| from PIL import Image | |
| import torch | |
| from transformers.agents.tools import Tool | |
| from transformers.utils import ( | |
| is_accelerate_available, | |
| is_vision_available, | |
| ) | |
| from diffusers import DiffusionPipeline | |
| if is_accelerate_available(): | |
| from accelerate import PartialState | |
| IMAGE_TRANSFORMATION_DESCRIPTION = ( | |
| "This is a tool that transforms an image according to a prompt and returns the " | |
| "modified image." | |
| ) | |
| class ImageTransformationTool(Tool): | |
| name = "image_transformation" | |
| default_stable_diffusion_checkpoint = "timbrooks/instruct-pix2pix" | |
| description = IMAGE_TRANSFORMATION_DESCRIPTION | |
| inputs = { | |
| 'image': {"type": Image.Image, "description": "the image to transform"}, | |
| 'prompt': {"type": str, "description": "the prompt to use to change the image"} | |
| } | |
| output_type = Image.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_vision_available(): | |
| raise ImportError("Pillow 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 = PartialState().default_device | |
| self.pipeline = DiffusionPipeline.from_pretrained(self.stable_diffusion) | |
| 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): | |
| if not self.is_initialized: | |
| self.setup() | |
| negative_prompt = "low quality, bad quality, deformed, low resolution" | |
| added_prompt = " , highest quality, highly realistic, very high resolution" | |
| return self.pipeline( | |
| prompt + added_prompt, | |
| image, | |
| negative_prompt=negative_prompt, | |
| num_inference_steps=50, | |
| ).images[0] |