-
Notifications
You must be signed in to change notification settings - Fork 569
Expand file tree
/
Copy pathdiffusion_model.hpp
More file actions
519 lines (423 loc) · 18.3 KB
/
diffusion_model.hpp
File metadata and controls
519 lines (423 loc) · 18.3 KB
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
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
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
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
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
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
#ifndef __DIFFUSION_MODEL_H__
#define __DIFFUSION_MODEL_H__
#include <optional>
#include "anima.hpp"
#include "flux.hpp"
#include "mmdit.hpp"
#include "qwen_image.hpp"
#include "tensor_ggml.hpp"
#include "unet.hpp"
#include "wan.hpp"
#include "z_image.hpp"
struct DiffusionParams {
const sd::Tensor<float>* x = nullptr;
const sd::Tensor<float>* timesteps = nullptr;
const sd::Tensor<float>* context = nullptr;
const sd::Tensor<float>* c_concat = nullptr;
const sd::Tensor<float>* y = nullptr;
const sd::Tensor<int32_t>* t5_ids = nullptr;
const sd::Tensor<float>* t5_weights = nullptr;
const sd::Tensor<float>* guidance = nullptr;
const std::vector<sd::Tensor<float>>* ref_latents = nullptr;
bool increase_ref_index = false;
int num_video_frames = -1;
const std::vector<sd::Tensor<float>>* controls = nullptr;
float control_strength = 0.f;
const sd::Tensor<float>* vace_context = nullptr;
float vace_strength = 1.f;
const std::vector<int>* skip_layers = nullptr;
};
template <typename T>
static inline const sd::Tensor<T>& tensor_or_empty(const sd::Tensor<T>* tensor) {
static const sd::Tensor<T> kEmpty;
return tensor != nullptr ? *tensor : kEmpty;
}
struct DiffusionModel {
virtual std::string get_desc() = 0;
virtual sd::Tensor<float> compute(int n_threads,
const DiffusionParams& diffusion_params) = 0;
virtual void alloc_params_buffer() = 0;
virtual void free_params_buffer() = 0;
virtual void free_compute_buffer() = 0;
virtual void get_param_tensors(std::map<std::string, ggml_tensor*>& tensors) = 0;
virtual size_t get_params_buffer_size() = 0;
virtual void set_weight_adapter(const std::shared_ptr<WeightAdapter>& adapter){};
virtual int64_t get_adm_in_channels() = 0;
virtual void set_flash_attention_enabled(bool enabled) = 0;
virtual void set_circular_axes(bool circular_x, bool circular_y) = 0;
};
struct UNetModel : public DiffusionModel {
UNetModelRunner unet;
UNetModel(ggml_backend_t backend,
bool offload_params_to_cpu,
const String2TensorStorage& tensor_storage_map = {},
SDVersion version = VERSION_SD1)
: unet(backend, offload_params_to_cpu, tensor_storage_map, "model.diffusion_model", version) {
}
std::string get_desc() override {
return unet.get_desc();
}
void alloc_params_buffer() override {
unet.alloc_params_buffer();
}
void free_params_buffer() override {
unet.free_params_buffer();
}
void free_compute_buffer() override {
unet.free_compute_buffer();
}
void get_param_tensors(std::map<std::string, ggml_tensor*>& tensors) override {
unet.get_param_tensors(tensors, "model.diffusion_model");
}
size_t get_params_buffer_size() override {
return unet.get_params_buffer_size();
}
void set_weight_adapter(const std::shared_ptr<WeightAdapter>& adapter) override {
unet.set_weight_adapter(adapter);
}
int64_t get_adm_in_channels() override {
return unet.unet.adm_in_channels;
}
void set_flash_attention_enabled(bool enabled) {
unet.set_flash_attention_enabled(enabled);
}
void set_circular_axes(bool circular_x, bool circular_y) override {
unet.set_circular_axes(circular_x, circular_y);
}
sd::Tensor<float> compute(int n_threads,
const DiffusionParams& diffusion_params) override {
GGML_ASSERT(diffusion_params.x != nullptr);
GGML_ASSERT(diffusion_params.timesteps != nullptr);
static const std::vector<sd::Tensor<float>> empty_controls;
return unet.compute(n_threads,
*diffusion_params.x,
*diffusion_params.timesteps,
tensor_or_empty(diffusion_params.context),
tensor_or_empty(diffusion_params.c_concat),
tensor_or_empty(diffusion_params.y),
diffusion_params.num_video_frames,
diffusion_params.controls ? *diffusion_params.controls : empty_controls,
diffusion_params.control_strength);
}
};
struct MMDiTModel : public DiffusionModel {
MMDiTRunner mmdit;
MMDiTModel(ggml_backend_t backend,
bool offload_params_to_cpu,
const String2TensorStorage& tensor_storage_map = {})
: mmdit(backend, offload_params_to_cpu, tensor_storage_map, "model.diffusion_model") {
}
std::string get_desc() override {
return mmdit.get_desc();
}
void alloc_params_buffer() override {
mmdit.alloc_params_buffer();
}
void free_params_buffer() override {
mmdit.free_params_buffer();
}
void free_compute_buffer() override {
mmdit.free_compute_buffer();
}
void get_param_tensors(std::map<std::string, ggml_tensor*>& tensors) override {
mmdit.get_param_tensors(tensors, "model.diffusion_model");
}
size_t get_params_buffer_size() override {
return mmdit.get_params_buffer_size();
}
void set_weight_adapter(const std::shared_ptr<WeightAdapter>& adapter) override {
mmdit.set_weight_adapter(adapter);
}
int64_t get_adm_in_channels() override {
return 768 + 1280;
}
void set_flash_attention_enabled(bool enabled) {
mmdit.set_flash_attention_enabled(enabled);
}
void set_circular_axes(bool circular_x, bool circular_y) override {
mmdit.set_circular_axes(circular_x, circular_y);
}
sd::Tensor<float> compute(int n_threads,
const DiffusionParams& diffusion_params) override {
GGML_ASSERT(diffusion_params.x != nullptr);
GGML_ASSERT(diffusion_params.timesteps != nullptr);
static const std::vector<int> empty_skip_layers;
return mmdit.compute(n_threads,
*diffusion_params.x,
*diffusion_params.timesteps,
tensor_or_empty(diffusion_params.context),
tensor_or_empty(diffusion_params.y),
diffusion_params.skip_layers ? *diffusion_params.skip_layers : empty_skip_layers);
}
};
struct FluxModel : public DiffusionModel {
Flux::FluxRunner flux;
FluxModel(ggml_backend_t backend,
bool offload_params_to_cpu,
const String2TensorStorage& tensor_storage_map = {},
SDVersion version = VERSION_FLUX,
bool use_mask = false)
: flux(backend, offload_params_to_cpu, tensor_storage_map, "model.diffusion_model", version, use_mask) {
}
std::string get_desc() override {
return flux.get_desc();
}
void alloc_params_buffer() override {
flux.alloc_params_buffer();
}
void free_params_buffer() override {
flux.free_params_buffer();
}
void free_compute_buffer() override {
flux.free_compute_buffer();
}
void get_param_tensors(std::map<std::string, ggml_tensor*>& tensors) override {
flux.get_param_tensors(tensors, "model.diffusion_model");
}
size_t get_params_buffer_size() override {
return flux.get_params_buffer_size();
}
void set_weight_adapter(const std::shared_ptr<WeightAdapter>& adapter) override {
flux.set_weight_adapter(adapter);
}
int64_t get_adm_in_channels() override {
return 768;
}
void set_flash_attention_enabled(bool enabled) {
flux.set_flash_attention_enabled(enabled);
}
void set_circular_axes(bool circular_x, bool circular_y) override {
flux.set_circular_axes(circular_x, circular_y);
}
sd::Tensor<float> compute(int n_threads,
const DiffusionParams& diffusion_params) override {
GGML_ASSERT(diffusion_params.x != nullptr);
GGML_ASSERT(diffusion_params.timesteps != nullptr);
static const std::vector<sd::Tensor<float>> empty_ref_latents;
static const std::vector<int> empty_skip_layers;
return flux.compute(n_threads,
*diffusion_params.x,
*diffusion_params.timesteps,
tensor_or_empty(diffusion_params.context),
tensor_or_empty(diffusion_params.c_concat),
tensor_or_empty(diffusion_params.y),
tensor_or_empty(diffusion_params.guidance),
diffusion_params.ref_latents ? *diffusion_params.ref_latents : empty_ref_latents,
diffusion_params.increase_ref_index,
diffusion_params.skip_layers ? *diffusion_params.skip_layers : empty_skip_layers);
}
};
struct AnimaModel : public DiffusionModel {
std::string prefix;
Anima::AnimaRunner anima;
AnimaModel(ggml_backend_t backend,
bool offload_params_to_cpu,
const String2TensorStorage& tensor_storage_map = {},
const std::string prefix = "model.diffusion_model")
: prefix(prefix), anima(backend, offload_params_to_cpu, tensor_storage_map, prefix) {
}
std::string get_desc() override {
return anima.get_desc();
}
void alloc_params_buffer() override {
anima.alloc_params_buffer();
}
void free_params_buffer() override {
anima.free_params_buffer();
}
void free_compute_buffer() override {
anima.free_compute_buffer();
}
void get_param_tensors(std::map<std::string, ggml_tensor*>& tensors) override {
anima.get_param_tensors(tensors, prefix);
}
size_t get_params_buffer_size() override {
return anima.get_params_buffer_size();
}
void set_weight_adapter(const std::shared_ptr<WeightAdapter>& adapter) override {
anima.set_weight_adapter(adapter);
}
int64_t get_adm_in_channels() override {
return 768;
}
void set_flash_attention_enabled(bool enabled) {
anima.set_flash_attention_enabled(enabled);
}
void set_circular_axes(bool circular_x, bool circular_y) override {
anima.set_circular_axes(circular_x, circular_y);
}
sd::Tensor<float> compute(int n_threads,
const DiffusionParams& diffusion_params) override {
GGML_ASSERT(diffusion_params.x != nullptr);
GGML_ASSERT(diffusion_params.timesteps != nullptr);
return anima.compute(n_threads,
*diffusion_params.x,
*diffusion_params.timesteps,
tensor_or_empty(diffusion_params.context),
tensor_or_empty(diffusion_params.t5_ids),
tensor_or_empty(diffusion_params.t5_weights));
}
};
struct WanModel : public DiffusionModel {
std::string prefix;
WAN::WanRunner wan;
WanModel(ggml_backend_t backend,
bool offload_params_to_cpu,
const String2TensorStorage& tensor_storage_map = {},
const std::string prefix = "model.diffusion_model",
SDVersion version = VERSION_WAN2)
: prefix(prefix), wan(backend, offload_params_to_cpu, tensor_storage_map, prefix, version) {
}
std::string get_desc() override {
return wan.get_desc();
}
void alloc_params_buffer() override {
wan.alloc_params_buffer();
}
void free_params_buffer() override {
wan.free_params_buffer();
}
void free_compute_buffer() override {
wan.free_compute_buffer();
}
void get_param_tensors(std::map<std::string, ggml_tensor*>& tensors) override {
wan.get_param_tensors(tensors, prefix);
}
size_t get_params_buffer_size() override {
return wan.get_params_buffer_size();
}
void set_weight_adapter(const std::shared_ptr<WeightAdapter>& adapter) override {
wan.set_weight_adapter(adapter);
}
int64_t get_adm_in_channels() override {
return 768;
}
void set_flash_attention_enabled(bool enabled) {
wan.set_flash_attention_enabled(enabled);
}
void set_circular_axes(bool circular_x, bool circular_y) override {
wan.set_circular_axes(circular_x, circular_y);
}
sd::Tensor<float> compute(int n_threads,
const DiffusionParams& diffusion_params) override {
GGML_ASSERT(diffusion_params.x != nullptr);
GGML_ASSERT(diffusion_params.timesteps != nullptr);
return wan.compute(n_threads,
*diffusion_params.x,
*diffusion_params.timesteps,
tensor_or_empty(diffusion_params.context),
tensor_or_empty(diffusion_params.y),
tensor_or_empty(diffusion_params.c_concat),
sd::Tensor<float>(),
tensor_or_empty(diffusion_params.vace_context),
diffusion_params.vace_strength);
}
};
struct QwenImageModel : public DiffusionModel {
std::string prefix;
Qwen::QwenImageRunner qwen_image;
QwenImageModel(ggml_backend_t backend,
bool offload_params_to_cpu,
const String2TensorStorage& tensor_storage_map = {},
const std::string prefix = "model.diffusion_model",
SDVersion version = VERSION_QWEN_IMAGE,
bool zero_cond_t = false)
: prefix(prefix), qwen_image(backend, offload_params_to_cpu, tensor_storage_map, prefix, version, zero_cond_t) {
}
std::string get_desc() override {
return qwen_image.get_desc();
}
void alloc_params_buffer() override {
qwen_image.alloc_params_buffer();
}
void free_params_buffer() override {
qwen_image.free_params_buffer();
}
void free_compute_buffer() override {
qwen_image.free_compute_buffer();
}
void get_param_tensors(std::map<std::string, ggml_tensor*>& tensors) override {
qwen_image.get_param_tensors(tensors, prefix);
}
size_t get_params_buffer_size() override {
return qwen_image.get_params_buffer_size();
}
void set_weight_adapter(const std::shared_ptr<WeightAdapter>& adapter) override {
qwen_image.set_weight_adapter(adapter);
}
int64_t get_adm_in_channels() override {
return 768;
}
void set_flash_attention_enabled(bool enabled) {
qwen_image.set_flash_attention_enabled(enabled);
}
void set_circular_axes(bool circular_x, bool circular_y) override {
qwen_image.set_circular_axes(circular_x, circular_y);
}
sd::Tensor<float> compute(int n_threads,
const DiffusionParams& diffusion_params) override {
GGML_ASSERT(diffusion_params.x != nullptr);
GGML_ASSERT(diffusion_params.timesteps != nullptr);
static const std::vector<sd::Tensor<float>> empty_ref_latents;
return qwen_image.compute(n_threads,
*diffusion_params.x,
*diffusion_params.timesteps,
tensor_or_empty(diffusion_params.context),
diffusion_params.ref_latents ? *diffusion_params.ref_latents : empty_ref_latents,
true);
}
};
struct ZImageModel : public DiffusionModel {
std::string prefix;
ZImage::ZImageRunner z_image;
ZImageModel(ggml_backend_t backend,
bool offload_params_to_cpu,
const String2TensorStorage& tensor_storage_map = {},
const std::string prefix = "model.diffusion_model",
SDVersion version = VERSION_Z_IMAGE)
: prefix(prefix), z_image(backend, offload_params_to_cpu, tensor_storage_map, prefix, version) {
}
std::string get_desc() override {
return z_image.get_desc();
}
void alloc_params_buffer() override {
z_image.alloc_params_buffer();
}
void free_params_buffer() override {
z_image.free_params_buffer();
}
void free_compute_buffer() override {
z_image.free_compute_buffer();
}
void get_param_tensors(std::map<std::string, ggml_tensor*>& tensors) override {
z_image.get_param_tensors(tensors, prefix);
}
size_t get_params_buffer_size() override {
return z_image.get_params_buffer_size();
}
void set_weight_adapter(const std::shared_ptr<WeightAdapter>& adapter) override {
z_image.set_weight_adapter(adapter);
}
int64_t get_adm_in_channels() override {
return 768;
}
void set_flash_attention_enabled(bool enabled) {
z_image.set_flash_attention_enabled(enabled);
}
void set_circular_axes(bool circular_x, bool circular_y) override {
z_image.set_circular_axes(circular_x, circular_y);
}
sd::Tensor<float> compute(int n_threads,
const DiffusionParams& diffusion_params) override {
GGML_ASSERT(diffusion_params.x != nullptr);
GGML_ASSERT(diffusion_params.timesteps != nullptr);
static const std::vector<sd::Tensor<float>> empty_ref_latents;
return z_image.compute(n_threads,
*diffusion_params.x,
*diffusion_params.timesteps,
tensor_or_empty(diffusion_params.context),
diffusion_params.ref_latents ? *diffusion_params.ref_latents : empty_ref_latents,
true);
}
};
#endif