search

gwang-kim / DiffusionCLIP

[CVPR 2022] Official PyTorch Implementation for DiffusionCLIP: Text-guided Image Manipulation Using Diffusion Models
Other
785 stars 113 forks source link

Text_dic for ImageNet manipulation #7

Closed EndyWon closed 2 years ago

EndyWon commented 2 years ago

Hi, Nice work! What text_dic you used for ImageNet manipulation? I didn't find it in text_dic.py. Besides, will the definition of text_dic affect the results? If so, how can I define the text_dic better? Can you share some experience? Thank you.

gwang-kim commented 2 years ago

Hi, @EndyWon. Thanks for your interest. Here are examples for text_dic for ImageNet manipulation.

SRC_TRG_TXT_DIC = {
    # Tennis ball
    'orange': (['tennis ball'],
                    ['orange']),
    # ImageNet Style Transfer
    'watercolor_art': (['a photo'],
                                ['a watercolor art']),
    }