File size: 2,530 Bytes
6853258 c3c0857 6853258 c3c0857 6853258 5cbbc02 6853258 c3c0857 6853258 c3c0857 dd5eade 6853258 cf3e24a 0911685 cf3e24a 6853258 ed1d8d0 6853258 cf3e24a c3c0857 cf3e24a 6853258 |
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 |
import numpy as np
import torch
from transformers.tools.base import Tool, get_default_device
from transformers.utils import (
is_accelerate_available,
is_diffusers_available,
is_opencv_available,
is_vision_available,
)
if is_vision_available():
from PIL import Image
if is_diffusers_available():
from diffusers import DiffusionPipeline
if is_opencv_available():
import cv2
IMAGE_TRANSFORMATION_DESCRIPTION = (
"This is a tool that transforms an image according to a prompt. It takes two inputs: `image`, which should be "
"the image to transform, and `prompt`, which should be the prompt to use to change it. It returns the "
"modified image."
)
class ImageTransformationTool(Tool):
default_stable_diffusion_checkpoint = "timbrooks/instruct-pix2pix"
description = IMAGE_TRANSFORMATION_DESCRIPTION
inputs = ['image', 'text']
outputs = ['image']
def __init__(self, device=None, controlnet=None, stable_diffusion=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.")
if not is_vision_available():
raise ImportError("Pillow should be installed in order to use the StableDiffusionTool.")
if not is_opencv_available():
raise ImportError("opencv should be installed in order to use the StableDiffusionTool.")
super().__init__()
self.stable_diffusion = self.default_stable_diffusion_checkpoint
self.device = device
self.hub_kwargs = hub_kwargs
def setup(self):
if self.device is None:
self.device = get_default_device()
self.pipeline = DiffusionPipeline.from_pretrained(
self.stable_diffusion, controlnet=self.controlnet
)
self.pipeline.to(self.device)
if self.device.type == "cuda":
self.pipeline.to(torch_dtype=torch.float16)
self.is_initialized = True
def __call__(self, image, prompt, negative_prompt="low quality, bad quality, deformed, low resolution", added_prompt=" , highest quality, highly realistic, very high resolution"):
if not self.is_initialized:
self.setup()
return self.pipeline(
prompt + added_prompt,
image,
negative_prompt=negative_prompt,
).images[0]
|