Stabilizer has very weak effects. Because the rule is \"don't break things\". So it may have no effect on super overfitted models. Also Stabilizer has another anime dataset to make anime characters look better.This LoRA is trained very hard and has much stronger effects, so it can \"overwrite\" those super overfitted models if you want. 100% real world images.What's this LoRA?This LoRA is for users who like raw and pure things and like to balance weights themselves.This LoRA is trained on a sub dataset of the Stabilizer LoRA.This sub dataset:Contains ~1K real world high quality photographs of objects and environment. No human. So it will not \"pollute\" your characters. Can be used on both anime and realistic models.Very diverse and creative.Has natural captions from LLM. Mainly because WD tagger v3 is really bad at real world images. Also because natural captions have more diverse vocabularies and can avoid overfitting.What's the effect?It really depends on your base model. Here is a quick comparations on WAI v13. With/without.Pixel level natural details. A so-called \"detailer\". But instead of training on AI images to amplify fake details from noise to generate more fake objects. This LoRA focuses on natural texture. Less flat and smooth feelings. Notice the food, clothes, light reflection on the table, depth of field and blurry background.Significantly improve background structural stability for anime models. Anime dataset doesn't contain much background knowledge. Most of are just \"simple background\". Even if some of them have some kind of background, they may be abstract art and lacking proper tags. So the base model will forget it or learn weird things during training. This LoRA was trained with tons of background/environment images with strong structural features.How to use?Trained on Illus v0.1. But also works on NoobAI.No trigger word needed.You don't have to set the patch strength for text encoder. This LoRA does not patch it.Lower your CFG scales (-30%) for better details.I got realistic faces on my anime characters.Don't blame this LoRA, it has zero knowledge of realistic faces. Most likely your base model was mixed with other realistic models, probably for better texture and lighting as well. It was already polluted. This LoRA may just active the polluted part because the training datasets are similar (both are from real world).Share merges using this LoRA is prohibited. FYI, there are hidden trigger words to print invisible watermark. It works well even if the merge strength is 0.05. I coded the watermark and detector myself. I don't want to use it, but I can.Update log(4/15/2025) v0.2:+30% images. Because there is a bug causing all avif files not being used in v0.1. Which is 30% of the dataset. lol.Changed some parameters. Stronger, cleaner and more stable effect.(4/02/2025) v0.1: init release.", + "sd version": "Other" +} \ No newline at end of file diff --git a/Lora/touching_grass_v0.2.preview.png b/Lora/touching_grass_v0.2.preview.png new file mode 100644 index 0000000000000000000000000000000000000000..52dd7a9ae93f7f4a7f1aa8604619728a479e7fb8 --- /dev/null +++ b/Lora/touching_grass_v0.2.preview.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3aa9f519fc84386a4d5a2c2f1135e6bdf5251e505e2bb1ed71b18a0093e3c7f4 +size 1311270 diff --git a/Lora/touching_grass_v0.2.safetensors b/Lora/touching_grass_v0.2.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7a401c3da6a5b953fc1189e837e9be1dd72308b7 --- /dev/null +++ b/Lora/touching_grass_v0.2.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75cf389d6c6b135b54f3715e36b9578bfb70c363ed9d5a7ecbe33fb3b3710ee7 +size 88008084