57 lines
1.9 KiB
INI
57 lines
1.9 KiB
INI
 
|
# lektor_ai_comfy — default settings
|
||
|
|
#
|
||
|
|
# These are the values used when a flag is not given on the command line.
|
||
|
|
# Precedence: command-line flag > this file > built-in defaults
|
||
|
|
#
|
||
|
|
# Delete a line (or the whole file) to fall back to the built-in default.
|
||
|
|
# A malformed value is reported and ignored, never fatal.
|
||
|
|
#
|
||
|
|
# Not configurable here, because they belong to a single run rather than to
|
||
|
|
# your setup: --start --end --seed --regen --rebuild --resume-from
|
||
|
|
# --embedded-subs --skip-tts
|
||
|
|
|
||
|
|
|
||
|
|
[tts]
|
||
|
|
# Voice reference. Either a name in voices/ (expects NAME.wav + NAME.txt),
|
||
|
|
# or a full path to a .wav file.
|
||
|
|
voice = gudowski_short
|
||
|
|
|
||
|
|
# Per-clip speed-up applied with atempo, before assembly.
|
||
|
|
# Raise it if speech regularly overruns its subtitle window; 1.0 = no change.
|
||
|
|
speed = 1.2
|
||
|
|
|
||
|
|
# Sampling temperature. 1.0 makes the model occasionally recite the reference
|
||
|
|
# transcript instead of the subtitle; 0.9 largely prevents that. Lower is more
|
||
|
|
# deterministic but flatter.
|
||
|
|
temperature = 0.7
|
||
|
|
|
||
|
|
# Ceiling on audio tokens per clip. Raise only if long clips are cut off
|
||
|
|
# mid-word.
|
||
|
|
max_tokens = 4096
|
||
|
|
|
||
|
|
# Trim this many ms from the start of every clip, to remove an inhale artifact.
|
||
|
|
# Try 80-150 if you hear one. Too high clips the first consonant.
|
||
|
|
strip_leading_ms = 0
|
||
|
|
|
||
|
|
# Fade out the last N ms of every clip to suppress tail pops. 0 disables.
|
||
|
|
trailing_fade_ms = 80
|
||
|
|
|
||
|
|
|
||
|
|
[mix]
|
||
|
|
# Levels inside the Polish lektor track only. Track 0 is always the untouched
|
||
|
|
# original, so mixing aggressively here costs you nothing.
|
||
|
|
# Dialogue-heavy sources: orig 0.5 / tts 2.0. Quiet sources: orig 1.0 / tts 1.4.
|
||
|
|
orig_volume = 0.70
|
||
|
|
tts_volume = 1.4
|
||
|
|
|
||
|
|
|
||
|
|
[paths]
|
||
|
|
# Where clips, assembled audio and the finished video are written.
|
||
|
|
# Relative paths are resolved from wherever you run the script.
|
||
|
|
output_dir = output
|
||
|
|
|
||
|
|
|
||
|
|
[comfy]
|
||
|
|
# Address of the ComfyUI backend running Higgs Audio V3.
|
||
|
|
comfy_url = http://127.0.0.1:8189
|