Wenbo Li

quality of text diffuser-2

5

**Describe** Model I am using (Text diffuser-2): I am running inference on text diffuser-2 , the inference code of mine: `CUDA_VISIBLE_DEVICES=6 python inference_textdiffuser2_t2i_full.py \ --pretrained_model_name_or_path="/path/to/stable-diffusion-v1-5" \ --mixed_precision="fp16" \ --enable_xformers_memory_efficient_attention \...

train text diffuser on customized dataset

2

**Describe** Model I am using textdiffuser: Hi, I am training textdiffuser using my customized dataset, and I wonder how to build segmentation mask information. It seems that there is no...

need evaluate code for text diffuser-2

1

**Describe** Model I am using (UniLM, MiniLM, LayoutLM ...): I think we need evaluate code like text diffuser-1 to reproduce result on MARIOEval benchmark or other datasets

question about balanced l1 loss

1

I have a few qustions about this loss: 1. threshold is no use, why; 2. if two attention maps are the same, loss should be -1, but shouldn't loss be...