search

cientgu / InstructDiffusion

PyTorch implementation of InstructDiffusion, a unifying and generic framework for aligning computer vision tasks with human instructions.
Other
369 stars 20 forks source link

Is there a printing error in the formula of the paper? #7

Open houjie8888 opened 1 year ago

houjie8888 commented 1 year ago

image Equation 1 here seems to be the instruction condition ci? Could the author confirm this?

houjie8888 commented 1 year ago

image Also, would it be possible to provide information about the instruction templates, and how the instructions are set up for each type of task?

Gengzigang commented 1 year ago

Thanks for your interest. You can check this folder for instructions for each task: https://github.com/cientgu/InstructDiffusion/tree/main/dataset/prompt.

houjie8888 commented 1 year ago

@GengzigangHi~ It seems that there is no instruction for image editing here

Gengzigang commented 1 year ago

For editing, we use the instructions provided within the dataset itself. During the inference process, you are free to be creative.