Spaces:
Running
on
Zero
Running
on
Zero
File size: 19,658 Bytes
703e263 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 |
from .sd3_vae_encoder import SD3VAEEncoder, SDVAEEncoderStateDictConverter
from .sd3_vae_decoder import SD3VAEDecoder, SDVAEDecoderStateDictConverter
class FluxVAEEncoder(SD3VAEEncoder):
def __init__(self):
super().__init__()
self.scaling_factor = 0.3611
self.shift_factor = 0.1159
@staticmethod
def state_dict_converter():
return FluxVAEEncoderStateDictConverter()
class FluxVAEDecoder(SD3VAEDecoder):
def __init__(self):
super().__init__()
self.scaling_factor = 0.3611
self.shift_factor = 0.1159
@staticmethod
def state_dict_converter():
return FluxVAEDecoderStateDictConverter()
class FluxVAEEncoderStateDictConverter(SDVAEEncoderStateDictConverter):
def __init__(self):
pass
def from_civitai(self, state_dict):
rename_dict = {
"encoder.conv_in.bias": "conv_in.bias",
"encoder.conv_in.weight": "conv_in.weight",
"encoder.conv_out.bias": "conv_out.bias",
"encoder.conv_out.weight": "conv_out.weight",
"encoder.down.0.block.0.conv1.bias": "blocks.0.conv1.bias",
"encoder.down.0.block.0.conv1.weight": "blocks.0.conv1.weight",
"encoder.down.0.block.0.conv2.bias": "blocks.0.conv2.bias",
"encoder.down.0.block.0.conv2.weight": "blocks.0.conv2.weight",
"encoder.down.0.block.0.norm1.bias": "blocks.0.norm1.bias",
"encoder.down.0.block.0.norm1.weight": "blocks.0.norm1.weight",
"encoder.down.0.block.0.norm2.bias": "blocks.0.norm2.bias",
"encoder.down.0.block.0.norm2.weight": "blocks.0.norm2.weight",
"encoder.down.0.block.1.conv1.bias": "blocks.1.conv1.bias",
"encoder.down.0.block.1.conv1.weight": "blocks.1.conv1.weight",
"encoder.down.0.block.1.conv2.bias": "blocks.1.conv2.bias",
"encoder.down.0.block.1.conv2.weight": "blocks.1.conv2.weight",
"encoder.down.0.block.1.norm1.bias": "blocks.1.norm1.bias",
"encoder.down.0.block.1.norm1.weight": "blocks.1.norm1.weight",
"encoder.down.0.block.1.norm2.bias": "blocks.1.norm2.bias",
"encoder.down.0.block.1.norm2.weight": "blocks.1.norm2.weight",
"encoder.down.0.downsample.conv.bias": "blocks.2.conv.bias",
"encoder.down.0.downsample.conv.weight": "blocks.2.conv.weight",
"encoder.down.1.block.0.conv1.bias": "blocks.3.conv1.bias",
"encoder.down.1.block.0.conv1.weight": "blocks.3.conv1.weight",
"encoder.down.1.block.0.conv2.bias": "blocks.3.conv2.bias",
"encoder.down.1.block.0.conv2.weight": "blocks.3.conv2.weight",
"encoder.down.1.block.0.nin_shortcut.bias": "blocks.3.conv_shortcut.bias",
"encoder.down.1.block.0.nin_shortcut.weight": "blocks.3.conv_shortcut.weight",
"encoder.down.1.block.0.norm1.bias": "blocks.3.norm1.bias",
"encoder.down.1.block.0.norm1.weight": "blocks.3.norm1.weight",
"encoder.down.1.block.0.norm2.bias": "blocks.3.norm2.bias",
"encoder.down.1.block.0.norm2.weight": "blocks.3.norm2.weight",
"encoder.down.1.block.1.conv1.bias": "blocks.4.conv1.bias",
"encoder.down.1.block.1.conv1.weight": "blocks.4.conv1.weight",
"encoder.down.1.block.1.conv2.bias": "blocks.4.conv2.bias",
"encoder.down.1.block.1.conv2.weight": "blocks.4.conv2.weight",
"encoder.down.1.block.1.norm1.bias": "blocks.4.norm1.bias",
"encoder.down.1.block.1.norm1.weight": "blocks.4.norm1.weight",
"encoder.down.1.block.1.norm2.bias": "blocks.4.norm2.bias",
"encoder.down.1.block.1.norm2.weight": "blocks.4.norm2.weight",
"encoder.down.1.downsample.conv.bias": "blocks.5.conv.bias",
"encoder.down.1.downsample.conv.weight": "blocks.5.conv.weight",
"encoder.down.2.block.0.conv1.bias": "blocks.6.conv1.bias",
"encoder.down.2.block.0.conv1.weight": "blocks.6.conv1.weight",
"encoder.down.2.block.0.conv2.bias": "blocks.6.conv2.bias",
"encoder.down.2.block.0.conv2.weight": "blocks.6.conv2.weight",
"encoder.down.2.block.0.nin_shortcut.bias": "blocks.6.conv_shortcut.bias",
"encoder.down.2.block.0.nin_shortcut.weight": "blocks.6.conv_shortcut.weight",
"encoder.down.2.block.0.norm1.bias": "blocks.6.norm1.bias",
"encoder.down.2.block.0.norm1.weight": "blocks.6.norm1.weight",
"encoder.down.2.block.0.norm2.bias": "blocks.6.norm2.bias",
"encoder.down.2.block.0.norm2.weight": "blocks.6.norm2.weight",
"encoder.down.2.block.1.conv1.bias": "blocks.7.conv1.bias",
"encoder.down.2.block.1.conv1.weight": "blocks.7.conv1.weight",
"encoder.down.2.block.1.conv2.bias": "blocks.7.conv2.bias",
"encoder.down.2.block.1.conv2.weight": "blocks.7.conv2.weight",
"encoder.down.2.block.1.norm1.bias": "blocks.7.norm1.bias",
"encoder.down.2.block.1.norm1.weight": "blocks.7.norm1.weight",
"encoder.down.2.block.1.norm2.bias": "blocks.7.norm2.bias",
"encoder.down.2.block.1.norm2.weight": "blocks.7.norm2.weight",
"encoder.down.2.downsample.conv.bias": "blocks.8.conv.bias",
"encoder.down.2.downsample.conv.weight": "blocks.8.conv.weight",
"encoder.down.3.block.0.conv1.bias": "blocks.9.conv1.bias",
"encoder.down.3.block.0.conv1.weight": "blocks.9.conv1.weight",
"encoder.down.3.block.0.conv2.bias": "blocks.9.conv2.bias",
"encoder.down.3.block.0.conv2.weight": "blocks.9.conv2.weight",
"encoder.down.3.block.0.norm1.bias": "blocks.9.norm1.bias",
"encoder.down.3.block.0.norm1.weight": "blocks.9.norm1.weight",
"encoder.down.3.block.0.norm2.bias": "blocks.9.norm2.bias",
"encoder.down.3.block.0.norm2.weight": "blocks.9.norm2.weight",
"encoder.down.3.block.1.conv1.bias": "blocks.10.conv1.bias",
"encoder.down.3.block.1.conv1.weight": "blocks.10.conv1.weight",
"encoder.down.3.block.1.conv2.bias": "blocks.10.conv2.bias",
"encoder.down.3.block.1.conv2.weight": "blocks.10.conv2.weight",
"encoder.down.3.block.1.norm1.bias": "blocks.10.norm1.bias",
"encoder.down.3.block.1.norm1.weight": "blocks.10.norm1.weight",
"encoder.down.3.block.1.norm2.bias": "blocks.10.norm2.bias",
"encoder.down.3.block.1.norm2.weight": "blocks.10.norm2.weight",
"encoder.mid.attn_1.k.bias": "blocks.12.transformer_blocks.0.to_k.bias",
"encoder.mid.attn_1.k.weight": "blocks.12.transformer_blocks.0.to_k.weight",
"encoder.mid.attn_1.norm.bias": "blocks.12.norm.bias",
"encoder.mid.attn_1.norm.weight": "blocks.12.norm.weight",
"encoder.mid.attn_1.proj_out.bias": "blocks.12.transformer_blocks.0.to_out.bias",
"encoder.mid.attn_1.proj_out.weight": "blocks.12.transformer_blocks.0.to_out.weight",
"encoder.mid.attn_1.q.bias": "blocks.12.transformer_blocks.0.to_q.bias",
"encoder.mid.attn_1.q.weight": "blocks.12.transformer_blocks.0.to_q.weight",
"encoder.mid.attn_1.v.bias": "blocks.12.transformer_blocks.0.to_v.bias",
"encoder.mid.attn_1.v.weight": "blocks.12.transformer_blocks.0.to_v.weight",
"encoder.mid.block_1.conv1.bias": "blocks.11.conv1.bias",
"encoder.mid.block_1.conv1.weight": "blocks.11.conv1.weight",
"encoder.mid.block_1.conv2.bias": "blocks.11.conv2.bias",
"encoder.mid.block_1.conv2.weight": "blocks.11.conv2.weight",
"encoder.mid.block_1.norm1.bias": "blocks.11.norm1.bias",
"encoder.mid.block_1.norm1.weight": "blocks.11.norm1.weight",
"encoder.mid.block_1.norm2.bias": "blocks.11.norm2.bias",
"encoder.mid.block_1.norm2.weight": "blocks.11.norm2.weight",
"encoder.mid.block_2.conv1.bias": "blocks.13.conv1.bias",
"encoder.mid.block_2.conv1.weight": "blocks.13.conv1.weight",
"encoder.mid.block_2.conv2.bias": "blocks.13.conv2.bias",
"encoder.mid.block_2.conv2.weight": "blocks.13.conv2.weight",
"encoder.mid.block_2.norm1.bias": "blocks.13.norm1.bias",
"encoder.mid.block_2.norm1.weight": "blocks.13.norm1.weight",
"encoder.mid.block_2.norm2.bias": "blocks.13.norm2.bias",
"encoder.mid.block_2.norm2.weight": "blocks.13.norm2.weight",
"encoder.norm_out.bias": "conv_norm_out.bias",
"encoder.norm_out.weight": "conv_norm_out.weight",
}
state_dict_ = {}
for name in state_dict:
if name in rename_dict:
param = state_dict[name]
if "transformer_blocks" in rename_dict[name]:
param = param.squeeze()
state_dict_[rename_dict[name]] = param
return state_dict_
class FluxVAEDecoderStateDictConverter(SDVAEDecoderStateDictConverter):
def __init__(self):
pass
def from_civitai(self, state_dict):
rename_dict = {
"decoder.conv_in.bias": "conv_in.bias",
"decoder.conv_in.weight": "conv_in.weight",
"decoder.conv_out.bias": "conv_out.bias",
"decoder.conv_out.weight": "conv_out.weight",
"decoder.mid.attn_1.k.bias": "blocks.1.transformer_blocks.0.to_k.bias",
"decoder.mid.attn_1.k.weight": "blocks.1.transformer_blocks.0.to_k.weight",
"decoder.mid.attn_1.norm.bias": "blocks.1.norm.bias",
"decoder.mid.attn_1.norm.weight": "blocks.1.norm.weight",
"decoder.mid.attn_1.proj_out.bias": "blocks.1.transformer_blocks.0.to_out.bias",
"decoder.mid.attn_1.proj_out.weight": "blocks.1.transformer_blocks.0.to_out.weight",
"decoder.mid.attn_1.q.bias": "blocks.1.transformer_blocks.0.to_q.bias",
"decoder.mid.attn_1.q.weight": "blocks.1.transformer_blocks.0.to_q.weight",
"decoder.mid.attn_1.v.bias": "blocks.1.transformer_blocks.0.to_v.bias",
"decoder.mid.attn_1.v.weight": "blocks.1.transformer_blocks.0.to_v.weight",
"decoder.mid.block_1.conv1.bias": "blocks.0.conv1.bias",
"decoder.mid.block_1.conv1.weight": "blocks.0.conv1.weight",
"decoder.mid.block_1.conv2.bias": "blocks.0.conv2.bias",
"decoder.mid.block_1.conv2.weight": "blocks.0.conv2.weight",
"decoder.mid.block_1.norm1.bias": "blocks.0.norm1.bias",
"decoder.mid.block_1.norm1.weight": "blocks.0.norm1.weight",
"decoder.mid.block_1.norm2.bias": "blocks.0.norm2.bias",
"decoder.mid.block_1.norm2.weight": "blocks.0.norm2.weight",
"decoder.mid.block_2.conv1.bias": "blocks.2.conv1.bias",
"decoder.mid.block_2.conv1.weight": "blocks.2.conv1.weight",
"decoder.mid.block_2.conv2.bias": "blocks.2.conv2.bias",
"decoder.mid.block_2.conv2.weight": "blocks.2.conv2.weight",
"decoder.mid.block_2.norm1.bias": "blocks.2.norm1.bias",
"decoder.mid.block_2.norm1.weight": "blocks.2.norm1.weight",
"decoder.mid.block_2.norm2.bias": "blocks.2.norm2.bias",
"decoder.mid.block_2.norm2.weight": "blocks.2.norm2.weight",
"decoder.norm_out.bias": "conv_norm_out.bias",
"decoder.norm_out.weight": "conv_norm_out.weight",
"decoder.up.0.block.0.conv1.bias": "blocks.15.conv1.bias",
"decoder.up.0.block.0.conv1.weight": "blocks.15.conv1.weight",
"decoder.up.0.block.0.conv2.bias": "blocks.15.conv2.bias",
"decoder.up.0.block.0.conv2.weight": "blocks.15.conv2.weight",
"decoder.up.0.block.0.nin_shortcut.bias": "blocks.15.conv_shortcut.bias",
"decoder.up.0.block.0.nin_shortcut.weight": "blocks.15.conv_shortcut.weight",
"decoder.up.0.block.0.norm1.bias": "blocks.15.norm1.bias",
"decoder.up.0.block.0.norm1.weight": "blocks.15.norm1.weight",
"decoder.up.0.block.0.norm2.bias": "blocks.15.norm2.bias",
"decoder.up.0.block.0.norm2.weight": "blocks.15.norm2.weight",
"decoder.up.0.block.1.conv1.bias": "blocks.16.conv1.bias",
"decoder.up.0.block.1.conv1.weight": "blocks.16.conv1.weight",
"decoder.up.0.block.1.conv2.bias": "blocks.16.conv2.bias",
"decoder.up.0.block.1.conv2.weight": "blocks.16.conv2.weight",
"decoder.up.0.block.1.norm1.bias": "blocks.16.norm1.bias",
"decoder.up.0.block.1.norm1.weight": "blocks.16.norm1.weight",
"decoder.up.0.block.1.norm2.bias": "blocks.16.norm2.bias",
"decoder.up.0.block.1.norm2.weight": "blocks.16.norm2.weight",
"decoder.up.0.block.2.conv1.bias": "blocks.17.conv1.bias",
"decoder.up.0.block.2.conv1.weight": "blocks.17.conv1.weight",
"decoder.up.0.block.2.conv2.bias": "blocks.17.conv2.bias",
"decoder.up.0.block.2.conv2.weight": "blocks.17.conv2.weight",
"decoder.up.0.block.2.norm1.bias": "blocks.17.norm1.bias",
"decoder.up.0.block.2.norm1.weight": "blocks.17.norm1.weight",
"decoder.up.0.block.2.norm2.bias": "blocks.17.norm2.bias",
"decoder.up.0.block.2.norm2.weight": "blocks.17.norm2.weight",
"decoder.up.1.block.0.conv1.bias": "blocks.11.conv1.bias",
"decoder.up.1.block.0.conv1.weight": "blocks.11.conv1.weight",
"decoder.up.1.block.0.conv2.bias": "blocks.11.conv2.bias",
"decoder.up.1.block.0.conv2.weight": "blocks.11.conv2.weight",
"decoder.up.1.block.0.nin_shortcut.bias": "blocks.11.conv_shortcut.bias",
"decoder.up.1.block.0.nin_shortcut.weight": "blocks.11.conv_shortcut.weight",
"decoder.up.1.block.0.norm1.bias": "blocks.11.norm1.bias",
"decoder.up.1.block.0.norm1.weight": "blocks.11.norm1.weight",
"decoder.up.1.block.0.norm2.bias": "blocks.11.norm2.bias",
"decoder.up.1.block.0.norm2.weight": "blocks.11.norm2.weight",
"decoder.up.1.block.1.conv1.bias": "blocks.12.conv1.bias",
"decoder.up.1.block.1.conv1.weight": "blocks.12.conv1.weight",
"decoder.up.1.block.1.conv2.bias": "blocks.12.conv2.bias",
"decoder.up.1.block.1.conv2.weight": "blocks.12.conv2.weight",
"decoder.up.1.block.1.norm1.bias": "blocks.12.norm1.bias",
"decoder.up.1.block.1.norm1.weight": "blocks.12.norm1.weight",
"decoder.up.1.block.1.norm2.bias": "blocks.12.norm2.bias",
"decoder.up.1.block.1.norm2.weight": "blocks.12.norm2.weight",
"decoder.up.1.block.2.conv1.bias": "blocks.13.conv1.bias",
"decoder.up.1.block.2.conv1.weight": "blocks.13.conv1.weight",
"decoder.up.1.block.2.conv2.bias": "blocks.13.conv2.bias",
"decoder.up.1.block.2.conv2.weight": "blocks.13.conv2.weight",
"decoder.up.1.block.2.norm1.bias": "blocks.13.norm1.bias",
"decoder.up.1.block.2.norm1.weight": "blocks.13.norm1.weight",
"decoder.up.1.block.2.norm2.bias": "blocks.13.norm2.bias",
"decoder.up.1.block.2.norm2.weight": "blocks.13.norm2.weight",
"decoder.up.1.upsample.conv.bias": "blocks.14.conv.bias",
"decoder.up.1.upsample.conv.weight": "blocks.14.conv.weight",
"decoder.up.2.block.0.conv1.bias": "blocks.7.conv1.bias",
"decoder.up.2.block.0.conv1.weight": "blocks.7.conv1.weight",
"decoder.up.2.block.0.conv2.bias": "blocks.7.conv2.bias",
"decoder.up.2.block.0.conv2.weight": "blocks.7.conv2.weight",
"decoder.up.2.block.0.norm1.bias": "blocks.7.norm1.bias",
"decoder.up.2.block.0.norm1.weight": "blocks.7.norm1.weight",
"decoder.up.2.block.0.norm2.bias": "blocks.7.norm2.bias",
"decoder.up.2.block.0.norm2.weight": "blocks.7.norm2.weight",
"decoder.up.2.block.1.conv1.bias": "blocks.8.conv1.bias",
"decoder.up.2.block.1.conv1.weight": "blocks.8.conv1.weight",
"decoder.up.2.block.1.conv2.bias": "blocks.8.conv2.bias",
"decoder.up.2.block.1.conv2.weight": "blocks.8.conv2.weight",
"decoder.up.2.block.1.norm1.bias": "blocks.8.norm1.bias",
"decoder.up.2.block.1.norm1.weight": "blocks.8.norm1.weight",
"decoder.up.2.block.1.norm2.bias": "blocks.8.norm2.bias",
"decoder.up.2.block.1.norm2.weight": "blocks.8.norm2.weight",
"decoder.up.2.block.2.conv1.bias": "blocks.9.conv1.bias",
"decoder.up.2.block.2.conv1.weight": "blocks.9.conv1.weight",
"decoder.up.2.block.2.conv2.bias": "blocks.9.conv2.bias",
"decoder.up.2.block.2.conv2.weight": "blocks.9.conv2.weight",
"decoder.up.2.block.2.norm1.bias": "blocks.9.norm1.bias",
"decoder.up.2.block.2.norm1.weight": "blocks.9.norm1.weight",
"decoder.up.2.block.2.norm2.bias": "blocks.9.norm2.bias",
"decoder.up.2.block.2.norm2.weight": "blocks.9.norm2.weight",
"decoder.up.2.upsample.conv.bias": "blocks.10.conv.bias",
"decoder.up.2.upsample.conv.weight": "blocks.10.conv.weight",
"decoder.up.3.block.0.conv1.bias": "blocks.3.conv1.bias",
"decoder.up.3.block.0.conv1.weight": "blocks.3.conv1.weight",
"decoder.up.3.block.0.conv2.bias": "blocks.3.conv2.bias",
"decoder.up.3.block.0.conv2.weight": "blocks.3.conv2.weight",
"decoder.up.3.block.0.norm1.bias": "blocks.3.norm1.bias",
"decoder.up.3.block.0.norm1.weight": "blocks.3.norm1.weight",
"decoder.up.3.block.0.norm2.bias": "blocks.3.norm2.bias",
"decoder.up.3.block.0.norm2.weight": "blocks.3.norm2.weight",
"decoder.up.3.block.1.conv1.bias": "blocks.4.conv1.bias",
"decoder.up.3.block.1.conv1.weight": "blocks.4.conv1.weight",
"decoder.up.3.block.1.conv2.bias": "blocks.4.conv2.bias",
"decoder.up.3.block.1.conv2.weight": "blocks.4.conv2.weight",
"decoder.up.3.block.1.norm1.bias": "blocks.4.norm1.bias",
"decoder.up.3.block.1.norm1.weight": "blocks.4.norm1.weight",
"decoder.up.3.block.1.norm2.bias": "blocks.4.norm2.bias",
"decoder.up.3.block.1.norm2.weight": "blocks.4.norm2.weight",
"decoder.up.3.block.2.conv1.bias": "blocks.5.conv1.bias",
"decoder.up.3.block.2.conv1.weight": "blocks.5.conv1.weight",
"decoder.up.3.block.2.conv2.bias": "blocks.5.conv2.bias",
"decoder.up.3.block.2.conv2.weight": "blocks.5.conv2.weight",
"decoder.up.3.block.2.norm1.bias": "blocks.5.norm1.bias",
"decoder.up.3.block.2.norm1.weight": "blocks.5.norm1.weight",
"decoder.up.3.block.2.norm2.bias": "blocks.5.norm2.bias",
"decoder.up.3.block.2.norm2.weight": "blocks.5.norm2.weight",
"decoder.up.3.upsample.conv.bias": "blocks.6.conv.bias",
"decoder.up.3.upsample.conv.weight": "blocks.6.conv.weight",
}
state_dict_ = {}
for name in state_dict:
if name in rename_dict:
param = state_dict[name]
if "transformer_blocks" in rename_dict[name]:
param = param.squeeze()
state_dict_[rename_dict[name]] = param
return state_dict_ |