JingyeChen

Hi, thanks for your interest in TextDiffuser. Does this issue exist in few cases? Sometimes the image owner may replace the image, resulting in the mismatch of downloaded image.

Hi, according to the fifth page of this paper, it seems that the authors used the Panoptic version of COCO

TextDiffuser can be adapted to generate handwritten texts in two ways: (1) fine-tune it with text images containing handwritten texts; (2) use the current version and add "handwritten" in the...

For the second way, I suppose you can replace the default font "Arial.ttf" to a handwritten font and give it a try. The intermediate shape of mask/layout will affect the...

Thanks for your attention to our work！ The provided ```inference.py``` only serves for inference rather than training. Have you downloaded the pre-trained weight already? If the weights are successfully downloaded...

Thanks for your attention to our work. It is recommended to use an advanced GPU for training.

Thanks for your attention to our work! In fact there are several operations about replacing files. Did you finsh these operations? Besides, the version diffuser package is 0.17.0.dev0 in my...

I go through the repo https://github.com/huggingface/diffusers and found that "attn_num_head_channels" was removed recently. Alternatively, you can install diffusers with the following commands: ```bash git clone https://github.com/JingyeChen/diffusers cd diffusers pip install...

Thanks for your attention to TextDiffuser. Please note that the visualization for training did not involve the classifier-free guidance. And when the visualization produce legible text (although the background may...

It seems weird. Did you use ```accelerate config``` to specify the number of GPU to be used?