ComfyUI Node: Flux2TTRTrainer

Authored by ttulttul

Created

Updated

1 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

advanced/attention

Inputs

model MODEL
latents LATENT
conditioning CONDITIONING
steps INT
training BOOLEAN
training_preview_ttr BOOLEAN
checkpoint_path STRING
feature_dim INT
query_chunk_size INT
key_chunk_size INT
landmark_fraction FLOAT
landmark_min INT
landmark_max INT
text_tokens_guess INT
alpha_init FLOAT
training_query_token_cap INT
replay_buffer_size INT
replay_offload_cpu BOOLEAN
replay_max_mb INT
train_steps_per_call INT
readiness_threshold FLOAT
readiness_min_updates INT
enable_memory_reserve BOOLEAN
layer_start INT
layer_end INT
cfg_scale FLOAT
min_swap_layers INT
max_swap_layers INT
inference_mixed_precision BOOLEAN
controller_checkpoint_path STRING
training_config TTR_TRAINING_CONFIG

Outputs

MODEL

FLOAT

Extension: ComfyUI-Taylor-Attention

ComfyUI Taylor attention custom node

Authored by ttulttul

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