forked from huggingface/diffusers
-
Notifications
You must be signed in to change notification settings - Fork 0
/
base_classes.py
297 lines (230 loc) · 10 KB
/
base_classes.py
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
import os
import sys
import torch
from diffusers import (
AutoPipelineForImage2Image,
AutoPipelineForInpainting,
AutoPipelineForText2Image,
ControlNetModel,
LCMScheduler,
StableDiffusionAdapterPipeline,
StableDiffusionControlNetPipeline,
StableDiffusionXLAdapterPipeline,
StableDiffusionXLControlNetPipeline,
T2IAdapter,
WuerstchenCombinedPipeline,
)
from diffusers.utils import load_image
sys.path.append(".")
from utils import ( # noqa: E402
BASE_PATH,
PROMPT,
BenchmarkInfo,
benchmark_fn,
bytes_to_giga_bytes,
flush,
generate_csv_dict,
write_to_csv,
)
RESOLUTION_MAPPING = {
"runwayml/stable-diffusion-v1-5": (512, 512),
"lllyasviel/sd-controlnet-canny": (512, 512),
"diffusers/controlnet-canny-sdxl-1.0": (1024, 1024),
"TencentARC/t2iadapter_canny_sd14v1": (512, 512),
"TencentARC/t2i-adapter-canny-sdxl-1.0": (1024, 1024),
"stabilityai/stable-diffusion-2-1": (768, 768),
"stabilityai/stable-diffusion-xl-base-1.0": (1024, 1024),
"stabilityai/stable-diffusion-xl-refiner-1.0": (1024, 1024),
"stabilityai/sdxl-turbo": (512, 512),
}
class BaseBenchmak:
pipeline_class = None
def __init__(self, args):
super().__init__()
def run_inference(self, args):
raise NotImplementedError
def benchmark(self, args):
raise NotImplementedError
def get_result_filepath(self, args):
pipeline_class_name = str(self.pipe.__class__.__name__)
name = (
args.ckpt.replace("/", "_")
+ "_"
+ pipeline_class_name
+ f"-bs@{args.batch_size}-steps@{args.num_inference_steps}-mco@{args.model_cpu_offload}-compile@{args.run_compile}.csv"
)
filepath = os.path.join(BASE_PATH, name)
return filepath
class TextToImageBenchmark(BaseBenchmak):
pipeline_class = AutoPipelineForText2Image
def __init__(self, args):
pipe = self.pipeline_class.from_pretrained(args.ckpt, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
if args.run_compile:
if not isinstance(pipe, WuerstchenCombinedPipeline):
pipe.unet.to(memory_format=torch.channels_last)
print("Run torch compile")
pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
if hasattr(pipe, "movq") and getattr(pipe, "movq", None) is not None:
pipe.movq.to(memory_format=torch.channels_last)
pipe.movq = torch.compile(pipe.movq, mode="reduce-overhead", fullgraph=True)
else:
print("Run torch compile")
pipe.decoder = torch.compile(pipe.decoder, mode="reduce-overhead", fullgraph=True)
pipe.vqgan = torch.compile(pipe.vqgan, mode="reduce-overhead", fullgraph=True)
pipe.set_progress_bar_config(disable=True)
self.pipe = pipe
def run_inference(self, pipe, args):
_ = pipe(
prompt=PROMPT,
num_inference_steps=args.num_inference_steps,
num_images_per_prompt=args.batch_size,
)
def benchmark(self, args):
flush()
print(f"[INFO] {self.pipe.__class__.__name__}: Running benchmark with: {vars(args)}\n")
time = benchmark_fn(self.run_inference, self.pipe, args) # in seconds.
memory = bytes_to_giga_bytes(torch.cuda.max_memory_allocated()) # in GBs.
benchmark_info = BenchmarkInfo(time=time, memory=memory)
pipeline_class_name = str(self.pipe.__class__.__name__)
flush()
csv_dict = generate_csv_dict(
pipeline_cls=pipeline_class_name, ckpt=args.ckpt, args=args, benchmark_info=benchmark_info
)
filepath = self.get_result_filepath(args)
write_to_csv(filepath, csv_dict)
print(f"Logs written to: {filepath}")
flush()
class TurboTextToImageBenchmark(TextToImageBenchmark):
def __init__(self, args):
super().__init__(args)
def run_inference(self, pipe, args):
_ = pipe(
prompt=PROMPT,
num_inference_steps=args.num_inference_steps,
num_images_per_prompt=args.batch_size,
guidance_scale=0.0,
)
class LCMLoRATextToImageBenchmark(TextToImageBenchmark):
lora_id = "latent-consistency/lcm-lora-sdxl"
def __init__(self, args):
super().__init__(args)
self.pipe.load_lora_weights(self.lora_id)
self.pipe.fuse_lora()
self.pipe.scheduler = LCMScheduler.from_config(self.pipe.scheduler.config)
def get_result_filepath(self, args):
pipeline_class_name = str(self.pipe.__class__.__name__)
name = (
self.lora_id.replace("/", "_")
+ "_"
+ pipeline_class_name
+ f"-bs@{args.batch_size}-steps@{args.num_inference_steps}-mco@{args.model_cpu_offload}-compile@{args.run_compile}.csv"
)
filepath = os.path.join(BASE_PATH, name)
return filepath
def run_inference(self, pipe, args):
_ = pipe(
prompt=PROMPT,
num_inference_steps=args.num_inference_steps,
num_images_per_prompt=args.batch_size,
guidance_scale=1.0,
)
class ImageToImageBenchmark(TextToImageBenchmark):
pipeline_class = AutoPipelineForImage2Image
url = "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/benchmarking/1665_Girl_with_a_Pearl_Earring.jpg"
image = load_image(url).convert("RGB")
def __init__(self, args):
super().__init__(args)
self.image = self.image.resize(RESOLUTION_MAPPING[args.ckpt])
def run_inference(self, pipe, args):
_ = pipe(
prompt=PROMPT,
image=self.image,
num_inference_steps=args.num_inference_steps,
num_images_per_prompt=args.batch_size,
)
class TurboImageToImageBenchmark(ImageToImageBenchmark):
def __init__(self, args):
super().__init__(args)
def run_inference(self, pipe, args):
_ = pipe(
prompt=PROMPT,
image=self.image,
num_inference_steps=args.num_inference_steps,
num_images_per_prompt=args.batch_size,
guidance_scale=0.0,
strength=0.5,
)
class InpaintingBenchmark(ImageToImageBenchmark):
pipeline_class = AutoPipelineForInpainting
mask_url = "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/benchmarking/overture-creations-5sI6fQgYIuo_mask.png"
mask = load_image(mask_url).convert("RGB")
def __init__(self, args):
super().__init__(args)
self.image = self.image.resize(RESOLUTION_MAPPING[args.ckpt])
self.mask = self.mask.resize(RESOLUTION_MAPPING[args.ckpt])
def run_inference(self, pipe, args):
_ = pipe(
prompt=PROMPT,
image=self.image,
mask_image=self.mask,
num_inference_steps=args.num_inference_steps,
num_images_per_prompt=args.batch_size,
)
class ControlNetBenchmark(TextToImageBenchmark):
pipeline_class = StableDiffusionControlNetPipeline
aux_network_class = ControlNetModel
root_ckpt = "runwayml/stable-diffusion-v1-5"
url = "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/benchmarking/canny_image_condition.png"
image = load_image(url).convert("RGB")
def __init__(self, args):
aux_network = self.aux_network_class.from_pretrained(args.ckpt, torch_dtype=torch.float16)
pipe = self.pipeline_class.from_pretrained(self.root_ckpt, controlnet=aux_network, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
pipe.set_progress_bar_config(disable=True)
self.pipe = pipe
if args.run_compile:
pipe.unet.to(memory_format=torch.channels_last)
pipe.controlnet.to(memory_format=torch.channels_last)
print("Run torch compile")
pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
pipe.controlnet = torch.compile(pipe.controlnet, mode="reduce-overhead", fullgraph=True)
self.image = self.image.resize(RESOLUTION_MAPPING[args.ckpt])
def run_inference(self, pipe, args):
_ = pipe(
prompt=PROMPT,
image=self.image,
num_inference_steps=args.num_inference_steps,
num_images_per_prompt=args.batch_size,
)
class ControlNetSDXLBenchmark(ControlNetBenchmark):
pipeline_class = StableDiffusionXLControlNetPipeline
root_ckpt = "stabilityai/stable-diffusion-xl-base-1.0"
def __init__(self, args):
super().__init__(args)
class T2IAdapterBenchmark(ControlNetBenchmark):
pipeline_class = StableDiffusionAdapterPipeline
aux_network_class = T2IAdapter
root_ckpt = "CompVis/stable-diffusion-v1-4"
url = "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/benchmarking/canny_for_adapter.png"
image = load_image(url).convert("L")
def __init__(self, args):
aux_network = self.aux_network_class.from_pretrained(args.ckpt, torch_dtype=torch.float16)
pipe = self.pipeline_class.from_pretrained(self.root_ckpt, adapter=aux_network, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
pipe.set_progress_bar_config(disable=True)
self.pipe = pipe
if args.run_compile:
pipe.unet.to(memory_format=torch.channels_last)
pipe.adapter.to(memory_format=torch.channels_last)
print("Run torch compile")
pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
pipe.adapter = torch.compile(pipe.adapter, mode="reduce-overhead", fullgraph=True)
self.image = self.image.resize(RESOLUTION_MAPPING[args.ckpt])
class T2IAdapterSDXLBenchmark(T2IAdapterBenchmark):
pipeline_class = StableDiffusionXLAdapterPipeline
root_ckpt = "stabilityai/stable-diffusion-xl-base-1.0"
url = "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/benchmarking/canny_for_adapter_sdxl.png"
image = load_image(url)
def __init__(self, args):
super().__init__(args)