File size: 5,805 Bytes
70de1d6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
from diffusers import (
    StableDiffusionXLControlNetImg2ImgPipeline,
    ControlNetModel,
    AutoencoderKL,
    AutoencoderTiny,
)
from compel import Compel, ReturnedEmbeddingsType
from pydantic import BaseModel, Field
from utils.canny_gpu import SobelOperator
import torch

try:
    import intel_extension_for_pytorch as ipex  # type: ignore
except:
    pass

import psutil
from PIL import Image
import math
import time


controlnet_model = "diffusers/controlnet-canny-sdxl-1.0"
model_id = "stabilityai/sdxl-turbo"
taesd_model = "madebyollin/taesdxl"

default_prompt = "Portrait of The Joker halloween costume, face painting, with , glare pose, detailed, intricate, full of colour, cinematic lighting, trending on artstation, 8k, hyperrealistic, focused, extreme details, unreal engine 5 cinematic, masterpiece"
default_negative_prompt = "blurry, low quality, render, 3D, oversaturated"

class Pipeline:
    class Info(BaseModel):
        name: str = "controlnet+SDXL+Turbo"
        title: str = "SDXL Turbo + Controlnet"
        description: str = "Generates an image from a text prompt"
        input_mode: str = "image"

    class InputParams(BaseModel):
        prompt: str = Field(
            default_prompt,
            title="Prompt",
            field="textarea",
            id="prompt",
        )
        negative_prompt: str = Field(
            default_negative_prompt,
            title="Negative Prompt",
            field="textarea",
            id="negative_prompt",
            hide=True,
        )
        seed: int = Field(
            2159232, min=0, title="Seed", field="seed", hide=True, id="seed"
        )
        steps: int = Field(
            2, min=1, max=15, title="Steps", field="range", hide=True, id="steps"
        )
        width: int = Field(
            512, min=2, max=15, title="Width", disabled=True, hide=True, id="width"
        )
        height: int = Field(
            512, min=2, max=15, title="Height", disabled=True, hide=True, id="height"
        )
        guidance_scale: float = Field(
            1.0,
            min=0,
            max=10,
            step=0.001,
            title="Guidance Scale",
            field="range",
            hide=True,
            id="guidance_scale",
        )
        strength: float = Field(
            0.5,
            min=0.25,
            max=1.0,
            step=0.001,
            title="Strength",
            field="range",
            hide=True,
            id="strength",
        )
        controlnet_scale: float = Field(
            0.5,
            min=0,
            max=1.0,
            step=0.001,
            title="Controlnet Scale",
            field="range",
            hide=True,
            id="controlnet_scale",
        )
        controlnet_start: float = Field(
            0.0,
            min=0,
            max=1.0,
            step=0.001,
            title="Controlnet Start",
            field="range",
            hide=True,
            id="controlnet_start",
        )
        controlnet_end: float = Field(
            1.0,
            min=0,
            max=1.0,
            step=0.001,
            title="Controlnet End",
            field="range",
            hide=True,
            id="controlnet_end",
        )
        canny_low_threshold: float = Field(
            0.31,
            min=0,
            max=1.0,
            step=0.001,
            title="Canny Low Threshold",
            field="range",
            hide=True,
            id="canny_low_threshold",
        )
        canny_high_threshold: float = Field(
            0.125,
            min=0,
            max=1.0,
            step=0.001,
            title="Canny High Threshold",
            field="range",
            hide=True,
            id="canny_high_threshold",
        )
        debug_canny: bool = Field(
            False,
            title="Debug Canny",
            field="checkbox",
            hide=True,
            id="debug_canny",
        )

    def __init__(self, device: torch.device, torch_dtype: torch.dtype):
        controlnet_canny = ControlNetModel.from_pretrained(
            controlnet_model, torch_dtype=torch_dtype
        ).to(device)

        vae = AutoencoderKL.from_pretrained(
            "madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch_dtype
        )

        self.pipe = StableDiffusionXLControlNetImg2ImgPipeline.from_pretrained(
            model_id,
            controlnet=controlnet_canny,
            vae=vae,
        )
     
        self.canny_torch = SobelOperator(device=device)

        self.pipe.set_progress_bar_config(disable=True)
        self.pipe.to(device=device, dtype=torch_dtype).to(device)
        if device.type != "mps":
            self.pipe.unet.to(memory_format=torch.channels_last)

        if psutil.virtual_memory().total < 64 * 1024**3:
            self.pipe.enable_attention_slicing()

        self.pipe.compel_proc = Compel(
            tokenizer=[self.pipe.tokenizer, self.pipe.tokenizer_2],
            text_encoder=[self.pipe.text_encoder, self.pipe.text_encoder_2],
            returned_embeddings_type=ReturnedEmbeddingsType.PENULTIMATE_HIDDEN_STATES_NON_NORMALIZED,
            requires_pooled=[False, True],
        )
        #if args.use_taesd:
        self.pipe.vae = AutoencoderTiny.from_pretrained(
            taesd_model, torch_dtype=torch_dtype, use_safetensors=True
        ).to(device)

        #if args.torch_compile:
        self.pipe.unet = torch.compile(
            self.pipe.unet, mode="reduce-overhead", fullgraph=True
        )
        self.pipe.vae = torch.compile(
            self.pipe.vae, mode="reduce-overhead", fullgraph=True
        )
        self.pipe(
            prompt="warmup",
            image=[Image.new("RGB", (512, 512))],
            control_image=[Image.new("RGB", (512, 512))],
        )