CONFIG / dataset.toml
EQX55's picture
Upload 2 files
8bd71e7 verified
# Resolutions to train on, given as the side length of a square image. You can have multiple sizes here.
resolutions = [1024]
# You can give resolutions as (width, height) pairs also. This doesn't do anything different, it's just
# another way of specifying the area (i.e. total number of pixels) you want to train on.
# resolutions = [[1280, 720]]
# Enable aspect ratio bucketing. For the different AR buckets, the final size will be such that
# the areas match the resolutions you configured above.
enable_ar_bucket = true
# The aspect ratio and frame bucket settings may be specified for each [[directory]] entry as well.
# Directory-level settings will override top-level settings.
# Min and max aspect ratios, given as width/height ratio.
min_ar = 0.5
max_ar = 2.0
# Total number of aspect ratio buckets, evenly spaced (in log space) between min_ar and max_ar.
num_ar_buckets = 7
# Can manually specify ar_buckets instead of using the range-style config above.
# Each entry can be width/height ratio, or (width, height) pair. But you can't mix them, because of TOML.
# ar_buckets = [[512, 512], [448, 576]]
# ar_buckets = [1.0, 1.5]
# For video training, you need to configure frame buckets (similar to aspect ratio buckets). There will always
# be a frame bucket of 1 for images. Videos will be assigned to the first frame bucket that the video is greater than or equal to in length.
# But videos are never assigned to the image frame bucket (1); if the video is very short it would just be dropped.
frame_buckets = [1, 33, 65]
[[directory]]
# Path to directory of images/videos, and corresponding caption files. The caption files should match the media file name, but with a .txt extension.
# A missing caption file will log a warning, but then just train using an empty caption.
path = '/diffusion-pipe/input'
# The dataset will act like it is duplicated this many times.
num_repeats = 10
# Example of overriding some settings, and using ar_buckets to directly specify ARs.
# ar_buckets = [[448, 576]]
# resolutions = [[448, 576]]
# frame_buckets = [1]
# You can list multiple directories.
# [[directory]]
# path = '/home/anon/data/images/something_else'
# num_repeats = 5