File size: 5,464 Bytes
1d3190d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2951b6b
1d3190d
 
 
 
 
46bd9ac
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1d3190d
 
 
 
 
 
 
 
46bd9ac
1d3190d
 
 
 
 
 
 
 
 
 
 
 
2951b6b
1d3190d
 
2951b6b
1d3190d
 
2951b6b
1d3190d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2951b6b
1d3190d
 
 
cf3ff1a
 
1d3190d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2951b6b
 
 
 
 
 
1d3190d
 
 
 
2951b6b
 
1d3190d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
from diffusers import (
    AutoPipelineForImage2Image,
    AutoencoderTiny,
)
from compel import Compel
import torch

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

import psutil
from config import Args
from pydantic import BaseModel, Field
from PIL import Image
import math

base_model = "SimianLuo/LCM_Dreamshaper_v7"
taesd_model = "madebyollin/taesd"

default_prompt = "Portrait of The Terminator with , glare pose, detailed, intricate, full of colour, cinematic lighting, trending on artstation, 8k, hyperrealistic, focused, extreme details, unreal engine 5 cinematic, masterpiece"
page_content = """
<h1 class="text-3xl font-bold">Real-Time Latent Consistency Model</h1>
<h3 class="text-xl font-bold">Image-to-Image LCM</h3>
<p class="text-sm">
    This demo showcases
    <a
    href="https://huggingface.co/blog/lcm_lora"
    target="_blank"
    class="text-blue-500 underline hover:no-underline">LCM</a>
Image to Image pipeline using
    <a
    href="https://huggingface.co/docs/diffusers/main/en/using-diffusers/lcm#performing-inference-with-lcm"
    target="_blank"
    class="text-blue-500 underline hover:no-underline">Diffusers</a
    > with a MJPEG stream server.
</p>
<p class="text-sm text-gray-500">
    Change the prompt to generate different images, accepts <a
    href="https://github.com/damian0815/compel/blob/main/doc/syntax.md"
    target="_blank"
    class="text-blue-500 underline hover:no-underline">Compel</a
    > syntax.
</p>
"""


class Pipeline:
    class Info(BaseModel):
        name: str = "img2img"
        title: str = "Image-to-Image LCM"
        description: str = "Generates an image from a text prompt"
        input_mode: str = "image"
        page_content: str = page_content

    class InputParams(BaseModel):
        prompt: str = Field(
            default_prompt,
            title="Prompt",
            field="textarea",
            id="prompt",
        )
        seed: int = Field(
            2159232, min=0, title="Seed", field="seed", hide=True, id="seed"
        )
        steps: int = Field(
            4, min=1, max=15, title="Steps", field="range", hide=True, id="steps"
        )
        width: int = Field(
            768, min=2, max=15, title="Width", disabled=True, hide=True, id="width"
        )
        height: int = Field(
            768, min=2, max=15, title="Height", disabled=True, hide=True, id="height"
        )
        guidance_scale: float = Field(
            0.2,
            min=0,
            max=20,
            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",
        )

    def __init__(self, args: Args, device: torch.device, torch_dtype: torch.dtype):
        if args.safety_checker:
            self.pipe = AutoPipelineForImage2Image.from_pretrained(base_model)
        else:
            self.pipe = AutoPipelineForImage2Image.from_pretrained(
                base_model,
                safety_checker=None,
            )
        if args.use_taesd:
            self.pipe.vae = AutoencoderTiny.from_pretrained(
                taesd_model, torch_dtype=torch_dtype, use_safetensors=True
            ).to(device)

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

        # check if computer has less than 64GB of RAM using sys or os
        if psutil.virtual_memory().total < 64 * 1024**3:
            self.pipe.enable_attention_slicing()

        if args.torch_compile:
            print("Running 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", (768, 768))],
            )

        self.compel_proc = Compel(
            tokenizer=self.pipe.tokenizer,
            text_encoder=self.pipe.text_encoder,
            truncate_long_prompts=False,
        )

    def predict(self, params: "Pipeline.InputParams") -> Image.Image:
        generator = torch.manual_seed(params.seed)
        prompt_embeds = self.compel_proc(params.prompt)

        steps = params.steps
        strength = params.strength
        if int(steps * strength) < 1:
            steps = math.ceil(1 / max(0.10, strength))

        results = self.pipe(
            image=params.image,
            prompt_embeds=prompt_embeds,
            generator=generator,
            strength=strength,
            num_inference_steps=steps,
            guidance_scale=params.guidance_scale,
            width=params.width,
            height=params.height,
            output_type="pil",
        )

        nsfw_content_detected = (
            results.nsfw_content_detected[0]
            if "nsfw_content_detected" in results
            else False
        )
        if nsfw_content_detected:
            return None
        result_image = results.images[0]

        return result_image