ComfyUI Node: GGUF Accelerator (patch_on_device)
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/Optimize
Inputs
model MODEL
mode
- auto_oom_safe
- manual
patch_on_device BOOLEAN
move_patches_now BOOLEAN
min_free_vram_mb INT
oom_fallback BOOLEAN
move_policy
- all_or_nothing
- partial_small_first
- partial_large_first
leave_free_vram_mb INT
Outputs
MODEL
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?
More nodes in IAMCCS-nodes
- Apply LoRA Hooks to Conditioning
- Apply Scheduled WAN LoRA From Conditioning
- IAMCCS AudioBoard Arranger
- IAMCCS AudioBoard Mixer
- Audio Extender (segment + overlap)
- Audio Extension Math (timeline sync)
- IAMCCS Audio Normalize For LTX
- IAMCCS Audio Phase Lazy Gate
- Audio Segment Auto Planner (audio -> segmenti)
- Audio Timeline Assembler (full track)
- Audio Timeline Gate (continue/stop)
- AU+IMG2VID Audio Timeline (legacy alias)
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.