ComfyUI Node: LoRA AutoTuner
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?
More nodes in LoRA Optimizer
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.