search

camenduru / sd-civitai-browser

An extension to help download models from CivitAi without leaving WebUI
111 stars 66 forks source link

json structure #3

Closed camenduru closed 1 year ago

camenduru commented 1 year ago 
from typing import List
from typing import Any
from dataclasses import dataclass
import json
@dataclass
class Creator:
    username: str
    image: str

    @staticmethod
    def from_dict(obj: Any) -> 'Creator':
        _username = str(obj.get("username"))
        _image = str(obj.get("image"))
        return Creator(_username, _image)

@dataclass
class File:
    name: str
    id: int
    sizeKB: float
    type: str
    format: str
    pickleScanResult: str
    pickleScanMessage: str
    virusScanResult: str
    scannedAt: str
    hashes: Hashes
    downloadUrl: str

    @staticmethod
    def from_dict(obj: Any) -> 'File':
        _name = str(obj.get("name"))
        _id = int(obj.get("id"))
        _sizeKB = float(obj.get("sizeKB"))
        _type = str(obj.get("type"))
        _format = str(obj.get("format"))
        _pickleScanResult = str(obj.get("pickleScanResult"))
        _pickleScanMessage = str(obj.get("pickleScanMessage"))
        _virusScanResult = str(obj.get("virusScanResult"))
        _scannedAt = str(obj.get("scannedAt"))
        _hashes = Hashes.from_dict(obj.get("hashes"))
        _downloadUrl = str(obj.get("downloadUrl"))
        return File(_name, _id, _sizeKB, _type, _format, _pickleScanResult, _pickleScanMessage, _virusScanResult, _scannedAt, _hashes, _downloadUrl)

@dataclass
class Hashes:
    SHA256: str
    AutoV1: str
    AutoV2: str
    BLAKE3: str
    CRC32: str

    @staticmethod
    def from_dict(obj: Any) -> 'Hashes':
        _SHA256 = str(obj.get("SHA256"))
        _AutoV1 = str(obj.get("AutoV1"))
        _AutoV2 = str(obj.get("AutoV2"))
        _BLAKE3 = str(obj.get("BLAKE3"))
        _CRC32 = str(obj.get("CRC32"))
        return Hashes(_SHA256, _AutoV1, _AutoV2, _BLAKE3, _CRC32)

@dataclass
class Image:
    url: str
    nsfw: bool
    width: int
    height: int
    hash: str
    meta: Meta

    @staticmethod
    def from_dict(obj: Any) -> 'Image':
        _url = str(obj.get("url"))
        _nsfw = 
        _width = int(obj.get("width"))
        _height = int(obj.get("height"))
        _hash = str(obj.get("hash"))
        _meta = Meta.from_dict(obj.get("meta"))
        return Image(_url, _nsfw, _width, _height, _hash, _meta)

@dataclass
class Item:
    id: int
    name: str
    description: str
    type: str
    poi: bool
    nsfw: bool
    allowNoCredit: bool
    allowCommercialUse: str
    allowDerivatives: bool
    allowDifferentLicense: bool
    creator: Creator
    tags: List[str]
    modelVersions: List[ModelVersion]

    @staticmethod
    def from_dict(obj: Any) -> 'Item':
        _id = int(obj.get("id"))
        _name = str(obj.get("name"))
        _description = str(obj.get("description"))
        _type = str(obj.get("type"))
        _poi = 
        _nsfw = 
        _allowNoCredit = 
        _allowCommercialUse = str(obj.get("allowCommercialUse"))
        _allowDerivatives = 
        _allowDifferentLicense = 
        _creator = Creator.from_dict(obj.get("creator"))
        _tags = [.from_dict(y) for y in obj.get("tags")]
        _modelVersions = [ModelVersion.from_dict(y) for y in obj.get("modelVersions")]
        return Item(_id, _name, _description, _type, _poi, _nsfw, _allowNoCredit, _allowCommercialUse, _allowDerivatives, _allowDifferentLicense, _creator, _tags, _modelVersions)

@dataclass
class Meta:
    ENSD: str
    Size: str
    seed: object
    steps: int
    prompt: str
    sampler: str
    cfgScale: float
    Batch pos: str
    resources: List[Resource]
    Batch size: str
    Model hash: str
    Hires upscale: str
    Hires upscaler: str
    negativePrompt: str
    Denoising strength: str
    Model: str
    Hires steps: str
    Clip skip: str
    Mask blur: str
    SD upscale overlap: str
    SD upscale upscaler: str

    @staticmethod
    def from_dict(obj: Any) -> 'Meta':
        _ENSD = str(obj.get("ENSD"))
        _Size = str(obj.get("Size"))
        _seed = 
        _steps = int(obj.get("steps"))
        _prompt = str(obj.get("prompt"))
        _sampler = str(obj.get("sampler"))
        _cfgScale = float(obj.get("cfgScale"))
        _Batch pos = str(obj.get("Batch pos"))
        _resources = [Resource.from_dict(y) for y in obj.get("resources")]
        _Batch size = str(obj.get("Batch size"))
        _Model hash = str(obj.get("Model hash"))
        _Hires upscale = str(obj.get("Hires upscale"))
        _Hires upscaler = str(obj.get("Hires upscaler"))
        _negativePrompt = str(obj.get("negativePrompt"))
        _Denoising strength = str(obj.get("Denoising strength"))
        _Model = str(obj.get("Model"))
        _Hires steps = str(obj.get("Hires steps"))
        _Clip skip = str(obj.get("Clip skip"))
        _Mask blur = str(obj.get("Mask blur"))
        _SD upscale overlap = str(obj.get("SD upscale overlap"))
        _SD upscale upscaler = str(obj.get("SD upscale upscaler"))
        return Meta(_ENSD, _Size, _seed, _steps, _prompt, _sampler, _cfgScale, _Batch pos, _resources, _Batch size, _Model hash, _Hires upscale, _Hires upscaler, _negativePrompt, _Denoising strength, _Model, _Hires steps, _Clip skip, _Mask blur, _SD upscale overlap, _SD upscale upscaler)

@dataclass
class ModelVersion:
    id: int
    modelId: int
    name: str
    createdAt: str
    updatedAt: str
    trainedWords: List[object]
    baseModel: str
    earlyAccessTimeFrame: int
    description: str
    files: List[File]
    images: List[Image]
    downloadUrl: str

    @staticmethod
    def from_dict(obj: Any) -> 'ModelVersion':
        _id = int(obj.get("id"))
        _modelId = int(obj.get("modelId"))
        _name = str(obj.get("name"))
        _createdAt = str(obj.get("createdAt"))
        _updatedAt = str(obj.get("updatedAt"))
        _trainedWords = [.from_dict(y) for y in obj.get("trainedWords")]
        _baseModel = str(obj.get("baseModel"))
        _earlyAccessTimeFrame = int(obj.get("earlyAccessTimeFrame"))
        _description = str(obj.get("description"))
        _files = [File.from_dict(y) for y in obj.get("files")]
        _images = [Image.from_dict(y) for y in obj.get("images")]
        _downloadUrl = str(obj.get("downloadUrl"))
        return ModelVersion(_id, _modelId, _name, _createdAt, _updatedAt, _trainedWords, _baseModel, _earlyAccessTimeFrame, _description, _files, _images, _downloadUrl)

@dataclass
class Resource:
    hash: str
    name: str
    type: str

    @staticmethod
    def from_dict(obj: Any) -> 'Resource':
        _hash = str(obj.get("hash"))
        _name = str(obj.get("name"))
        _type = str(obj.get("type"))
        return Resource(_hash, _name, _type)

@dataclass
class Root:
    items: List[Item]

    @staticmethod
    def from_dict(obj: Any) -> 'Root':
        _items = [Item.from_dict(y) for y in obj.get("items")]
        return Root(_items)

# Example Usage
# jsonstring = json.loads(myjsonstring)
# root = Root.from_dict(jsonstring)
camenduru commented 1 year ago

https://github.com/civitai/civitai https://github.com/civitai/sd_civitai_extension

camenduru commented 1 year ago 
from typing import List
from typing import Any
from dataclasses import dataclass
import json
@dataclass
class Creator:
    username: str
    image: str

    @staticmethod
    def from_dict(obj: Any) -> 'Creator':
        _username = str(obj.get("username"))
        _image = str(obj.get("image"))
        return Creator(_username, _image)

@dataclass
class File:
    name: str
    id: int
    sizeKB: float
    type: str
    format: str
    pickleScanResult: str
    pickleScanMessage: str
    virusScanResult: str
    scannedAt: str
    hashes: Hashes
    downloadUrl: str

    @staticmethod
    def from_dict(obj: Any) -> 'File':
        _name = str(obj.get("name"))
        _id = int(obj.get("id"))
        _sizeKB = float(obj.get("sizeKB"))
        _type = str(obj.get("type"))
        _format = str(obj.get("format"))
        _pickleScanResult = str(obj.get("pickleScanResult"))
        _pickleScanMessage = str(obj.get("pickleScanMessage"))
        _virusScanResult = str(obj.get("virusScanResult"))
        _scannedAt = str(obj.get("scannedAt"))
        _hashes = Hashes.from_dict(obj.get("hashes"))
        _downloadUrl = str(obj.get("downloadUrl"))
        return File(_name, _id, _sizeKB, _type, _format, _pickleScanResult, _pickleScanMessage, _virusScanResult, _scannedAt, _hashes, _downloadUrl)

@dataclass
class Hashes:
    AutoV1: str
    AutoV2: str
    SHA256: str
    CRC32: str
    BLAKE3: str

    @staticmethod
    def from_dict(obj: Any) -> 'Hashes':
        _AutoV1 = str(obj.get("AutoV1"))
        _AutoV2 = str(obj.get("AutoV2"))
        _SHA256 = str(obj.get("SHA256"))
        _CRC32 = str(obj.get("CRC32"))
        _BLAKE3 = str(obj.get("BLAKE3"))
        return Hashes(_AutoV1, _AutoV2, _SHA256, _CRC32, _BLAKE3)

@dataclass
class Image:
    url: str
    nsfw: bool
    width: int
    height: int
    hash: str
    meta: Meta
    generationProcess: str
    tags: List[object]

    @staticmethod
    def from_dict(obj: Any) -> 'Image':
        _url = str(obj.get("url"))
        _nsfw = 
        _width = int(obj.get("width"))
        _height = int(obj.get("height"))
        _hash = str(obj.get("hash"))
        _meta = Meta.from_dict(obj.get("meta"))
        _generationProcess = str(obj.get("generationProcess"))
        _tags = [.from_dict(y) for y in obj.get("tags")]
        return Image(_url, _nsfw, _width, _height, _hash, _meta, _generationProcess, _tags)

@dataclass
class Item:
    id: int
    name: str
    description: str
    type: str
    poi: bool
    nsfw: bool
    allowNoCredit: bool
    allowCommercialUse: str
    allowDerivatives: bool
    allowDifferentLicense: bool
    creator: Creator
    tags: List[str]
    modelVersions: List[ModelVersion]

    @staticmethod
    def from_dict(obj: Any) -> 'Item':
        _id = int(obj.get("id"))
        _name = str(obj.get("name"))
        _description = str(obj.get("description"))
        _type = str(obj.get("type"))
        _poi = 
        _nsfw = 
        _allowNoCredit = 
        _allowCommercialUse = str(obj.get("allowCommercialUse"))
        _allowDerivatives = 
        _allowDifferentLicense = 
        _creator = Creator.from_dict(obj.get("creator"))
        _tags = [.from_dict(y) for y in obj.get("tags")]
        _modelVersions = [ModelVersion.from_dict(y) for y in obj.get("modelVersions")]
        return Item(_id, _name, _description, _type, _poi, _nsfw, _allowNoCredit, _allowCommercialUse, _allowDerivatives, _allowDifferentLicense, _creator, _tags, _modelVersions)

@dataclass
class Meta:
    ENSD: str
    Size: str
    seed: object
    Model: str
    steps: int
    prompt: str
    sampler: str
    cfgScale: float
    Model hash: str
    negativePrompt: str
    Face restoration: str
    resources: List[Resource]
    Batch pos: str
    Batch size: str
    Hires upscale: str
    Hires upscaler: str
    Denoising strength: str
    Hires steps: str
    Mask blur: str
    Conditional mask weight: str
    Clip skip: str
    SD upscale overlap: str
    SD upscale upscaler: str
    First pass size: str

    @staticmethod
    def from_dict(obj: Any) -> 'Meta':
        _ENSD = str(obj.get("ENSD"))
        _Size = str(obj.get("Size"))
        _seed = 
        _Model = str(obj.get("Model"))
        _steps = int(obj.get("steps"))
        _prompt = str(obj.get("prompt"))
        _sampler = str(obj.get("sampler"))
        _cfgScale = float(obj.get("cfgScale"))
        _Model hash = str(obj.get("Model hash"))
        _negativePrompt = str(obj.get("negativePrompt"))
        _Face restoration = str(obj.get("Face restoration"))
        _resources = [Resource.from_dict(y) for y in obj.get("resources")]
        _Batch pos = str(obj.get("Batch pos"))
        _Batch size = str(obj.get("Batch size"))
        _Hires upscale = str(obj.get("Hires upscale"))
        _Hires upscaler = str(obj.get("Hires upscaler"))
        _Denoising strength = str(obj.get("Denoising strength"))
        _Hires steps = str(obj.get("Hires steps"))
        _Mask blur = str(obj.get("Mask blur"))
        _Conditional mask weight = str(obj.get("Conditional mask weight"))
        _Clip skip = str(obj.get("Clip skip"))
        _SD upscale overlap = str(obj.get("SD upscale overlap"))
        _SD upscale upscaler = str(obj.get("SD upscale upscaler"))
        _First pass size = str(obj.get("First pass size"))
        return Meta(_ENSD, _Size, _seed, _Model, _steps, _prompt, _sampler, _cfgScale, _Model hash, _negativePrompt, _Face restoration, _resources, _Batch pos, _Batch size, _Hires upscale, _Hires upscaler, _Denoising strength, _Hires steps, _Mask blur, _Conditional mask weight, _Clip skip, _SD upscale overlap, _SD upscale upscaler, _First pass size)

@dataclass
class Metadata:
    totalItems: int
    currentPage: int
    pageSize: int
    totalPages: int
    nextPage: str

    @staticmethod
    def from_dict(obj: Any) -> 'Metadata':
        _totalItems = int(obj.get("totalItems"))
        _currentPage = int(obj.get("currentPage"))
        _pageSize = int(obj.get("pageSize"))
        _totalPages = int(obj.get("totalPages"))
        _nextPage = str(obj.get("nextPage"))
        return Metadata(_totalItems, _currentPage, _pageSize, _totalPages, _nextPage)

@dataclass
class ModelVersion:
    id: int
    modelId: int
    name: str
    createdAt: str
    updatedAt: str
    trainedWords: List[str]
    baseModel: str
    earlyAccessTimeFrame: int
    description: str
    files: List[File]
    images: List[Image]
    downloadUrl: str

    @staticmethod
    def from_dict(obj: Any) -> 'ModelVersion':
        _id = int(obj.get("id"))
        _modelId = int(obj.get("modelId"))
        _name = str(obj.get("name"))
        _createdAt = str(obj.get("createdAt"))
        _updatedAt = str(obj.get("updatedAt"))
        _trainedWords = [.from_dict(y) for y in obj.get("trainedWords")]
        _baseModel = str(obj.get("baseModel"))
        _earlyAccessTimeFrame = int(obj.get("earlyAccessTimeFrame"))
        _description = str(obj.get("description"))
        _files = [File.from_dict(y) for y in obj.get("files")]
        _images = [Image.from_dict(y) for y in obj.get("images")]
        _downloadUrl = str(obj.get("downloadUrl"))
        return ModelVersion(_id, _modelId, _name, _createdAt, _updatedAt, _trainedWords, _baseModel, _earlyAccessTimeFrame, _description, _files, _images, _downloadUrl)

@dataclass
class Resource:
    hash: str
    name: str
    type: str

    @staticmethod
    def from_dict(obj: Any) -> 'Resource':
        _hash = str(obj.get("hash"))
        _name = str(obj.get("name"))
        _type = str(obj.get("type"))
        return Resource(_hash, _name, _type)

@dataclass
class Root:
    items: List[Item]
    metadata: Metadata

    @staticmethod
    def from_dict(obj: Any) -> 'Root':
        _items = [Item.from_dict(y) for y in obj.get("items")]
        _metadata = Metadata.from_dict(obj.get("metadata"))
        return Root(_items, _metadata)

# Example Usage
# jsonstring = json.loads(myjsonstring)
# root = Root.from_dict(jsonstring)
camenduru commented 1 year ago 
"type": "Checkpoint",
"type": "Model",
"type": "Model",
"type": "model"
"type": "model"
"type": "model"
"type": "Model",
"type": "Model",
"type": "Checkpoint",
"type": "Model",
"type": "Model",
"type": "Pruned Model",
"type": "Pruned Model",
"type": "Model",
"type": "Model",
"type": "Pruned Model",
"type": "Pruned Model",
"type": "model"
"type": "Model",
"type": "Model",
"type": "Model",
"type": "Pruned Model",
"type": "Pruned Model",
"type": "Model",
"type": "Model",
"type": "Pruned Model",
"type": "Pruned Model",
"type": "Model",
"type": "Pruned Model",
"type": "Model",
"type": "Checkpoint",
"type": "Model",
"type": "Model",
"type": "Config",
"type": "Model",
"type": "Model",
"type": "Model",
"type": "Model",
"type": "Checkpoint",
"type": "Model",
"type": "Model",
"type": "Pruned Model",
"type": "Pruned Model",
"type": "model"
"type": "Checkpoint",
"type": "Model",
"type": "Model",
"type": "VAE",
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "Model",
"type": "Model",
"type": "VAE",
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "Model",
"type": "Model",
"type": "VAE",
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "Model",
"type": "Model",
"type": "VAE",
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "Checkpoint",
"type": "Model",
"type": "Model",
"type": "Model",
"type": "Model",
"type": "Model",
"type": "Pruned Model",
"type": "Checkpoint",
"type": "Model",
"type": "VAE",
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "Model",
"type": "Model",
"type": "Model",
"type": "Model",
"type": "VAE",
"type": "Model",
"type": "Model",
"type": "VAE",
"type": "Checkpoint",
"type": "Model",
"type": "Model",
"type": "Checkpoint",
"type": "Model",
"type": "VAE",
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "Model",
"type": "VAE",
"type": "Checkpoint",
"type": "Model",
"type": "Checkpoint",
"type": "Model",
"type": "Pruned Model",
"type": "Model",
"type": "Pruned Model",
"type": "Checkpoint",
"type": "Model",
"type": "Model",
"type": "Checkpoint",
"type": "Model",
"type": "Model",
"type": "Pruned Model",
"type": "Pruned Model",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "Model",
"type": "Model",
"type": "lora",
"type": "lora",
"type": "model"
"type": "lora",
"type": "lora",
"type": "model"
"type": "model"
"type": "TextualInversion",
"type": "Model",
"type": "Model",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "Model",
"type": "Checkpoint",
"type": "Model",
"type": "Pruned Model",
"type": "hypernet",
"type": "Model",
"type": "LORA",
"type": "Model",
"type": "lora",
"type": "model"
"type": "lora",
"type": "lora",
"type": "lora",
"type": "Model",
"type": "lora",
"type": "lora",
"type": "Model",
"type": "lora",
"type": "lora",
"type": "Checkpoint",
"type": "Model",
"type": "Model",
"type": "Checkpoint",
"type": "Model",
"type": "Model",
"type": "Pruned Model",
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "Model",
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "Model",
"type": "Model",
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "Model",
"type": "Model",
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "Model",
"type": "model"
"type": "model"
"type": "model"
"type": "Model",
"type": "model"
"type": "Model",
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "Checkpoint",
"type": "Config",
"type": "Model",
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "Config",
"type": "Model",
"type": "Pruned Model",
"type": "Checkpoint",
"type": "Model",
"type": "Model",
"type": "LORA",
"type": "Model",
"type": "LORA",
"type": "Model",
"type": "model"
"type": "lora",
"type": "lora",
"type": "model"
"type": "lora",
"type": "lora",
"type": "model"
"type": "lora",
"type": "lora",
"type": "model"
"type": "lora",
"type": "lora",
"type": "model"
"type": "lora",
"type": "lora",
"type": "model"
"type": "lora",
"type": "lora",
"type": "Model",
"type": "model"
"type": "lora",
"type": "lora",
"type": "model"
"type": "lora",
"type": "model"
"type": "lora",
"type": "model"
"type": "lora",
"type": "lora",
"type": "lora",
"type": "model"
"type": "lora",
"type": "lora",
"type": "model"
"type": "lora",
"type": "lora",
"type": "Model",
"type": "model"
"type": "lora",
"type": "lora",
"type": "model"
"type": "lora",
"type": "model"
"type": "lora",
"type": "lora",
"type": "lora",
"type": "Checkpoint",
"type": "Model",
"type": "Model",
"type": "Checkpoint",
"type": "Model",
"type": "VAE",
"type": "Checkpoint",
"type": "Model",
"type": "Model",
"type": "Pruned Model",
"type": "Pruned Model",
"type": "Checkpoint",
"type": "Model",
"type": "Model",
"type": "Model",
"type": "Model",
"type": "Model",
"type": "Model",
"type": "Model",
"type": "Model",
"type": "Model",
"type": "Model",
"type": "Model",
"type": "Model",
"type": "Model",
"type": "Model",
"type": "Checkpoint",
"type": "Model",
"type": "Model",
"type": "Pruned Model",
"type": "Pruned Model",
"type": "Model",
"type": "Model",
"type": "Pruned Model",
"type": "Pruned Model",
"type": "Model",
"type": "Model",
"type": "Checkpoint",
"type": "Model",
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "LORA",
"type": "Model",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "Checkpoint",
"type": "Model",
"type": "Model",
"type": "Pruned Model",
"type": "Pruned Model",
"type": "Checkpoint",
"type": "Model",
"type": "Model",
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "Model",
"type": "Model",
"type": "Model",
"type": "Checkpoint",
"type": "Model",
"type": "Model",
"type": "Model",
"type": "Model",
"type": "Checkpoint",
"type": "Model",
"type": "Model",
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "Model",
"type": "Model",
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "Model",
"type": "Model",
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "Hypernetwork",
"type": "Model",
"type": "Model",
"type": "Checkpoint",
"type": "Model",
"type": "VAE",
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "Checkpoint",
"type": "Model",
"type": "Model",
"type": "Pruned Model",
"type": "Model",
"type": "Model",
"type": "Pruned Model",
"type": "Model",
"type": "Model",
"type": "Pruned Model",
"type": "Pruned Model",
"type": "Model",
"type": "Pruned Model",
"type": "Checkpoint",
"type": "Model",
"type": "TextualInversion",
"type": "Model",
"type": "Checkpoint",
"type": "Model",
"type": "Model",
"type": "Model",
"type": "Model",
"type": "LORA",
"type": "Model",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "Model",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "Checkpoint",
"type": "Model",
"type": "Checkpoint",
"type": "Model",
"type": "Pruned Model",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "Model",
"type": "Model",
"type": "Pruned Model",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "lora",
"type": "Checkpoint",
"type": "Model",
"type": "Model",
"type": "Model",
"type": "Model",
"type": "Model",
"type": "Checkpoint",
"type": "Model",
"type": "Model",
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "Config",
"type": "Model",
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "Config",
"type": "Model",
"type": "Model",
"type": "Config",
"type": "Model",
"type": "TextualInversion",
"type": "Model",
"type": "Checkpoint",
"type": "Model",
"type": "Model",
"type": "Pruned Model",
"type": "Pruned Model",
"type": "model"
"type": "Checkpoint",
"type": "Model",
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "model"
"type": "Checkpoint",
"type": "Model",
"type": "Model",
"type": "LORA",
"type": "Model",
"type": "model"
"type": "lora",
"type": "model"
"type": "lora",
"type": "model"
"type": "lora",
"type": "model"
"type": "lora",
"type": "model"
"type": "lora",
"type": "model"
"type": "lora",
"type": "Checkpoint",
"type": "Model",
"type": "Model",