File size: 8,080 Bytes
72895aa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

import inspect
from typing import Callable, List, Optional, Union

import numpy as np
import PIL.Image

from ...utils import logging
from .pipeline_stable_diffusion import StableDiffusionPipeline
from .pipeline_stable_diffusion_img2img import StableDiffusionImg2ImgPipeline
from .pipeline_stable_diffusion_inpaint_legacy import (
    StableDiffusionInpaintPipelineLegacy,
)

logger = logging.get_logger(__name__)  # pylint: disable=invalid-name


class StableDiffusionMegaPipeline(StableDiffusionPipeline):
    r"""
    Pipeline for generation using Stable Diffusion.

    This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods the
    library implements for all the pipelines (such as downloading or saving, running on a particular xxxx, etc.)

    Args:
        vae ([`AutoencoderKL`]):
            Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.
        text_encoder ([`CLIPTextModel`]):
            Frozen text-encoder. Stable Diffusion uses the text portion of
            [CLIP](https://huggingface.co/docs/transformers/model_doc/clip#transformers.CLIPTextModel), specifically
            the [clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14) variant.
        tokenizer (`CLIPTokenizer`):
            Tokenizer of class
            [CLIPTokenizer](https://huggingface.co/docs/transformers/v4.21.0/en/model_doc/clip#transformers.CLIPTokenizer).
        unet ([`UNet2DConditionModel`]): Conditional U-Net architecture to denoise the encoded image latents.
        scheduler ([`SchedulerMixin`]):
            A scheduler to be used in combination with `unet` to denoise the encoded image latents. Can be one of
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], [`PNDMScheduler`], [`EulerDiscreteScheduler`], [`EulerAncestralDiscreteScheduler`]
            or [`DPMSolverMultistepScheduler`].
        safety_checker ([`StableDiffusionSafetyChecker`]):
            Classification module that estimates whether generated images could be considered offensive or harmful.
            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
        feature_extractor ([`CLIPFeatureExtractor`]):
            Model that extracts features from generated images to be used as inputs for the `safety_checker`.
    """
    _optional_components = ["safety_checker", "feature_extractor"]

    def __call__(self, *args, **kwargs):
        return self.text2img(*args, **kwargs)

    def text2img(
        self,
        prompt: Union[str, List[str]],
        height: Optional[int] = 512,
        width: Optional[int] = 512,
        num_inference_steps: Optional[int] = 50,
        guidance_scale: Optional[float] = 7.5,
        negative_prompt: Optional[Union[str, List[str]]] = None,
        num_images_per_prompt: Optional[int] = 1,
        eta: Optional[float] = 0.0,
        generator: Optional[np.random.RandomState] = None,
        latents: Optional[np.ndarray] = None,
        output_type: Optional[str] = "pil",
        return_dict: bool = True,
        callback: Optional[Callable[[int, int, np.ndarray], None]] = None,
        callback_steps: Optional[int] = 1,
    ):

        expected_components = inspect.signature(StableDiffusionPipeline.__init__).parameters.keys()
        components = {name: component for name, component in self.components.items() if name in expected_components}
        temp_pipeline = StableDiffusionPipeline(
            **components, requires_safety_checker=self.config.requires_safety_checker
        )
        output = temp_pipeline(
            prompt=prompt,
            height=height,
            width=width,
            num_inference_steps=num_inference_steps,
            guidance_scale=guidance_scale,
            negative_prompt=negative_prompt,
            num_images_per_prompt=num_images_per_prompt,
            eta=eta,
            generator=generator,
            latents=latents,
            output_type=output_type,
            return_dict=return_dict,
            callback=callback,
            callback_steps=callback_steps,
        )
        return output

    def img2img(
        self,
        prompt: Union[str, List[str]],
        image: Union[np.ndarray, PIL.Image.Image],
        strength: float = 0.8,
        num_inference_steps: Optional[int] = 50,
        guidance_scale: Optional[float] = 7.5,
        negative_prompt: Optional[Union[str, List[str]]] = None,
        num_images_per_prompt: Optional[int] = 1,
        eta: Optional[float] = 0.0,
        generator: Optional[np.random.RandomState] = None,
        output_type: Optional[str] = "pil",
        return_dict: bool = True,
        callback: Optional[Callable[[int, int, np.ndarray], None]] = None,
        callback_steps: Optional[int] = 1,
    ):
        expected_components = inspect.signature(StableDiffusionImg2ImgPipeline.__init__).parameters.keys()
        components = {name: component for name, component in self.components.items() if name in expected_components}
        temp_pipeline = StableDiffusionImg2ImgPipeline(
            **components, requires_safety_checker=self.config.requires_safety_checker
        )
        output = temp_pipeline(
            prompt=prompt,
            image=image,
            strength=strength,
            num_inference_steps=num_inference_steps,
            guidance_scale=guidance_scale,
            negative_prompt=negative_prompt,
            num_images_per_prompt=num_images_per_prompt,
            eta=eta,
            generator=generator,
            output_type=output_type,
            return_dict=return_dict,
            callback=callback,
            callback_steps=callback_steps,
        )

        return output

    def inpaint_legacy(
        self,
        prompt: Union[str, List[str]],
        image: Union[np.ndarray, PIL.Image.Image],
        mask_image: Union[np.ndarray, PIL.Image.Image],
        strength: float = 0.8,
        num_inference_steps: Optional[int] = 50,
        guidance_scale: Optional[float] = 7.5,
        negative_prompt: Optional[Union[str, List[str]]] = None,
        num_images_per_prompt: Optional[int] = 1,
        eta: Optional[float] = 0.0,
        generator: Optional[np.random.RandomState] = None,
        output_type: Optional[str] = "pil",
        return_dict: bool = True,
        callback: Optional[Callable[[int, int, np.ndarray], None]] = None,
        callback_steps: Optional[int] = 1,
    ):
        expected_components = inspect.signature(StableDiffusionInpaintPipelineLegacy.__init__).parameters.keys()
        components = {name: component for name, component in self.components.items() if name in expected_components}
        temp_pipeline = StableDiffusionInpaintPipelineLegacy(
            **components, requires_safety_checker=self.config.requires_safety_checker
        )
        output = temp_pipeline(
            prompt=prompt,
            image=image,
            mask_image=mask_image,
            strength=strength,
            num_inference_steps=num_inference_steps,
            guidance_scale=guidance_scale,
            negative_prompt=negative_prompt,
            num_images_per_prompt=num_images_per_prompt,
            eta=eta,
            generator=generator,
            output_type=output_type,
            return_dict=return_dict,
            callback=callback,
            callback_steps=callback_steps,
        )

        return output