PoseToImage¶

class agentlego.tools.PoseToImage(model='sd', device='cuda', toolmeta=None)[源代码]

A tool to generate image according to a human pose image.

参数:

model (str) – The pose controlnet model to use. You can choose from “sd” and “sdxl”. Defaults to “sd”.
device (str) – The device to load the model. Defaults to ‘cuda’.
toolmeta (None | dict | ToolMeta) – The additional info of the tool. Defaults to None.

默认工具信息¶

名称: PoseToImage
描述: This tool can generate an image from a human pose image and a text.
输入:
- image (ImageIO)
- keywords (str): A series of English keywords separated by comma.
输出:
- ImageIO

Examples¶

Download the demo resource

wget http://download.openmmlab.com/agentlego/pose_demo.jpg

Use the tool directly (without agent)

from agentlego.apis import load_tool
from PIL import Image

# load tool
tool = load_tool('PoseToImage', device='cuda')

# apply tool
image = tool('pose_demo.jpg', 'A pretty dancing girl.')
print(image)

With Lagent

from lagent import ReAct, GPTAPI, ActionExecutor
from agentlego.apis import load_tool

# load tools and build agent
# please set `OPENAI_API_KEY` in your environment variable.
tool = load_tool('PoseToImage', device='cuda').to_lagent()
agent = ReAct(GPTAPI(temperature=0.), action_executor=ActionExecutor([tool]))

# agent running with the tool.
img_path = 'pose_demo.jpg'
ret = agent.chat(f'According to the pose image `{img_path}`, draw a pretty dancing girl.')
for step in ret.inner_steps[1:]:
    print('------')
    print(step['content'])

Set up¶

Before using the tool, please confirm you have installed the related dependencies by the below commands.

pip install -U diffusers

Reference¶

This tool uses a Control Net model in default settings. See the following paper for details.

@misc{zhang2023adding,
      title={Adding Conditional Control to Text-to-Image Diffusion Models},
      author={Lvmin Zhang and Maneesh Agrawala},
      year={2023},
      eprint={2302.05543},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}