File size: 1,481 Bytes
393b5eb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9c61b4b
 
393b5eb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
from transformers.tools.base import Tool, get_default_device
from transformers.utils import is_accelerate_available, is_diffusers_available

if is_diffusers_available():
    from diffusers import DiffusionPipeline


TEXT_TO_IMAGE_DESCRIPTION = (
    "This is a tool that creates an image according to a prompt, which is a text description. It takes an input named `prompt` which "
    "contains the image description and outputs an image."
)


class TextToImageTool(Tool):
    default_checkpoint = "runwayml/stable-diffusion-v1-5"
    description = TEXT_TO_IMAGE_DESCRIPTION
    inputs = ['text']
    outputs = ['image']

    def __init__(self, device=None, **hub_kwargs) -> None:
        if not is_accelerate_available():
            raise ImportError("Accelerate should be installed in order to use tools.")
        if not is_diffusers_available():
            raise ImportError("Diffusers should be installed in order to use the StableDiffusionTool.")

        super().__init__()

        self.device = device
        self.pipeline = None
        self.hub_kwargs = hub_kwargs

    def setup(self):
        if self.device is None:
            self.device = get_default_device()

        self.pipeline = DiffusionPipeline.from_pretrained(self.default_checkpoint)
        self.pipeline.to(self.device)

        self.is_initialized = True

    def __call__(self, prompt):
        if not self.is_initialized:
            self.setup()

        return self.pipeline(prompt).images[0]