Upload 6 files

SDXL-2D/animagineXLV31_v30.civitai.info

@@ -0,0 +1,218 @@
+{
+    "id": 293564,
+    "modelId": 260267,
+    "name": "v3.0",
+    "createdAt": "2024-01-10T13:32:12.113Z",
+    "updatedAt": "2024-03-21T04:45:21.909Z",
+    "status": "Published",
+    "publishedAt": "2024-01-10T13:57:46.063Z",
+    "trainedWords": [],
+    "trainingStatus": null,
+    "trainingDetails": null,
+    "baseModel": "SDXL 1.0",
+    "baseModelType": "Standard",
+    "earlyAccessTimeFrame": 0,
+    "description": "<!--\nANIMAGINE XL 3.0\n\nHuggingface link: https://huggingface.co/cagliostrolab/animagine-xl-3.0\n\nGradio Demo : https://huggingface.co/spaces/Linaqruf/animagine-xl\n\nOfficial Blog Release: https://cagliostrolab.net/posts/animagine-xl-v3-release\n\nSupport us at: https://ko-fi.com/linaqruf\n\nOverview\n\nAnimagine XL 3.0 is the latest version of the sophisticated open-source anime text-to-image model, building upon the capabilities of its predecessor, Animagine XL 2.0. Developed based on Stable Diffusion XL, this iteration boasts superior image generation with notable improvements in hand anatomy, efficient tag ordering, and enhanced knowledge about anime concepts. Unlike the previous iteration, we focused to make the model learn concepts rather than aesthetic.\n\nAnimagine XL 3.0 was trained on a 2x A100 GPU with 80GB memory for 21 days or over 500 gpu hours. For further information please visit our official blog or huggingface repository.\n\nModel Details\n\n* Developed by: Cagliostro Research Lab\n\n* Model type: Diffusion-based text-to-image generative model\n\n* Model Description: Animagine XL 3.0 is engineered to generate high-quality anime images from textual prompts. It features enhanced hand anatomy, better concept understanding, and prompt interpretation, making it the most advanced model in its series.\n\n* License: Fair AI Public License 1.0-SD\n\n* Finetuned from model: Animagine XL 2.0\n-->",
+    "stats": {
+        "downloadCount": 77349,
+        "ratingCount": 1267,
+        "rating": 4.97,
+        "thumbsUpCount": 2375
+    },
+    "model": {
+        "name": "Animagine XL V3.1",
+        "type": "Checkpoint",
+        "nsfw": false,
+        "poi": false,
+        "description": "<!--\nAnimagine XL 3.1 is an update in the Animagine XL V3 series, enhancing the previous version, Animagine XL 3.0. This open-source, anime-themed text-to-image model has been improved for generating anime-style images with higher quality. It includes a broader range of characters from well-known anime series, an optimized dataset, and new aesthetic tags for better image creation. Built on Stable Diffusion XL, Animagine XL 3.1 aims to be a valuable resource for anime fans, artists, and content creators by producing accurate and detailed representations of anime characters.\n\nModel Details* Developed by: Cagliostro Research Lab\n\n* In collaboration with: SeaArt.ai\n\n* Model type: Diffusion-based text-to-image generative model\n\n* Model Description: Animagine XL 3.1 generates high-quality anime images from textual prompts. It boasts enhanced hand anatomy, improved concept understanding, and advanced prompt interpretation.\n\n* License: Fair AI Public License 1.0-SD\n\n* Fine-tuned from: Animagine XL 3.0\n\n\n\nUsage GuidelinesTag OrderingFor optimal results, it's recommended to follow the structured prompt template because we train the model like this:\n\n`1girl/1boy, character name, from what series, everything else in any order.\n`Special TagsAnimagine XL 3.1 utilizes special tags to steer the result toward quality, rating, creation date and aesthetic. While the model can generate images without these tags, using them can help achieve better results.\n\nQuality ModifiersQuality tags now consider both scores and post ratings to ensure a balanced quality distribution. We've refined labels for greater clarity, such as changing 'high quality' to 'great quality'.\n\n`\nQuality Modifier\tScore Criterion\nmasterpiece\t        > 95%\nbest quality\t        > 85% & \u2264 95%\ngreat quality\t        > 75% & \u2264 85%\ngood quality\t        > 50% & \u2264 75%\nnormal quality\t        > 25% & \u2264 50%\nlow quality\t        > 10% & \u2264 25%\nworst quality\t        \u2264 10%`Rating ModifiersWe've also streamlined our rating tags for simplicity and clarity, aiming to establish global rules that can be applied across different models. For example, the tag 'rating: general' is now simply 'general', and 'rating: sensitive' has been condensed to 'sensitive'.\n\n`\nRating Modifier\t    Rating Criterion\nsafe\t            General\nsensitive\t    Sensitive\nnsfw\t            Questionable\nexplicit, nsfw\t    Explicit`Year ModifierWe've also redefined the year range to steer results towards specific modern or vintage anime art styles more accurately. This update simplifies the range, focusing on relevance to current and past eras.\n\n`\nYear Tag\tYear Range\nnewest\t        2021 to 2024\nrecent\t        2018 to 2020\nmid\t        2015 to 2017\nearly\t        2011 to 2014\noldest\t        2005 to 2010`Aesthetic TagsWe've enhanced our tagging system with aesthetic tags to refine content categorization based on visual appeal. These tags are derived from evaluations made by a specialized ViT (Vision Transformer) image classification model, specifically trained on anime data. For this purpose, we utilized the model shadowlilac/aesthetic-shadow-v2, which assesses the aesthetic value of content before it undergoes training. This ensures that each piece of content is not only relevant and accurate but also visually appealing.\n\n`\nAesthetic Tag\t       Score Range\nvery aesthetic\t       > 0.71\naesthetic\t       > 0.45 & < 0.71\ndispleasing\t       > 0.27 & < 0.45\nvery displeasing       \u2264 0.27`Recommended settingsTo guide the model towards generating high-aesthetic images, use negative prompts like:\n\n`nsfw, lowres, (bad), text, error, fewer, extra, missing, worst quality, jpeg artifacts, low quality, watermark, unfinished, displeasing, oldest, early, chromatic aberration, signature, extra digits, artistic error, username, scan, [abstract]\n`For higher quality outcomes, prepend prompts with:\n\n`masterpiece, best quality, very aesthetic, absurdres\n`it\u2019s recommended to use a lower classifier-free guidance (CFG Scale) of around 5-7, sampling steps below 30, and to use Euler Ancestral (Euler a) as a sampler.\n\nMulti Aspect ResolutionThis model supports generating images at the following dimensions:\n\n`Dimensions\tAspect Ratio\n1024 x 1024\t1:1 Square\n1152 x 896\t9:7\n896 x 1152\t7:9\n1216 x 832\t19:13\n832 x 1216\t13:19\n1344 x 768\t7:4 Horizontal\n768 x 1344\t4:7 Vertical\n1536 x 640\t12:5 Horizontal\n640 x 1536\t5:12 Vertical`AcknowledgementsThe development and release of Animagine XL 3.1 would not have been possible without the invaluable contributions and support from the following individuals and organizations:\n\n* SeaArt.ai: Our collaboration partner and sponsor.\n\n* Shadow Lilac: For providing the aesthetic classification model, aesthetic-shadow-v2.\n\n* Derrian Distro: For their custom learning rate scheduler, adapted from LoRA Easy Training Scripts.\n\n* Kohya SS: For their comprehensive training scripts.\n\n* Cagliostrolab Collaborators: For their dedication to model training, project management, and data curation.\n\n* Early Testers: For their valuable feedback and quality assurance efforts.\n\n* NovelAI: For their innovative approach to aesthetic tagging, which served as an inspiration for our implementation.\n\nThank you all for your support and expertise in pushing the boundaries of anime-style image generation.\n\n\n\nLimitationsWhile Animagine XL 3.1 represents a significant advancement in anime-style image generation, it is important to acknowledge its limitations:\n\n* Anime-Focused: This model is specifically designed for generating anime-style images and is not suitable for creating realistic photos.\n\n* Prompt Complexity: This model may not be suitable for users who expect high-quality results from short or simple prompts. The training focus was on concept understanding rather than aesthetic refinement, which may require more detailed and specific prompts to achieve the desired output.\n\n* Prompt Format: Animagine XL 3.1 is optimized for Danbooru-style tags rather than natural language prompts. For best results, users are encouraged to format their prompts using the appropriate tags and syntax.\n\n* Anatomy and Hand Rendering: Despite the improvements made in anatomy and hand rendering, there may still be instances where the model produces suboptimal results in these areas.\n\n* Dataset Size: The dataset used for training Animagine XL 3.1 consists of approximately 870,000 images. When combined with the previous iteration's dataset (1.2 million), the total training data amounts to around 2.1 million images. While substantial, this dataset size may still be considered limited in scope for an \"ultimate\" anime model.\n\n* NSFW Content: Animagine XL 3.1 has been designed to generate more balanced NSFW content. However, it is important to note that the model may still produce NSFW results, even if not explicitly prompted.\n\nBy acknowledging these limitations, we aim to provide transparency and set realistic expectations for users of Animagine XL 3.1. Despite these constraints, we believe that the model represents a significant step forward in anime-style image generation and offers a powerful tool for artists, designers, and enthusiasts alike.\n\nLicenseBased on Animagine XL 3.0, Animagine XL 3.1 falls under Fair AI Public License 1.0-SD license, which is compatible with Stable Diffusion models\u2019 license. Key points:\n\n* Modification Sharing: If you modify Animagine XL 3.1, you must share both your changes and the original license.\n\n* Source Code Accessibility: If your modified version is network-accessible, provide a way (like a download link) for others to get the source code. This applies to derived models too.\n\n* Distribution Terms: Any distribution must be under this license or another with similar rules.\n\n* Compliance: Non-compliance must be fixed within 30 days to avoid license termination, emphasizing transparency and adherence to open-source values.\n\nThe choice of this license aims to keep Animagine XL 3.1 open and modifiable, aligning with open source community spirit. It protects contributors and users, encouraging a collaborative, ethical open-source community. This ensures the model not only benefits from communal input but also respects open-source development freedoms.\n\nFinally Cagliostro Lab Server open to public https://discord.gg/cqh9tZgbGc\n\nFeel free to join our discord server.\nIf you want to donate or buy us a coffee you can donate Here\n\nThank you very much ^_^\n-->",
+        "tags": [
+            "anime",
+            "base model"
+        ],
+        "allowNoCredit": true,
+        "allowCommercialUse": [
+            "Image",
+            "RentCivit",
+            "Rent"
+        ],
+        "allowDerivatives": true,
+        "allowDifferentLicense": false
+    },
+    "files": [
+        {
+            "id": 231047,
+            "sizeKB": 6775604.111328125,
+            "name": "animagineXLV31_v30.safetensors",
+            "type": "Model",
+            "pickleScanResult": "Success",
+            "pickleScanMessage": "No Pickle imports",
+            "virusScanResult": "Success",
+            "virusScanMessage": null,
+            "scannedAt": "2024-01-10T13:52:59.709Z",
+            "metadata": {
+                "format": "SafeTensor",
+                "size": "full",
+                "fp": "fp32"
+            },
+            "hashes": {
+                "AutoV1": "75F2F05B",
+                "AutoV2": "1449E5B0B9",
+                "SHA256": "1449E5B0B9DE87B0F414C5F29CB11CE3B3DC61FA2B320E784C9441720BF7B766",
+                "CRC32": "3283A76F",
+                "BLAKE3": "BA8B3384D287A2AE24E59D05898F92A39CCD56C28CD5560F854CF0900FBF8948",
+                "AutoV3": "4C4359A0C94D"
+            },
+            "primary": true,
+            "downloadUrl": "https://civitai.com/api/download/models/293564"
+        }
+    ],
+    "images": [
+        {
+            "url": "https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/a6e71784-afec-4a83-876f-1df167381e44/width=450/5352351.jpeg",
+            "nsfwLevel": 1,
+            "width": 1344,
+            "height": 1728,
+            "hash": "U8D+[20KD*s;~p%MkW9F=|RjRkx]_4jE00R+",
+            "type": "image",
+            "metadata": {
+                "hash": "U8D+[20KD*s;~p%MkW9F=|RjRkx]_4jE00R+",
+                "size": 4412704,
+                "width": 1344,
+                "height": 1728
+            },
+            "availability": "Public",
+            "meta": {
+                "steps": 28,
+                "prompt": "1girl, amiya \\(arknights\\), arknights, dirty face, outstretched hand, close-up, cinematic angle, foreshortening, dark, dark background, masterpiece, best quality",
+                "sampler": "Euler a",
+                "cfgScale": 7,
+                "negativePrompt": "nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name,"
+            }
+        },
+        {
+            "url": "https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/76e8f93e-678a-4976-8403-5a08bcd39034/width=450/5352345.jpeg",
+            "nsfwLevel": 1,
+            "width": 1344,
+            "height": 1728,
+            "hash": "UAH-ri009x^*pbSg=|D*~pIosCWX4nIo%LRQ",
+            "type": "image",
+            "metadata": {
+                "hash": "UAH-ri009x^*pbSg=|D*~pIosCWX4nIo%LRQ",
+                "size": 4841746,
+                "width": 1344,
+                "height": 1728
+            },
+            "availability": "Public",
+            "meta": {
+                "steps": 28,
+                "prompt": "1girl, c.c., code geass, white shirt, long sleeves, turtleneck, sitting, looking at viewer, eating, pizza, plate, fork, knife, table, chair, table, restaurant, cinematic angle, cinematic lighting, masterpiece, best quality",
+                "sampler": "Euler a",
+                "cfgScale": 7,
+                "negativePrompt": "nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name,"
+            }
+        },
+        {
+            "url": "https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/4153b9e0-64b3-48af-9eb2-d935bb3ea7db/width=450/5352352.jpeg",
+            "nsfwLevel": 1,
+            "width": 1728,
+            "height": 1344,
+            "hash": "U9HA;TrXO@k=#Tw|0LNZ00tRa0In_MNG?H%M",
+            "type": "image",
+            "metadata": {
+                "hash": "U9HA;TrXO@k=#Tw|0LNZ00tRa0In_MNG?H%M",
+                "size": 4880706,
+                "width": 1728,
+                "height": 1344
+            },
+            "availability": "Public",
+            "meta": {
+                "seed": 1966975782,
+                "steps": 28,
+                "prompt": "1girl, arima kana, oshi no ko, solo, idol, idol clothes, one eye closed, red shirt, black skirt, black headwear, gloves, stage light, singing, open mouth, crowd, smile, pointing at viewer, masterpiece, best quality",
+                "sampler": "Euler a",
+                "cfgScale": 7,
+                "negativePrompt": "nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, "
+            }
+        },
+        {
+            "url": "https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/dcfa3f5a-72f0-45bd-85d5-84824c1940bd/width=450/5352348.jpeg",
+            "nsfwLevel": 1,
+            "width": 1728,
+            "height": 1344,
+            "hash": "UMI4q*xrJW^+}r-;IoVrD%M_xZM_^*xt%1-p",
+            "type": "image",
+            "metadata": {
+                "hash": "UMI4q*xrJW^+}r-;IoVrD%M_xZM_^*xt%1-p",
+                "size": 4527845,
+                "width": 1728,
+                "height": 1344
+            },
+            "availability": "Public",
+            "meta": {
+                "seed": 2097324220,
+                "steps": 28,
+                "prompt": "1girl, higuchi madoka, idolmaster shiny colors, game cg, solo, looking viewer, outdoors, night, snow, blush, breath, cinematic angle, masterpiece, best quality",
+                "sampler": "Euler a",
+                "cfgScale": 7,
+                "negativePrompt": "nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name,"
+            }
+        },
+        {
+            "url": "https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/c8f8f31c-060f-4e30-a9b7-4848f2a7dd4e/width=450/5352346.jpeg",
+            "nsfwLevel": 1,
+            "width": 1728,
+            "height": 1344,
+            "hash": "UNI=cHIp9Z-;_MR*IoWBcGNG-UoJ%iR.wwM|",
+            "type": "image",
+            "metadata": {
+                "hash": "UNI=cHIp9Z-;_MR*IoWBcGNG-UoJ%iR.wwM|",
+                "size": 4272956,
+                "width": 1728,
+                "height": 1344
+            },
+            "availability": "Public",
+            "meta": {
+                "seed": 936248759,
+                "steps": 28,
+                "prompt": "1girl, toki \\(blue archive\\), blue archive, game cg, solo, double v, looking at viewer, upper body, cinematic angle, depth of field, outdoors, masterpiece, best quality",
+                "sampler": "Euler a",
+                "cfgScale": 7,
+                "negativePrompt": "nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name,"
+            }
+        },
+        {
+            "url": "https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/1047fffe-4d2a-4d63-bdc5-bbc91f26d09a/width=450/5352347.jpeg",
+            "nsfwLevel": 1,
+            "width": 1344,
+            "height": 1728,
+            "hash": "UFKwX*4n5S00_3R%%M8_~q0Kx]iwsm9Gxuog",
+            "type": "image",
+            "metadata": {
+                "hash": "UFKwX*4n5S00_3R%%M8_~q0Kx]iwsm9Gxuog",
+                "size": 3851171,
+                "width": 1344,
+                "height": 1728
+            },
+            "availability": "Public",
+            "meta": {
+                "steps": 28,
+                "prompt": "A boy and a girl, Emiya Shirou and Artoria Pendragon from fate series, having their breakfast in the dining room. Emiya Shirou wears white t-shirt and jacket. Artoria Pendragon wears white dress with blue neck ribbon. Rice, soup, and minced meats are served on the table. They look at each other while smiling happily, masterpiece, best quality",
+                "sampler": "Euler a",
+                "cfgScale": 7,
+                "negativePrompt": "nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name,"
+            }
+        }
+    ],
+    "downloadUrl": "https://civitai.com/api/download/models/293564",
+    "creator": {
+        "username": "CagliostroLab",
+        "image": null
+    },
+    "extensions": {
+        "sd_civitai_helper": {
+            "version": "1.8.4",
+            "last_update": 1712879038,
+            "skeleton_file": false
+        }
+    }
+}

SDXL-2D/animagineXLV31_v30.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1449e5b0b9de87b0f414c5f29cb11ce3b3dc61fa2b320e784c9441720bf7b766
+size 6938218610

SDXL-2D/baxlBlueArchiveFlatCelluloidStyleFineTune_xlv3.civitai.info

@@ -0,0 +1,681 @@
+{
+    "id": 426588,
+    "modelId": 212253,
+    "name": "XLv3-\u0394",
+    "createdAt": "2024-04-03T18:14:04.442Z",
+    "updatedAt": "2024-04-05T15:59:32.050Z",
+    "status": "Published",
+    "publishedAt": "2024-04-05T15:59:32.047Z",
+    "trainedWords": [],
+    "trainingStatus": null,
+    "trainingDetails": null,
+    "baseModel": "SDXL 1.0",
+    "baseModelType": "Standard",
+    "earlyAccessTimeFrame": 0,
+    "description": "<!--\nBase model change to Kohaku Delta.\n-->",
+    "stats": {
+        "downloadCount": 746,
+        "ratingCount": 0,
+        "rating": 0,
+        "thumbsUpCount": 110
+    },
+    "model": {
+        "name": "BAXL | Blue Archive Flat Celluloid Style Fine-tune | \u78a7\u84dd\u6863\u6848\u8d5b\u7490\u7490\u5e73\u6d82\u753b\u98ce [Kohaku \u0394 & Animagine XL v3]",
+        "type": "Checkpoint",
+        "nsfw": false,
+        "poi": false,
+        "description": "<!--\nBAXLv3 is up now!Focus on generalization ability, cover art style of most copyright characters without catastrophic forgetting / overfitting.\n\ntest img @QR0W_\n\n\nWhat you should expected from this update:\n\n* Better generalization\n\n* Closer to Blue Archive style\n\n* Beautiful glare\n\n* Much improved LoRA compatibility based on Kohaku\u0394.\n\n\n\nWhat you should NOT expected from this update:\n\n* Better anatomy, always good hands and feet\n\n* easy to use\n\n* focus on given prompts (compare to previous version)\n\n* multiple person / nsfw support (this is not gonna get any close to pony.)\n\n* detailed background\n\n\n\nHow-to:Prompting logic is same to Kohaku\u0394.\n\n`1girl, <character>, <general tag>, <quality tag>`\n\nNegative:\n\n`lowres, error, worst quality, low quality, jpeg artifacts, watermark, signature, username`\n\nKeep prompt clean and tidy. Suggest prompt length < 75 tokens.\n\n\n\nSuggetion:\n\n* CFG: 4-7 \uff08higher will have slightly better anatomy\uff09\n\n* Sampler: Euler A @ 25steps\n\n* Resolution: 768 - 1792(ultrawide only), +32 each step.\n\n* Use DanTagGen.\n\n* Set a low temperature (<1)\n\n* Ban words: `sketch, comic, flat color, .*official.*, .*boy.*, mecha, no humans, text, pixel art, speech bubble`\n\n* Total tag length: short\n\n* Use Hires.Fix\n\n* Upscaler: DATx2\n\n* Denoising: 0.4-0.5\n\n* Use ADetailer.\n\n* face_yolov8n.pt\n\n* If you want generate typical color, put color scheme to at first.\n\n\n\nWhat's difference:Base model switch to Kohaku\u0394 rev1.\n\nReason\n\n* Aesthetic rating which AniXL used is NOT friendly to Celluloid art style, quality / negative tags of AniXL are effortless, sometimes even drawback for drawing clean, thin lines. Also it seems like AniXL has some overfitted characters.\n\n* \ud83d\udc46TBH, I haven't use same training methods on AniXL3.1 yet. Maybe it can be fixed by the final training config I use.\n\n* Meanwhile, Kohaku\u0394 is undertrained, which means flexible, more friendly to fine-tune art style.\n\n* I have no idea how to tag like AniXL3.1, but I know how to tag like Kohaku\u0394, since I could get the exact same dataset from Hakubooru.\n\n\n\nBetter generalization & horizonal composition.\n\n* Kohaku\u0394 rev1 is not good at anatomy & composition, due to lack of training time (dual 3090 bro, what you expected).\n\n* Due to Regularization, this fine-tune do make things better (especially horizonal image), but I'm not gonna lie you, BAXLv3-\u0394 is VERY EASY to generate bad hand / extra legs, get worse if the prompts have problems (too long / semantic repetition / immoderate tag order).\n\n\n\nRegularization / Datasets Update.\n\n* Regularization Danbooru Dataset, class token=solo:\n\n* 1000+ horizonal image\n\n* fav count > 30\n\n* tag with \"1girl, solo\"\n\n* 1000+ vertical image\n\n* fav count > 30\n\n* tag with \"1girl, solo\"\n\n* artist who is celluloid art style & BA art style imitator\n\n* Dataset update to 0068 events CG, include 5th PV screenshots.\n\n\n\nTraining Details:* Image count: 574 without repeat.\n\n* min_bucket_reso = 256\n\n* max_bucket_reso = 4096\n\n* bucket_reso_steps = 32\n\n* train_batch_size = 2\n\n* gradient_accumulation_steps = 32\n\n* learning_rate = 7.5e-6 Unet only\n\n* lr_scheduler = \"constant_with_warmup\"\n\n* lr_warmup_steps = 100\n\n* optimizer_type = \"Lion8bit\"\n\n* min_snr_gamma = 5\n\n* Batch size = 2\n\n* mixed_precision = \"fp16\"\n\n* full_fp16 = true\n\n* optimizer_args = [ \"weight_decay=0.1\", \"betas=0.9,0.95\" ]\n\n* shuffle_caption = true\n\n* weighted_captions = false\n\n* keep_tokens = 0\n\n* caption_tag_dropout_rate = 0.1\n\n\n\nKnown issues:* `halo` / `heterochromia` / `.*focus.*` seems to be overfitted in some circumstances. Can be helped by put them in negative tags.\n\n* Background is not stable, keen to draw something unnecessary even if you type `simple background, white background`\n\n\n\n\n\nLicense & Disclaimer* License:\n\nFair AI Public License 1.0-SD\n\n\n\n* Dislcaimer:\n\nAccording to Blue Archive's Fanart Guidelines ( JP | CN ), this model shall not be used for any kind of commercial use, including but not limited to selling this model or merges of this model, selling image generated by this model or merges of this model, or 'paid member exclusive' for monetization platforms like Patreon/Fanbox/etc.\n\n\n\n===========XLv2 INFO===========TL; DR:Based on Animagine XL V3, use Blue Archive's official artwork as fine-tune dataset for its art style. You are prohibited to use this model for any kind of commercial use. Please read the disclaimer below before you use this model.\n\n\n\nHow-to:* Suggest prompt order:\n\n* character name, 1girl, other tags, quality tags,\n\n* Suggest quality tags (please delete other quality tags in prompts):\n\n* `flat_coating clear_color highres absurdres best_quality`\n\n* DO NOT USE `masterpiece` if you are generating genral images. It will ruin the flat coating.\n\n* Suggest negative:\n\n* `nsfw, lowres, worst quality, low quality, bad perspective, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, jpeg artifacts, signature, watermark, username, artist name`\n\n* DO NOT USE `blurry` as negative prompts.\n\n* Suggest Resolution: same to A3XL, but limited to 1600x900 vertical, horizonal is lower.\n\n* Higher resolution = Closer to BA style\n\n* CFG 5 Euler A step 25\n\n* You can treat this like Animagine XL V3, all tag still work at same methods.\n\n* LoRA based on Animagine XL V3 will work fine on it.\n\n* Suggest Upscaler: AnimeVideo v3\n\n* No color scheme training\n\n* Feel free to give feedback, I need your suggestion for further developments.\n\n\n\nDisclaimer:Animagine XL V3's license asked that merges of this model should be released as same permissions, which is allowed user to use generation service or sell generated images of the model.\n\nBut according to Blue Archive's Fanart Guidelines ( JP | CN ), this model (BArtstyle) shall not be used for any kind of commercial use, including but not limited to selling this model or merges of this model, selling image generated by this model or merges of this model, or 'paid member exclusive' for monetization platforms like Patreon/Fanbox/etc.\n\nThe license change of this model is permitted by Cagliostro Research Lab, the author of Animagine XL. Once again, I sincerely thank them for their understanding and dedication for open-source community. (Permission Source)\n\n\n\n\u514d\u8d23\u58f0\u660e:\u6839\u636e Animagine XL V3 \u7684\u8bb8\u53ef\u8bc1\uff0c\u57fa\u4e8e\u8be5\u6a21\u578b\u7684\u884d\u751f\u6a21\u578b\u5e94\u4ee5\u76f8\u540c\u6388\u6743\u65b9\u5f0f\u516c\u5f00\uff0c\u5373\u5141\u8bb8\u7528\u6237\u4f7f\u7528\u7ebf\u4e0a\u751f\u6210\u670d\u52a1\uff0c\u6216\u552e\u5356\u8be5\u6a21\u578b\u751f\u6210\u7684\u56fe\u7247\u3002\n\n\u4f46\u6839\u636e\u300a<\u851a\u84dd\u6863\u6848>\u540c\u4eba\u521b\u4f5c\u6307\u5f15\u300b ( \u65e5\u6587 | \u4e2d\u6587 )\uff0c\u6b64\u6a21\u578b\uff08BArtstyle\uff09\u4e0d\u5f97\u7528\u4e8e\u4efb\u4f55\u5f62\u5f0f\u7684\u5546\u4e1a\u7528\u9014\uff0c\u5305\u62ec\u4f46\u4e0d\u9650\u4e8e\u552e\u5356\u8be5\u6a21\u578b\u53ca\u5176\u884d\u751f\u6a21\u578b\u81ea\u8eab\u6216\u5176\u751f\u6210\u7684\u56fe\u7247\uff0c\u6216Patreon/Fanbox\u7b49\u4f17\u7b79\u5e73\u53f0\u7684\u201c\u8ba2\u9605\u4f1a\u5458\u9650\u5b9a\u201d\u670d\u52a1\u3002\n\n\u8be5\u8bb8\u53ef\u8bc1\u6388\u6743\u8303\u56f4\u53d8\u66f4\u5f97\u5230 Animagine XL \u4f5c\u8005 Cagliostro Research Lab \u7684\u8bb8\u53ef\u3002\n\n\u5728\u8fd9\u91cc\u518d\u6b21\u611f\u8c22\u4ed6\u4eec\u7684\u7406\u89e3\uff0c\u4ee5\u53ca\u4ed6\u4eec\u5bf9\u4e8e\u5f00\u6e90\u793e\u533a\u7684\u8d21\u732e\u3002\uff08\u6388\u6743\u6765\u6e90\uff09\n\n\n\n===========XLv1 INFO===========How-to:This model is in ALPHA phase, pretty much undertrained, only works perfect for Blue Archive's characters.\n\n* You can treat this like Animagine XL V3, all tag still work at same methods.\n\n* LoRA based on Animagine XL V3 will work fine on it.\n\n* Suggest Upscaler: AnimeVideo v3\n\n* Still trained with color tags like BArtstyleDBv1, but seems not very effective.\n\n* Feel free to give feedback, I need your suggestion for further developments.\n\n\n\nTraining Details:AdamW8bit\n\n200 Images@1024x1024\n\n200 epoch@batch size 1\n\nUNET: 1E-5\n\nTE1/TE2: 5E-6\n\nCosine with 15 Restarts\n\n\n\n===========DBv1 INFO===========How-to:* Positive Prompts:\n\n* Just like BArtstyle LoRA, color scheme still work, and I managed to make these typical color like `blue theme` or `pink theme` much closer to original data without overfitting.\n\n* Natural Language + Low CFG (4.5-6) + Roll dices + cherry-pick > \"quality tags\"\n\n* From my test, about 30% image should be good enough at first glance. If you can't get similar result, check if there are any duplicate/conflict tags in your prompt, shrink it and lower your CFG.\n\n* Negative Prompts:\n\n* DO NOT USE FCKING LONG NEGATIVE PROMPTS UNLESS YOU KNOW WHAT ARE YOU DOING!!!\n\n* For randomly generate, simple EasyNegativeV2 is good enough.\n\n* You can try to add `glowing, 3d, painting \\(medium\\), photorealistic, nsfw` in negative prompts if you think this model is still have too much CounterFeit artstyle, but I can't guarantee the effect.\n\n* VAE: WD1-4-kl-f8-anime2-bless09.ckpt\n\n* Sampler: Euler A\n\n* step 50-100\n\n* Yeh, CHAD Euler A still better than Virgin DPM\n\n* Upscaler: AnimeVideo v3\n\n* step 10-15\n\n* Denoising 0.45-0.55\n\nBase Model:\n\n* Counterfeit V3-fp16-fix\n\n* After 6 MONTHS wait, author has released a vae fix version of CFv3. Original version had a serious VAE issue that make all the LoRA of CFv3 is bit broken, even if you replace the VAE won't help. Strongly recommend to update if you use it.\n\n* It seems like it is the ONLY TRAINING model that is capable with NAI 1.0 LoRA. That means only this model is good for fine-tuning\n\nDataset:\n\n* 200 images from Blue Archive's Official Artwork + flip, 400 in total.\n\n* TOTALLY OVERHAULED DATASET COMPARE WITH BArtstyle LoRA.\n\n* Highest resolution I could found, cropped to improve dataset quality\n\n* Use XnConvert Downscale to 1280x1280\n\nTraining Setting:\n\n* OPTIMIZER: AdamW8bit\n\n* SCHEDULER: Constant with Warmup\n\n* Warmup to 10% of total steps.\n\n* UNET LR: 1e-6\n\n* TE LR: 1.25-7\n\n* 1/8 of UNET LR as suggestion\n\n* Stop TE Training at 50% of total steps.\n\n* EPOCH: 100\n\n* BATCH SIZE: 1\n\n* STEP: 40000\n\n* RES: 1280X1280\n\n* TIME: 10H27M\n-->",
+        "tags": [
+            "anime",
+            "style",
+            "art style",
+            "blue archive",
+            "game cg",
+            "mobile game",
+            "kohaku",
+            "styles",
+            "animagine xl"
+        ],
+        "allowNoCredit": true,
+        "allowCommercialUse": [
+            "RentCivit",
+            "Rent"
+        ],
+        "allowDerivatives": true,
+        "allowDifferentLicense": false
+    },
+    "files": [
+        {
+            "id": 347937,
+            "sizeKB": 6775430.310546875,
+            "name": "baxlBlueArchiveFlatCelluloidStyleFineTune_xlv3.safetensors",
+            "type": "Model",
+            "pickleScanResult": "Success",
+            "pickleScanMessage": "No Pickle imports",
+            "virusScanResult": "Success",
+            "virusScanMessage": null,
+            "scannedAt": "2024-04-03T19:24:09.074Z",
+            "metadata": {
+                "format": "SafeTensor",
+                "size": "full",
+                "fp": "fp16"
+            },
+            "hashes": {
+                "AutoV1": "D3D5476F",
+                "AutoV2": "95AFFD8C8F",
+                "SHA256": "95AFFD8C8F664E6F30C1C5DD54723EACF1DBF3F02DA15CB82A67A21EB003875F",
+                "CRC32": "228B04AF",
+                "BLAKE3": "A771DB7FF55DB789E1AEE5C304AFE3782B86A931E489C64EAAC72BD3099CC3B7",
+                "AutoV3": "D84E6A7A6B65"
+            },
+            "primary": true,
+            "downloadUrl": "https://civitai.com/api/download/models/426588"
+        }
+    ],
+    "images": [
+        {
+            "url": "https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/07367b4e-9bc1-4b20-a027-f8079d2171fe/width=450/9171232.jpeg",
+            "nsfwLevel": 1,
+            "width": 1160,
+            "height": 1880,
+            "hash": "UdM7$DD$xZ?c~q%Mofog?bx]ozWV%MRPM{D%",
+            "type": "image",
+            "metadata": {
+                "hash": "UdM7$DD$xZ?c~q%Mofog?bx]ozWV%MRPM{D%",
+                "size": 1593774,
+                "width": 1160,
+                "height": 1880
+            },
+            "availability": "Public",
+            "meta": {
+                "ENSD": "31337",
+                "Size": "832x1344",
+                "seed": 1263769734,
+                "Model": "BArtstyleDB-XL-Kohaku\u00ce\u0094-v3-11-000025",
+                "steps": 25,
+                "hashes": {
+                    "model": "95affd8c8f"
+                },
+                "prompt": "1girl, \nnoa \\(blue archive\\),  \nsolo, shirt tucked in, shirt, multicolored hair, collared shirt, pantyhose, white skirt, jacket partially removed, knees up, purple eyes, jacket, necktie, open clothes, open jacket, very long hair, medium breasts, heart, blue necktie, black pantyhose, miniskirt, blue hair, headphones, two-sided fabric, arm support, long sleeves, feet out of frame, id card, white background, heart of string, simple background, halo, two-sided jacket, sidelocks, looking at viewer, gradient hair, sitting, one eye closed, long hair, white jacket, mechanical halo, white shirt, smile, skirt, breasts, pleated skirt, suit, closed mouth, artist name, \nbest quality, masterpiece, highres, absurdres",
+                "Version": "v1.8.0",
+                "sampler": "Euler a",
+                "Emphasis": "No norm",
+                "cfgScale": 5,
+                "clipSkip": 2,
+                "Mask blur": "4",
+                "resources": [
+                    {
+                        "hash": "95affd8c8f",
+                        "name": "BArtstyleDB-XL-Kohaku\u00ce\u0094-v3-11-000025",
+                        "type": "model"
+                    }
+                ],
+                "Model hash": "95affd8c8f",
+                "Hires steps": "15",
+                "Inpaint area": "Only masked",
+                "Hires upscale": "1.4",
+                "Hypertile VAE": "True",
+                "Hires upscaler": "4x-UltraSharp",
+                "negativePrompt": "armor, weapon, nsfw, lowres, error, worst quality, low quality, jpeg artifacts, signature, username, blurry, chibi, text",
+                "ADetailer model": "face_yolov8s.pt",
+                "ADetailer version": "24.3.1",
+                "Denoising strength": "0.4",
+                "ADetailer mask blur": "4",
+                "ADetailer model 2nd": "hand_yolov8n.pt",
+                "Masked area padding": "32",
+                "ADetailer confidence": "0.3",
+                "ADetailer dilate erode": "4",
+                "ADetailer mask blur 2nd": "4",
+                "ADetailer confidence 2nd": "0.4",
+                "ADetailer inpaint padding": "32",
+                "ADetailer dilate erode 2nd": "4",
+                "ADetailer denoising strength": "0.4",
+                "ADetailer inpaint only masked": "True",
+                "ADetailer inpaint padding 2nd": "32",
+                "ADetailer denoising strength 2nd": "0.5",
+                "ADetailer inpaint only masked 2nd": "True"
+            }
+        },
+        {
+            "url": "https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/ddf7731e-894c-48b9-a3dc-6922c9e63f54/width=450/9202965.jpeg",
+            "nsfwLevel": 1,
+            "width": 1160,
+            "height": 1880,
+            "hash": "U7HK*P00~6-?=MNXDg%200sk9Zn+0L?It9NG",
+            "type": "image",
+            "metadata": {
+                "hash": "U7HK*P00~6-?=MNXDg%200sk9Zn+0L?It9NG",
+                "size": 2092858,
+                "width": 1160,
+                "height": 1880
+            },
+            "availability": "Public",
+            "meta": {
+                "ENSD": "31337",
+                "Size": "832x1344",
+                "seed": 3149052496,
+                "Model": "BArtstyleDB-XL-Kohaku\u00ce\u0094-v3-11-000025",
+                "steps": 25,
+                "hashes": {
+                    "model": "95affd8c8f"
+                },
+                "prompt": "1girl solo 1girl, rem \\(re:zero\\), re:zero kara hajimeru isekai seikatsu corset ivory tower blue moon wasteland-highres absurdres best-quality safe masterpiece",
+                "Version": "v1.8.0",
+                "sampler": "Euler a",
+                "Emphasis": "No norm",
+                "cfgScale": 4.5,
+                "clipSkip": 2,
+                "Mask blur": "4",
+                "resources": [
+                    {
+                        "hash": "95affd8c8f",
+                        "name": "BArtstyleDB-XL-Kohaku\u00ce\u0094-v3-11-000025",
+                        "type": "model"
+                    }
+                ],
+                "Model hash": "95affd8c8f",
+                "Hires steps": "15",
+                "Inpaint area": "Only masked",
+                "Hires upscale": "1.4",
+                "Hypertile VAE": "True",
+                "TagSep Prompt": {},
+                "Hires upscaler": "4x-UltraSharp",
+                "negativePrompt": "nsfw lowres error worst-quality low-quality normal-quality jpeg-artifacts signature username",
+                "ADetailer model": "face_yolov8s.pt",
+                "TagSep Negative": {},
+                "Wildcard prompt": "1girl solo __character__ __\u00e4\u00ba\u00ba\u00e7\u0089\u00a9-\u00e8\u00a1\u00a3\u00e6\u009c\u008d__ __\u00e8\u0089\u00b2\u00e5\u00bd\u00a9-118\u00e8\u0089\u00b2__ __\u00e4\u00ba\u00ba\u00e6\u0096\u0087\u00e6\u0099\u00af\u00e8\u00a7\u0082-\u00e5\u00bb\u00ba\u00e7\u00ad\u0091__ __\u00e8\u0087\u00aa\u00e7\u0084\u00b6\u00e6\u0099\u00af\u00e8\u00a7\u0082-\u00e5\u00a4\u00a9\u00e8\u00b1\u00a1__ __\u00e8\u0087\u00aa\u00e7\u0084\u00b6\u00e6\u0099\u00af\u00e8\u00a7\u0082-\u00e5\u009c\u00ba\u00e6\u0099\u00af__-highres absurdres best-quality safe masterpiece",
+                "ADetailer version": "24.3.1",
+                "Denoising strength": "0.4",
+                "ADetailer mask blur": "4",
+                "Masked area padding": "32",
+                "ADetailer confidence": "0.3",
+                "ADetailer dilate erode": "4",
+                "ADetailer inpaint padding": "32",
+                "ADetailer denoising strength": "0.4",
+                "ADetailer inpaint only masked": "True"
+            }
+        },
+        {
+            "url": "https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/0c0d365a-179c-4d69-8fec-e3a1acf8ed2d/width=450/9234715.jpeg",
+            "nsfwLevel": 1,
+            "width": 1184,
+            "height": 2176,
+            "hash": "UWOMpu_NIq?bDhNKN{eo4oM{NJV?Iospr=tS",
+            "type": "image",
+            "metadata": {
+                "hash": "UWOMpu_NIq?bDhNKN{eo4oM{NJV?Iospr=tS",
+                "size": 1838200,
+                "width": 1184,
+                "height": 2176
+            },
+            "availability": "Public",
+            "meta": {
+                "ENSD": "31337",
+                "Size": "768x1408",
+                "seed": 2282089594,
+                "Model": "BArtstyleDB-XL-Kohaku\u00ce\u0094-v3-11-000025",
+                "steps": 25,
+                "hashes": {
+                    "model": "95affd8c8f"
+                },
+                "prompt": "1girl\nmari \\(blue archive\\)\nbare legs, blue eyes, blush, fox ears, fox girl, from above, hair between eyes, halo, hand between legs, heart print, indoors, long hair, looking at viewer, looking up, necklace, off shoulder, on bed\nnewest, pillow, shirt, bare shoulders, smile, window, between legs, closed mouth, wariza, animal ear fluff, bed, clothes writing, solo, blue hair, depth of field, blurry, animal ears, blurry background, very long hair, jewelry, heart, sitting, white shirt, print shirt, \n absurdres, highres, sensitive",
+                "Version": "v1.8.0",
+                "sampler": "Euler a",
+                "Emphasis": "No norm",
+                "cfgScale": 7,
+                "clipSkip": 2,
+                "Mask blur": "5",
+                "resources": [
+                    {
+                        "hash": "95affd8c8f",
+                        "name": "BArtstyleDB-XL-Kohaku\u00ce\u0094-v3-11-000025",
+                        "type": "model"
+                    }
+                ],
+                "Model hash": "95affd8c8f",
+                "Hires steps": "10",
+                "Inpaint area": "Only masked",
+                "Hires upscale": "1.55",
+                "Hypertile VAE": "True",
+                "Hires upscaler": "DAT_x2",
+                "negativePrompt": "light, candlelight, candlestand, candle, halo, monochromic, nsfw, lowres, error, worst quality, low quality, jpeg artifacts, signature, username, blurry, chibi, text, copyright name, watermark, azur lane",
+                "ADetailer model": "face_yolov8n.pt",
+                "ADetailer version": "24.3.5",
+                "Denoising strength": "0.2",
+                "ADetailer mask blur": "5",
+                "Masked area padding": "64",
+                "ADetailer confidence": "0.5",
+                "ADetailer dilate erode": "4",
+                "ADetailer inpaint padding": "64",
+                "ADetailer denoising strength": "0.2",
+                "ADetailer inpaint only masked": "True"
+            }
+        },
+        {
+            "url": "https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/0a98b920-abfd-47f1-8e21-2f194ff9285f/width=450/9090080.jpeg",
+            "nsfwLevel": 1,
+            "width": 1296,
+            "height": 1728,
+            "hash": "UIKwOr4.tm%f_M8_OYaeXSIUr@XS?b%L?b%2",
+            "type": "image",
+            "metadata": {
+                "hash": "UIKwOr4.tm%f_M8_OYaeXSIUr@XS?b%L?b%2",
+                "size": 2137974,
+                "width": 1296,
+                "height": 1728
+            },
+            "availability": "Public",
+            "meta": {
+                "ENSD": "31337",
+                "Size": "960x1280",
+                "seed": 2043347489,
+                "Model": "BArtstyleDB-XL-Kohaku\u00ce\u0094-v3-11-000025",
+                "steps": 25,
+                "hashes": {
+                    "model": "95affd8c8f"
+                },
+                "prompt": "1girl, \nsolo, 1girl, ouga saki, amaryllis gumi, windmill, starry background\nhighres, holding weapon, style parody, white background, wings, holding, sword, pointing, red eyes, parody, standing, weapon, holding sword, open hand, head wings, tokusatsu, \nbest quality, masterpiece, absurdres, safe",
+                "Version": "v1.8.0",
+                "sampler": "Euler a",
+                "Emphasis": "No norm",
+                "cfgScale": 4.5,
+                "clipSkip": 2,
+                "Mask blur": "4",
+                "resources": [
+                    {
+                        "hash": "95affd8c8f",
+                        "name": "BArtstyleDB-XL-Kohaku\u00ce\u0094-v3-11-000025",
+                        "type": "model"
+                    }
+                ],
+                "Model hash": "95affd8c8f",
+                "Hires steps": "15",
+                "Inpaint area": "Only masked",
+                "Hires upscale": "1.35",
+                "Hypertile VAE": "True",
+                "Hires upscaler": "4x-UltraSharp",
+                "negativePrompt": "nsfw, lowres, error, worst quality, low quality, normal quality, jpeg artifacts, signature,  username,",
+                "ADetailer model": "face_yolov8s.pt",
+                "Wildcard prompt": {},
+                "ADetailer version": "24.3.1",
+                "Denoising strength": "0.4",
+                "ADetailer mask blur": "4",
+                "Masked area padding": "32",
+                "ADetailer confidence": "0.3",
+                "ADetailer dilate erode": "4",
+                "ADetailer inpaint padding": "32",
+                "ADetailer denoising strength": "0.4",
+                "ADetailer inpaint only masked": "True"
+            }
+        },
+        {
+            "url": "https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/a94bbbbb-78fa-4e02-9bd6-cd1752ba36d7/width=450/9089625.jpeg",
+            "nsfwLevel": 1,
+            "width": 1296,
+            "height": 1728,
+            "hash": "UUKKc[9Zo}^+~WtSIUxtbvxb^+NGIo%MxaS1",
+            "type": "image",
+            "metadata": {
+                "hash": "UUKKc[9Zo}^+~WtSIUxtbvxb^+NGIo%MxaS1",
+                "size": 1751142,
+                "width": 1296,
+                "height": 1728
+            },
+            "availability": "Public",
+            "meta": {
+                "ENSD": "31337",
+                "Size": "960x1280",
+                "seed": 2017462485,
+                "Model": "BArtstyleDB-XL-Kohaku\u00ce\u0094-v3-11-000025",
+                "steps": 25,
+                "hashes": {
+                    "model": "95affd8c8f"
+                },
+                "prompt": "1girl, \nkoharu \\(blue archive\\),  \n@_@, beret, black hat, black shirt, black wings, blush, cropped legs, halo, head wings, long hair, pink eyes, pink hair, pleated skirt, red halo, red skirt, sailor collar, sailor shirt, sleeves past fingers, sleeves past wrists, solo, white background, white sailor collar, wings, hair between eyes, shirt, simple background, winged hat, open mouth, nose blush, spaghetti strap, pink halo, looking at viewer, hat, twintails, black headwear, skirt, \nbest quality, masterpiece, highres, absurdres, safe",
+                "Version": "v1.8.0",
+                "sampler": "Euler a",
+                "Emphasis": "No norm",
+                "cfgScale": 4.5,
+                "clipSkip": 2,
+                "Mask blur": "4",
+                "resources": [
+                    {
+                        "hash": "95affd8c8f",
+                        "name": "BArtstyleDB-XL-Kohaku\u00ce\u0094-v3-11-000025",
+                        "type": "model"
+                    }
+                ],
+                "Model hash": "95affd8c8f",
+                "Hires steps": "15",
+                "Inpaint area": "Only masked",
+                "Hires upscale": "1.35",
+                "Hypertile VAE": "True",
+                "Hires upscaler": "4x-UltraSharp",
+                "negativePrompt": "nsfw, lowres, error, worst quality, low quality, normal quality, jpeg artifacts, signature,  username,",
+                "ADetailer model": "face_yolov8s.pt",
+                "ADetailer version": "24.3.1",
+                "Denoising strength": "0.4",
+                "ADetailer mask blur": "4",
+                "Masked area padding": "32",
+                "ADetailer confidence": "0.3",
+                "ADetailer dilate erode": "4",
+                "ADetailer inpaint padding": "32",
+                "ADetailer denoising strength": "0.4",
+                "ADetailer inpaint only masked": "True"
+            }
+        },
+        {
+            "url": "https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/c0d1aeff-6f63-43a1-859f-d1975de1ba47/width=450/9167553.jpeg",
+            "nsfwLevel": 1,
+            "width": 1744,
+            "height": 1080,
+            "hash": "UcLWbY%g_4%L-;t7x[NG9sWA%1s:oft7s;Rj",
+            "type": "image",
+            "metadata": {
+                "hash": "UcLWbY%g_4%L-;t7x[NG9sWA%1s:oft7s;Rj",
+                "size": 1482287,
+                "width": 1744,
+                "height": 1080
+            },
+            "availability": "Public",
+            "meta": {
+                "ENSD": "31337",
+                "Size": "1344x832",
+                "seed": 2373281615,
+                "Model": "BArtstyleDB-XL-Kohaku\u00ce\u0094-v3-11-000025",
+                "steps": 25,
+                "hashes": {
+                    "model": "95affd8c8f"
+                },
+                "prompt": "1girl, \nsolo, 1girl, houshou marine \\(summer\\), hololive, annoyed, crossed legs, arms at side, sky, airfield\nmasterpiece, long hair, open mouth, hair between eyes, purple eyes, looking at viewer, hat, purple hair, white background, upper body, sugimori ken'ichirou, baseball cap, blush, pink background, simple background, \nbest quality, highres, absurdres, safe",
+                "Version": "v1.8.0",
+                "sampler": "Euler a",
+                "Emphasis": "No norm",
+                "cfgScale": 4.5,
+                "clipSkip": 2,
+                "Mask blur": "5",
+                "resources": [
+                    {
+                        "hash": "95affd8c8f",
+                        "name": "BArtstyleDB-XL-Kohaku\u00ce\u0094-v3-11-000025",
+                        "type": "model"
+                    }
+                ],
+                "Model hash": "95affd8c8f",
+                "Hires steps": "15",
+                "Inpaint area": "Only masked",
+                "Hires upscale": "1.3",
+                "Hypertile VAE": "True",
+                "Hires upscaler": "DAT x4",
+                "negativePrompt": "halo, monochromic, nsfw, lowres, error, worst quality, low quality, jpeg artifacts, signature, username, blurry, chibi, text, copyright name, watermark, copyright, logo",
+                "ADetailer model": "face_yolov8n.pt",
+                "Wildcard prompt": {},
+                "ADetailer version": "24.3.5",
+                "Denoising strength": "0.2",
+                "ADetailer mask blur": "5",
+                "Masked area padding": "64",
+                "ADetailer confidence": "0.5",
+                "ADetailer dilate erode": "4",
+                "ADetailer inpaint padding": "64",
+                "ADetailer denoising strength": "0.2",
+                "ADetailer inpaint only masked": "True"
+            }
+        },
+        {
+            "url": "https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/330d49e5-f828-46e5-984a-ff79ff5562b3/width=450/9089622.jpeg",
+            "nsfwLevel": 16,
+            "width": 1808,
+            "height": 1120,
+            "hash": "U5IOFb00~q~E0000.800Sb?F00WG4:4n?bI;",
+            "type": "image",
+            "metadata": {
+                "hash": "U5IOFb00~q~E0000.800Sb?F00WG4:4n?bI;",
+                "size": 1909249,
+                "width": 1808,
+                "height": 1120
+            },
+            "availability": "Public",
+            "meta": {
+                "ENSD": "31337",
+                "Size": "1344x832",
+                "seed": 365756742,
+                "Model": "BArtstyleDB-XL-Kohaku\u00ce\u0094-v3-11-000025",
+                "steps": 25,
+                "hashes": {
+                    "model": "95affd8c8f"
+                },
+                "prompt": "1girl, kisaki \\(blue archive\\), armpits, arms behind head, arms up, bare shoulders, black dress, black hair, blush, braid, braided bun, breasts, butterfly hair ornament, china dress, chinese clothes, covered navel, double bun, dragon print, dress, grey eyes, hair bun, hair ornament, halo, long hair, looking at viewer, lying, on back, pelvic curtain, short dress, side slit, small breasts, solo, thighs, twintails, absurdres, highres, newest, masterpiece",
+                "Version": "v1.8.0",
+                "sampler": "Euler a",
+                "Emphasis": "No norm",
+                "cfgScale": 4,
+                "clipSkip": 2,
+                "Mask blur": "4",
+                "resources": [
+                    {
+                        "hash": "95affd8c8f",
+                        "name": "BArtstyleDB-XL-Kohaku\u00ce\u0094-v3-11-000025",
+                        "type": "model"
+                    }
+                ],
+                "Model hash": "95affd8c8f",
+                "Hires steps": "15",
+                "Inpaint area": "Only masked",
+                "Hires upscale": "1.35",
+                "Hypertile VAE": "True",
+                "Hires upscaler": "4x-UltraSharp",
+                "negativePrompt": "lowres, error, worst quality, low quality, normal quality, jpeg artifacts",
+                "ADetailer model": "face_yolov8s.pt",
+                "ADetailer version": "24.3.1",
+                "Denoising strength": "0.4",
+                "ADetailer mask blur": "4",
+                "Masked area padding": "32",
+                "ADetailer confidence": "0.3",
+                "ADetailer dilate erode": "4",
+                "ADetailer inpaint padding": "32",
+                "ADetailer denoising strength": "0.4",
+                "ADetailer inpaint only masked": "True"
+            }
+        },
+        {
+            "url": "https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/48a7a3c7-e63c-49a7-9b03-05381639e9f5/width=450/9170187.jpeg",
+            "nsfwLevel": 1,
+            "width": 1744,
+            "height": 1080,
+            "hash": "UEF}?A00^,-;00%f4.IoxZIo-oNH~CWYn$xu",
+            "type": "image",
+            "metadata": {
+                "hash": "UEF}?A00^,-;00%f4.IoxZIo-oNH~CWYn$xu",
+                "size": 1665471,
+                "width": 1744,
+                "height": 1080
+            },
+            "availability": "Public",
+            "meta": {
+                "ENSD": "31337",
+                "Size": "1344x832",
+                "seed": 484327583,
+                "Model": "BArtstyleDB-XL-Kohaku\u00ce\u0094-v3-11-000025",
+                "steps": 25,
+                "hashes": {
+                    "model": "95affd8c8f",
+                    "lora:HarunaXL-Lokr-01": "ae01ce88dda7"
+                },
+                "prompt": "1girl, haruna \\(kancolle\\) \\(kaisan\\), nontraditional miko \\(kaisan\\), headgear \\(kaisan\\), hairband \\(kaisan\\), black hair, hairclips, solo, bare shoulders, wide sleeves, night theme, medium shot, from above,  standing, expressionless, v-shaped eyebrows, serious, brown eyes, glowing eye, flaming eye,  parted lips, shaded face, looking at viewer, ocean, water, horizon, \nmasterpiece, highres, absurdres, best quality, safe <lora:HarunaXL-Lokr-01:0.7>",
+                "Version": "v1.8.0",
+                "sampler": "Euler a",
+                "Emphasis": "No norm",
+                "cfgScale": 5.5,
+                "clipSkip": 2,
+                "Mask blur": "5",
+                "resources": [
+                    {
+                        "hash": "ae01ce88dda7",
+                        "name": "HarunaXL-Lokr-01",
+                        "type": "lora",
+                        "weight": 0.7
+                    },
+                    {
+                        "hash": "95affd8c8f",
+                        "name": "BArtstyleDB-XL-Kohaku\u00ce\u0094-v3-11-000025",
+                        "type": "model"
+                    }
+                ],
+                "Model hash": "95affd8c8f",
+                "Hires steps": "10",
+                "Inpaint area": "Only masked",
+                "Hires upscale": "1.3",
+                "Hypertile VAE": "True",
+                "Hires upscaler": "DAT_x2",
+                "negativePrompt": "halo, monochromic, nsfw, lowres, error, worst quality, low quality, jpeg artifacts, signature, username, blurry, chibi, text, copyright name, watermark, azur lane",
+                "ADetailer model": "face_yolov8n.pt",
+                "Wildcard prompt": {
+                    "HarunaXL-Lokr-01": "0.7>"
+                },
+                "ADetailer version": "24.3.5",
+                "Denoising strength": "0.2",
+                "ADetailer mask blur": "5",
+                "Masked area padding": "64",
+                "ADetailer confidence": "0.5",
+                "ADetailer dilate erode": "4",
+                "ADetailer inpaint padding": "64",
+                "ADetailer denoising strength": "0.2",
+                "ADetailer inpaint only masked": "True"
+            }
+        },
+        {
+            "url": "https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/3e336b3b-a356-4548-96af-5cc7100f262c/width=450/9089621.jpeg",
+            "nsfwLevel": 1,
+            "width": 1808,
+            "height": 1120,
+            "hash": "UMIXzR9F~WS$D+-=nzxt4.%Msps.D~WBxvV[",
+            "type": "image",
+            "metadata": {
+                "hash": "UMIXzR9F~WS$D+-=nzxt4.%Msps.D~WBxvV[",
+                "size": 1870502,
+                "width": 1808,
+                "height": 1120
+            },
+            "availability": "Public",
+            "meta": {
+                "ENSD": "31337",
+                "Size": "1344x832",
+                "seed": 1247749320,
+                "Model": "BArtstyleDB-XL-Kohaku\u00ce\u0094-v3-11-000025",
+                "steps": 25,
+                "hashes": {
+                    "model": "95affd8c8f"
+                },
+                "prompt": "1girl, \nyuuka \\(blue archive\\),  \narm rest, bed sheet, black shirt, blush, collarbone, crossed arms, cushion, feet up, grey skirt, halo, indoors, long hair, looking at viewer, night sky, on stomach, pencil skirt, plaid skirt, purple eyes, purple hair, red pupils, sky, soles, solo, the pose, two side up, very long hair, breasts, shirt, bed, toes, short sleeves, legs, feet, barefoot, arm support, lying, arm under breasts, plaid, full body, night, skirt, \nmasterpiece, absurdres, sensitive",
+                "Version": "v1.8.0",
+                "sampler": "Euler a",
+                "Emphasis": "No norm",
+                "cfgScale": 6,
+                "clipSkip": 2,
+                "Mask blur": "4",
+                "resources": [
+                    {
+                        "hash": "95affd8c8f",
+                        "name": "BArtstyleDB-XL-Kohaku\u00ce\u0094-v3-11-000025",
+                        "type": "model"
+                    }
+                ],
+                "Model hash": "95affd8c8f",
+                "Hires steps": "15",
+                "Inpaint area": "Only masked",
+                "Hires upscale": "1.35",
+                "Hypertile VAE": "True",
+                "Hires upscaler": "4x-UltraSharp",
+                "negativePrompt": "nsfw, lowres, error, worst quality, low quality, normal quality, jpeg artifacts",
+                "ADetailer model": "face_yolov8s.pt",
+                "ADetailer version": "24.3.1",
+                "Denoising strength": "0.4",
+                "ADetailer mask blur": "4",
+                "Masked area padding": "32",
+                "ADetailer confidence": "0.3",
+                "ADetailer dilate erode": "4",
+                "ADetailer inpaint padding": "32",
+                "ADetailer denoising strength": "0.4",
+                "ADetailer inpaint only masked": "True"
+            }
+        },
+        {
+            "url": "https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/bf1e3362-799e-467b-a946-d875d197ecc8/width=450/9168562.jpeg",
+            "nsfwLevel": 1,
+            "width": 1080,
+            "height": 1744,
+            "hash": "URI;rF57tSIUGHozV@ax%NtRM{Rj?w%2%MIo",
+            "type": "image",
+            "metadata": {
+                "hash": "URI;rF57tSIUGHozV@ax%NtRM{Rj?w%2%MIo",
+                "size": 1596038,
+                "width": 1080,
+                "height": 1744
+            },
+            "availability": "Public",
+            "meta": {
+                "ENSD": "31337",
+                "Size": "832x1344",
+                "seed": 3845135251,
+                "Model": "BArtstyleDB-XL-Kohaku\u00ce\u0094-v3-11-000025",
+                "steps": 25,
+                "hashes": {
+                    "model": "95affd8c8f",
+                    "lora:HarunaXL-Lokr-01": "ae01ce88dda7"
+                },
+                "prompt": "1girl, \nharuna \\(kancolle\\) \\(kaisan\\), nontraditional miko \\(kaisan\\), headgear \\(kaisan\\), hairband \\(kaisan\\), black hair, hairclips, collar, solo, on back, ocean, thighhighs, skirt, breasts, smile, sidelocks, hair ornament, sleeveless, wide sleeves, long hair, detached sleeves, looking at viewer, japanese clothes, \nmasterpiece, best quality, highres, absurdres, safe\n <lora:HarunaXL-Lokr-01:0.7>",
+                "Version": "v1.8.0",
+                "sampler": "Euler a",
+                "Emphasis": "No norm",
+                "cfgScale": 5.5,
+                "clipSkip": 2,
+                "Mask blur": "5",
+                "resources": [
+                    {
+                        "hash": "ae01ce88dda7",
+                        "name": "HarunaXL-Lokr-01",
+                        "type": "lora",
+                        "weight": 0.7
+                    },
+                    {
+                        "hash": "95affd8c8f",
+                        "name": "BArtstyleDB-XL-Kohaku\u00ce\u0094-v3-11-000025",
+                        "type": "model"
+                    }
+                ],
+                "Model hash": "95affd8c8f",
+                "Hires steps": "10",
+                "Inpaint area": "Only masked",
+                "Hires upscale": "1.3",
+                "Hypertile VAE": "True",
+                "Hires upscaler": "DAT_x2",
+                "negativePrompt": "halo, monochromic, nsfw, lowres, error, worst quality, low quality, jpeg artifacts, signature, username, blurry, chibi, text, copyright name, watermark, azur lane,",
+                "ADetailer model": "face_yolov8n.pt",
+                "Wildcard prompt": {
+                    "HarunaXL-Lokr-01": "0.7>"
+                },
+                "ADetailer version": "24.3.5",
+                "Denoising strength": "0.2",
+                "ADetailer mask blur": "5",
+                "Masked area padding": "64",
+                "ADetailer confidence": "0.5",
+                "ADetailer dilate erode": "4",
+                "ADetailer inpaint padding": "64",
+                "ADetailer denoising strength": "0.2",
+                "ADetailer inpaint only masked": "True"
+            }
+        }
+    ],
+    "downloadUrl": "https://civitai.com/api/download/models/426588",
+    "creator": {
+        "username": "4BEraser",
+        "image": "https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/c52eedf3-6940-435c-d792-17c82ce32000/width=96/4BEraser.jpeg"
+    },
+    "extensions": {
+        "sd_civitai_helper": {
+            "version": "1.8.4",
+            "last_update": 1712842139,
+            "skeleton_file": false
+        }
+    }
+}

SDXL-2D/baxlBlueArchiveFlatCelluloidStyleFineTune_xlv3.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95affd8c8f664e6f30c1c5dd54723eacf1dbf3f02da15cb82a67a21eb003875f
+size 6938040638