ComfyUI Node: ๐ŸŽ›๏ธ MOSS Training Config

Authored by diodiogod

Created

Updated

1089 stars

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Category

TTS Audio Suite/๐ŸŽ“ Training

Inputs

training_mode
  • LoRA Adapter (Delay 8B)
epochs INT
max_train_steps INT
batch_size INT
gradient_accumulation_steps INT
learning_rate FLOAT
weight_decay FLOAT
warmup_steps INT
max_grad_norm FLOAT
num_workers INT
mixed_precision
  • bf16
  • fp16
  • no
gradient_checkpointing BOOLEAN
base_quantization
  • none
  • 4bit_nf4
bnb_4bit_compute_dtype
  • auto
  • bf16
  • fp16
  • fp32
bnb_4bit_use_double_quant BOOLEAN
save_steps INT
eval_steps INT
log_steps INT
lora_r INT
lora_alpha INT
lora_dropout FLOAT
trainable_lora_modules
  • mlp
  • mlp_plus_o
  • all

Outputs

TRAINING_CONFIG

STRING

Extension: TTS Audio Suite

TTS Audio Suite - Universal multi-engine TTS extension for ComfyUI with unified architecture supporting ChatterBox, F5-TTS, and future engines like RVC. Features modular engine adapters, character voice management, comprehensive SRT subtitle support, and advanced audio processing capabilities.

Authored by diodiogod

Looking for a different node?

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Learn more