{
    "id": 35578,
    "modelId": 22696,
    "name": "V4 1.0",
    "createdAt": "2023-04-04T09:16:56.971Z",
    "updatedAt": "2023-04-04T10:04:28.070Z",
    "trainedWords": [
        "*color* theme",
        "abstract",
        "powerful",
        "great style",
        "good style",
        "bad style",
        "blurry",
        "lowres",
        "blurry background",
        "particles",
        "realistic",
        "3d",
        "olis"
    ],
    "baseModel": "Other",
    "earlyAccessTimeFrame": 0,
    "description": "<p><strong>This is an Extended LoRA and will require LOCON extension.</strong></p><p>This version can vary wildly from v4 0.6, so be aware of that. Generally features better control, further negative tagging, and so on.</p><p>Optional pos/neg tag pair \"Great style/good style\" \"bad style\" is ready for use and does have serious impact on image. Will be expanded in future versions.</p><p>Additionally this dataset has own images tagged \"blurry, lowres\", so using those negatives is advised.</p><p>Changelog:</p><p>V4 2.0: Dataset expansion to 1000+. Maybe rank increase. Future new training techniques, if available.</p><p><strong>-You are here-</strong><br />V4: Smoothing tagging further. Better control. Separation of \"Particles\" concept from unprompted generation. Much less various particles appear unprompted.</p><p><em>(Not Released)v4 0.6.5: Better stability. Weight Clipping for tenc used.</em></p><p>v4 0.6: Adequate tagging and knowledge separation. Advanced Adan training with separated tenc and u-net weight decay. Complete basic negative tagging.</p><p><em>(Not Released)v4 0.5: Dataset expansion to over 500 images. Initial tagging of additional dataset. Advanced Adan training. Initial negative tagging.</em></p><p><em>(Not Released)v3.3.4: Better color theme tag. More tags. Optimized Adan training. Awesome drawn texturing. Stable. Experiencing interesting style of upscale.</em></p><p><em>(Not Released)v3.3.3 Themes: initial addition of color theme tag. Expanded tagging. New Adan training. Unstable.</em><br />3.3.2: Adan optimizer training v2. Complete tagging of base dataset. Trying to localize style to \"ohwx\", while separating abstraction elements.<br />v3.3.2 is trained as a fine-tune, so it will affect generation without trigger words, but some concepts are isolated in them, overall, it tries to not change contents of image in a major way, but sometimes can.<br /><em>(Not Released)3.3.1: Experiment with Adan optimizer. Went bad.<br />(Not Released)3.2: Itterating on settings, trying out Lion optimizer.<br />(Nor Released)3.1(V3 sv1): advanced tagging, still incomplete. Separation of some knowledge to specific words, like \"abstract\" and \"powerful\"<br />(Not Released)V3: Decent usable state, tagging incomplete. Custom deep mix trained.<br />(Not Released)V2: Something actually usable, moving to extended. ACM trained.<br />(Not Released)V1: just basic lora, learning to do stuff. ACM trained.</em></p>",
    "model": {
        "name": "S12 V4 1.0 update! | Style LoRA | Extended LoRA",
        "type": "LoCon",
        "nsfw": false,
        "poi": false
    },
    "files": [
        {
            "name": "s12V410UpdateStyleLora_v410.safetensors",
            "id": 28867,
            "sizeKB": 239629.013671875,
            "type": "Model",
            "metadata": {
                "fp": null,
                "size": null,
                "format": "SafeTensor"
            },
            "pickleScanResult": "Success",
            "pickleScanMessage": "No Pickle imports",
            "virusScanResult": "Success",
            "scannedAt": "2023-04-04T09:26:19.335Z",
            "hashes": {
                "AutoV1": "835059BF",
                "AutoV2": "5C05EF5D3C",
                "SHA256": "5C05EF5D3C3A67C7E31ED6238A394C6744E980A08616634166310667225E6FD9",
                "CRC32": "4010AE1D",
                "BLAKE3": "8F6049E9BEFEB066E0DAF07A5664F33AF98FD51E0B914C2C15F59F3E423C52E0"
            },
            "primary": true,
            "downloadUrl": "https://civitai.com/api/download/models/35578"
        }
    ],
    "images": [],
    "downloadUrl": "https://civitai.com/api/download/models/35578"
}