andyjiang

你好，这个地方 https://github.com/wangyuxin87/VisionLAN/blob/main/train_LF_2.py#L74-L76 通过id来选择不同参数，我通过print打印，第一组参数是空，也就是没有匹配到id_total的参数，是哪里有问题吗？

**Is your feature request related to a problem? Please describe.** Hi, when I trained sdv1.5 model with fp16 mode by using the `examples/text_to_image/train_text_to_image.py` file, I found there is a mismatch...

I use the two person Pulid-Flux workflow, the input is two person face, I give the detailed prompt, but the generated images are always unsatisfactory, both the person is in...