Comfyui Launch Flags

What it does

When your agent uses it

• A graph OOMs (especially long video like LTX 2 / WAN)
• The GPU spills into shared VRAM and slows to a crawl
• Switching between models eats all RAM
• Z-Image produces black/garbled output under Sage

Example prompts

• “/comfyui-launch-flags”

Requirements

• Python 3

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

1. 1Z-Image + Sage = broken. Z-Image (Turbo/Base) does not sample
2. 2Sage black output on other models. If a model outputs black only with

What it can do on your machine

Read from SKILL.md and the folder at commit 6ad6fc0. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • python
  • uv

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • github.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Comfyui Launch Flags loads about 3.1k tokens when it runs. Until then it costs about 223 tokens; SKILL.md has 1,148 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~223

When it runs · the whole SKILL.md, loaded when a task matches

~3.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from artokun/comfyui-mcp at commit 6ad6fc0, republished under its MIT licence (© artokun). 1,148 words, ~3,106 tokens.

name

comfyui-launch-flags

description

Pick the right ComfyUI startup flags for VRAM, attention, caching, and speed. The full decision matrix for OOM (--novram / --cache-none / --disable-smart-memory), shared-VRAM creep on Windows (--reserve-vram N), model-switching with big text encoders (--cache-none), high-VRAM throughput (--gpu-only / --highvram), and attention-backend selection (--use-sage-attention for speed, --use-pytorch-cross-attention as the highest-quality / Z-Image-safe fallback). Also the acceleration-stack + Blackwell/RTX 5000 (sm_120) notes. Use when a graph OOMs (especially long video like LTX 2 / WAN), when the GPU spills into shared VRAM and slows to a crawl, when switching between models eats all RAM, when Z-Image produces black/garbled output under Sage, or when deciding which attention backend to launch with. Flag names verified against upstream comfy/cli_args.py; see Sources.

globs

**/*.json, **/packs/**

Symptom                                             ▶ Flag(s) to try
─────────────────────────────────────────────────────────────────────────────
CUDA out of memory, long video (LTX 2 / WAN)        ▶ --novram  (+ --cache-none)
OOM, still want models resident when they fit       ▶ --reserve-vram N  then --disable-smart-memory
GPU slows to a crawl, spills into "shared GPU        ▶ --reserve-vram 2..4
  memory" (Windows WDDM) mid-run
RAM blows up switching between models, or a huge     ▶ --cache-none
  text encoder (FLUX 2 / Mistral) won't unload
Plenty of VRAM (48GB+), want max throughput         ▶ --gpu-only  or  --highvram
Want faster sampling on NVIDIA                       ▶ --use-ck-attention if kitchen INT8 is available (skip the sage wheel); else --use-sage-attention
Z-Image produces BLACK / wrong output               ▶ --use-pytorch-cross-attention (NOT sage)
Sage gives black output on some models              ▶ --use-pytorch-cross-attention (or fix dtype)
ROCm, kitchen present, triton ≥ 3.7                  ▶ --enable-triton-backend

Long video OOM (LTX 2 / WAN, 24GB):   --novram --cache-none
                                      (add --disable-smart-memory if it stalls)
Windows shared-VRAM creep:            --reserve-vram 3
FLUX 2 / huge text-encoder swaps:     --cache-none
High-VRAM throughput (48GB+):         --gpu-only        (or --highvram)
Fast NVIDIA sampling (most models):   --use-ck-attention   (if kitchen INT8 is available)
                                      --use-sage-attention (otherwise; needs the wheel)
Z-Image (any):                        --use-pytorch-cross-attention
ROCm + kitchen + triton ≥ 3.7:        --enable-triton-backend

© artokun, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugin/skills/comfyui-launch-flags of artokun/comfyui-mcp.

Open the folder on GitHubat commit 6ad6fc0