unitorch.models.diffusers¤
StableProcessor¤
Bases: HfTextClassificationProcessor
Source code in src/unitorch/models/diffusers/processing_stable.py
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 |
|
StableForText2ImageGeneration¤
Bases: GenericStableModel
Source code in src/unitorch/models/diffusers/modeling_stable.py
261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 |
|
StableForImage2ImageGeneration¤
Bases: GenericStableModel
Source code in src/unitorch/models/diffusers/modeling_stable.py
393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 |
|
StableForImageInpainting¤
Bases: GenericStableModel
Source code in src/unitorch/models/diffusers/modeling_stable.py
477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 |
|
StableForImageResolution¤
Bases: GenericStableModel
Source code in src/unitorch/models/diffusers/modeling_stable.py
633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 |
|
StableXLProcessor¤
Source code in src/unitorch/models/diffusers/processing_stable_xl.py
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 |
|
StableXLForText2ImageGeneration¤
Bases: GenericStableXLModel
Source code in src/unitorch/models/diffusers/modeling_stable_xl.py
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 |
|
StableXLForImage2ImageGeneration¤
Bases: GenericStableXLModel
Source code in src/unitorch/models/diffusers/modeling_stable_xl.py
422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 |
|
StableXLForImageInpainting¤
Bases: GenericStableXLModel
Source code in src/unitorch/models/diffusers/modeling_stable_xl.py
518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 |
|
ControlNetForText2ImageGeneration¤
Bases: GenericStableModel
Source code in src/unitorch/models/diffusers/modeling_controlnet.py
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 |
|
ControlNetForImage2ImageGeneration¤
Bases: GenericStableModel
Source code in src/unitorch/models/diffusers/modeling_controlnet.py
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 |
|
ControlNetForImageInpainting¤
Bases: GenericStableModel
Source code in src/unitorch/models/diffusers/modeling_controlnet.py
289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 |
|
ControlNetXLForText2ImageGeneration¤
Bases: GenericStableXLModel
ControlNetXL model for text-to-image generation.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
config_path |
str
|
Path to the model configuration file. |
required |
text_config_path |
str
|
Path to the text model configuration file. |
required |
text2_config_path |
str
|
Path to the second text model configuration file. |
required |
vae_config_path |
str
|
Path to the VAE model configuration file. |
required |
controlnet_configs_path |
str
|
Path to the ControlNet model configuration file. |
required |
scheduler_config_path |
str
|
Path to the scheduler configuration file. |
required |
quant_config_path |
Optional[str]
|
Path to the quantization configuration file (default: None). |
None
|
image_size |
Optional[int]
|
Size of the input image (default: None). |
None
|
in_channels |
Optional[int]
|
Number of input channels (default: None). |
None
|
out_channels |
Optional[int]
|
Number of output channels (default: None). |
None
|
num_train_timesteps |
Optional[int]
|
Number of training timesteps (default: 1000). |
1000
|
num_infer_timesteps |
Optional[int]
|
Number of inference timesteps (default: 50). |
50
|
freeze_vae_encoder |
Optional[bool]
|
Whether to freeze the VAE encoder (default: True). |
True
|
freeze_text_encoder |
Optional[bool]
|
Whether to freeze the text encoder (default: True). |
True
|
freeze_unet_encoder |
Optional[bool]
|
Whether to freeze the UNet encoder (default: True). |
False
|
seed |
Optional[int]
|
Random seed (default: 1123). |
1123
|
Source code in src/unitorch/models/diffusers/modeling_controlnet_xl.py
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 |
|
forward ¤
forward(
input_ids: Tensor,
input2_ids: Tensor,
add_time_ids: Tensor,
pixel_values: Tensor,
condition_pixel_values: Tensor,
attention_mask: Optional[Tensor] = None,
attention2_mask: Optional[Tensor] = None,
)
Forward pass of the model.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
input_ids |
Tensor
|
Input IDs. |
required |
input2_ids |
Tensor
|
Second input IDs. |
required |
add_time_ids |
Tensor
|
Additional time IDs. |
required |
pixel_values |
Tensor
|
Pixel values. |
required |
condition_pixel_values |
Tensor
|
Condition pixel values. |
required |
attention_mask |
Optional[Tensor]
|
Attention mask (default: None). |
None
|
attention2_mask |
Optional[Tensor]
|
Second attention mask (default: None). |
None
|
Returns:
Type | Description |
---|---|
torch.Tensor: Loss value. |
Source code in src/unitorch/models/diffusers/modeling_controlnet_xl.py
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 |
|
generate ¤
generate(
condition_pixel_values: Tensor,
input_ids: Tensor,
input2_ids: Tensor,
negative_input_ids: Tensor,
negative_input2_ids: Tensor,
attention_mask: Optional[Tensor] = None,
attention2_mask: Optional[Tensor] = None,
negative_attention_mask: Optional[Tensor] = None,
negative_attention2_mask: Optional[Tensor] = None,
height: Optional[int] = 1024,
width: Optional[int] = 1024,
guidance_scale: Optional[float] = 5.0,
controlnet_conditioning_scale: Optional[
Union[float, List[float]]
] = 1.0,
)
Generate images using the model.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
condition_pixel_values |
Tensor
|
Condition pixel values. |
required |
input_ids |
Tensor
|
Input IDs. |
required |
input2_ids |
Tensor
|
Second input IDs. |
required |
negative_input_ids |
Tensor
|
Negative input IDs. |
required |
negative_input2_ids |
Tensor
|
Negative second input IDs. |
required |
attention_mask |
Optional[Tensor]
|
Attention mask (default: None). |
None
|
attention2_mask |
Optional[Tensor]
|
Second attention mask (default: None). |
None
|
negative_attention_mask |
Optional[Tensor]
|
Negative attention mask (default: None). |
None
|
negative_attention2_mask |
Optional[Tensor]
|
Negative second attention mask (default: None). |
None
|
height |
Optional[int]
|
Height of the generated images (default: 1024). |
1024
|
width |
Optional[int]
|
Width of the generated images (default: 1024). |
1024
|
guidance_scale |
Optional[float]
|
Scale for guidance (default: 5.0). |
5.0
|
Returns:
Name | Type | Description |
---|---|---|
GenericOutputs |
Generated images. |
Source code in src/unitorch/models/diffusers/modeling_controlnet_xl.py
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 |
|
ControlNetXLForImage2ImageGeneration¤
Bases: GenericStableXLModel
Source code in src/unitorch/models/diffusers/modeling_controlnet_xl.py
275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 |
|
ControlNetXLForImageInpainting¤
Bases: GenericStableXLModel
Source code in src/unitorch/models/diffusers/modeling_controlnet_xl.py
392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 |
|