ComfyUI Node: LoRA AutoTuner

Authored by ethanfel

Created

Updated

135 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

LoRA Optimizer

Inputs

model MODEL
lora_stack LORA_STACK
output_strength FLOAT
clip CLIP
clip_strength_multiplier FLOAT
top_n INT
normalize_keys
  • disabled
  • enabled
scoring_svd
  • disabled
  • merge_quality
  • lora_rank
  • full
scoring_device
  • cpu
  • gpu
architecture_preset
  • auto
  • sd_unet
  • dit
  • acestep_dit
  • llm
auto_strength_floor FLOAT
evaluator AUTOTUNER_EVALUATOR
community_cache
  • disabled
  • upload_only
  • upload_and_download
cache_patches
  • enabled
  • disabled
diff_cache_mode
  • disabled
  • auto
  • ram
  • disk
diff_cache_ram_pct FLOAT
vram_budget FLOAT
scoring_speed
  • full
  • fast
  • turbo
  • turbo+
scoring_formula
  • v2
  • v1
output_mode
  • merge
  • tuning_only
decision_smoothing FLOAT
smooth_slerp_gate BOOLEAN
memory_mode
  • disabled
  • auto
  • auto_ignore_strength
  • read_only
  • clear_and_run
selection INT
record_dataset
  • disabled
  • enabled

Outputs

MODEL

CLIP

STRING

STRING

TUNER_DATA

LORA_DATA

Extension: LoRA Optimizer

Auto-optimizer node for combining multiple LoRAs via diff-based merging with TIES conflict resolution

Authored by ethanfel

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