From 5863676ccbada0887529a99dcb9d879149b199e5 Mon Sep 17 00:00:00 2001 From: Kohya S Date: Sun, 2 Jul 2023 16:49:18 +0900 Subject: [PATCH] update readme --- README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/README.md b/README.md index e2812e449..efa4d1ee2 100644 --- a/README.md +++ b/README.md @@ -30,6 +30,8 @@ Summary of the feature: - Both scripts has following additional options: - `--cache_text_encoder_outputs`: Cache the outputs of the text encoders. This option is useful to reduce the GPU memory usage. This option cannot be used with options for shuffling or dropping the captions. - `--no_half_vae`: Disable the half-precision (mixed-precision) VAE. VAE for SDXL seems to produce NaNs in some cases. This option is useful to avoid the NaNs. +- The image generation during training is now available. However, the VAE for SDXL seems to produce NaNs in some cases when using `fp16`. The images will be black. Currently, the NaNs cannot be avoided even with `--no_half_vae` option. It works with `bf16` or without mixed precision. +- `--weighted_captions` option is not supported yet. `requirements.txt` is updated to support SDXL training.