ComfyUI Node: HW Supporter (auto VRAM/attention/torch knobs)

Authored by IAMCCS

Created

Updated

109 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

IAMCCS/HW

Inputs

model MODEL
profile
  • auto
  • 12GB_VRAM_32GB_RAM
  • low_vram
  • balanced
  • max_speed
apply_reserved_vram BOOLEAN
reserved_vram_mode
  • manual
  • auto_used_plus
reserved_vram_gb FLOAT
sage_attention
  • disabled
  • auto
  • sageattn_qk_int8_pv_fp16_cuda
  • sageattn_qk_int8_pv_fp16_triton
  • sageattn_qk_int8_pv_fp8_cuda
  • sageattn_qk_int8_pv_fp8_cuda++
  • sageattn3
  • sageattn3_per_block_mean
allow_sageattention_torch_compile BOOLEAN
torch_compile_mode
  • off
  • auto
  • default
  • reduce-overhead
  • max-autotune
  • max-autotune-no-cudagraphs
fp16_accumulation
  • auto
  • on
  • off
tf32
  • auto
  • on
  • off
clean_gpu_before BOOLEAN
console_log BOOLEAN
include_hardware_report BOOLEAN
clip CLIP
vae VAE

Outputs

MODEL

CLIP

VAE

STRING

Extension: IAMCCS-nodes

Custom nodes by IAMCCS, including a critical fix for LoRA loading in native WANAnimate workflows, especially useful for advanced models like FLUX and WAN 2.1. This bypasses the need for the WanVideoWrapper for LoRA functionality.

Authored by IAMCCS

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