Sept 19 (Sat) 19:00 · Shibuya Hikarie

Book launch talk & signing — “画像・動画生成AI スタートガイド” (SB Creative)

14 seats, signed copy included (¥5,000). Japanese-language event.

ComfyUI, in your browser.

No install. No GPU of your own. Cloud ComfyUI from the moment you open it.

Start a free 5-minute trial

New here? You are in the right place — this page is where accounts start, in Japan and overseas. If you already use our shared ComfyUI, support lives at aicu.jp/comfy.

How it works

  1. Open it. A ComfyUI instance starts in your browser. Nothing to install.
  2. Pick a workflow. Verified combinations of models and custom nodes, ready to run.
  3. Generate. On an NVIDIA RTX 4000 Ada with 20 GB of VRAM.

What we run

Video
MiniMax H3 (Ref2VA / FL2VA), with and without the 4-step Turbo LoRA
Image
SDXL, FLUX, and the models the Japanese creative-AI scene actually uses
GPU
NVIDIA RTX 4000 Ada, 20 GB VRAM
Licensing
Checked per model. Only redistributable weights go into our public mirror

Why we publish our numbers

We are building ComfyLTS, a long-term-support ComfyUI package. Upstream moves every day, and what worked yesterday can break today. So we measure — timings, VRAM, what the model actually does with a prompt — and we publish it, including the runs that failed.

Recent notes

2026-09-05

Where ComfyPods is going — gathering the place where video happens at scmf.ai

2026-09-04

Is FLUX really non-commercial? We counted 312 car and train LoRAs

2026-09-03

"This green won't key" was wrong — measure green strength, not hue

All verification notes →

ComfyPods is in open beta. Video generation is planned for September 2026.

Newsletter for release notices

ComfyLTS — a star tells us how many people need this