Hinode: ComfyUI in the cloud that keeps your nodes and models
Install ComfyUI in one click and render on a GPU with up to 96 GB of VRAM. Your custom nodes, models and LoRAs are still there next time. Open it in your own browser on a Mac or PC, and pay by the minute.
Machines from $1.75/hr · ComfyUI in one click ·
Pauses itself when idle
Sign up here. ComfyUI opens on your computer.
Opened with hinode open comfyui
localhost:8188 · ComfyUI on comfy-48
18 / 28 steps
Opened with hinode open comfyui
The problem
Rented GPUs forget everything
A pod is built to be thrown away. Your setup is not. The same evening, two ways.
sent 31.4 GB · 22 min
$ python generate.py --batch 24
done · 24 images · 214 s
Terminating instance and cleaning up...
A pod is gone when you stop it. Models, custom nodes and outputs go with it. Tomorrow you upload 31 GB again.
loras/
outputs/
Hinode pauses instead. The card stops billing, the disk keeps everything, and Resume brings back the same desktop.
From a Mac
Run ComfyUI on a Mac with a cloud GPU
ComfyUI runs on an NVIDIA card in the cloud, and your Mac shows it in a browser tab. The machine keeps your nodes and models between sessions.
Install once · on the workspace
~ — zsh$ hinode apps install comfyui
$ hinode env promote
snapshot v4 saved
Pick the card · for the model
comfy-48RunningL40S · 48 GB · $3.96/hr
pauses itself after 15 idle minOpen it · in your browser
Your browser · localhost:8188ComfyUI in a tab on your Mac
hinode open comfyuiforwards the machine's port to your computer and opens a tab. The port is never open to the internet.
Machines
Rent a GPU with 24, 48 or 96 GB of VRAM
Pick the VRAM and RAM the job needs. The machine starts with your apps on it and bills by the minute.
$ comfy run flux_video.json
loading wan2.2 · 31.2 GB
CUDA out of memory
job killed · 11 min lost
The job dies. The model needs more memory than the card has, and a bigger pod starts empty.
Attach a machine
GPU memory
System RAM
$ comfy run flux_video.json
loading wan2.2 · 31.2 GB
✓ loaded · 31.2 / 96 GB
rendering 81 frames ...
Start the card the job needs. From $1.75 to $12.58 an hour. Pause it or delete it when the render is done.
Apps
ComfyUI, vLLM and Ollama, installed in one click
Install from the workspace screen. What an app needs comes with it. Save a snapshot, and the next machine starts with all of it.
ComfyUI
Installing · 64%
PyTorch
~3 GB
JupyterLab
~50 MB
AI Toolkit
~8 GB
+ 6 more in the catalog
2 apps are not in a snapshot yet
- v4torch 2.5 and the new LoRA nodes
Shared folder
Write a checkpoint on one machine. Use it on the next.
Models, datasets and outputs live in one folder. The workspace and every machine read it at once, so there is nothing to copy and nothing lost when you delete a machine.
1train-48 finishes training and saves a LoRA
$ python train_lora.py --steps 2000
step 2000/2000 · loss 0.041
saved → ~/shared/loras/
portrait-v3.safetensors
2comfy-96 finds it in its LoRA list
lora_name
320 MB/s
reading one big model over four streams
653 MB/s
reading it again, from the machine’s cache
$0.11
per GB a month, only for what is in it
Local home
Python environments and git stay laptop-fast
Pricing
Cloud GPU pricing, by the minute
No plan and nothing up front. One bill at the end of the month, itemised by what ran.
WORKSPACE
$0.297/hr
A desktop on 1/8 of an NVIDIA L4, your files and your apps. Pauses itself when you leave.
- Disk
- $0.15 / GB-month written
- Shared folder
- $0.11 / GB-month
- Traffic out
- $0.10 / GB
MACHINE · 24 GB
from$1.75/hr
NVIDIA L4
Image generation, light fine-tuning, most ComfyUI work
MACHINE · 48 GB
Popularfrom$3.30/hr
NVIDIA L40S
Video models, bigger LoRAs, 30B-class inference
MACHINE · 96 GB
from$8.05/hr
RTX PRO 6000 Blackwell
70B-class models, long video, what fits nowhere else
What a month costs
≈ $112/month
87 h of workspace $25.84 + 26 h on 48x32 $85.80. Disks and the shared folder are extra.
These are the rates your invoice uses. The US and Europe cost the same.
Hinode vs RunPod
The same cards, with a computer around them
A 48 GB Hinode machine is the L40S RunPod rents, with a desktop, your apps and your files already on it.
| Hinode | RunPod | Vast | Lambda | HF Pro | |
|---|---|---|---|---|---|
| GPU | L40S · 48 GB | L40S · 48 GB | RTX A6000 · 48 GB | A100 · 40 GB | ZeroGPU · shared |
| GPU access | Dedicated | Dedicated | Dedicated | Dedicated | Quota + queue |
| Interface | Desktop, SSH, VS Code, AI assistants | SSH / Jupyter | SSH / Jupyter | SSH / Jupyter | Spaces (web) |
| When you stop | Paused, files and apps kept | Lost on stop | Tied to one host | Lost on terminate | Ephemeral |
| Devices | Mac, Windows, Linux apps + Chrome | Browser | Browser | Browser | Browser |
Swipe for Vast, Lambda and HF Pro →
FAQ
ComfyUI on Hinode: questions
Yes. It is your machine: install nodes with ComfyUI-Manager or git clone, as on your own computer. Install them on the workspace and save a snapshot, and every new machine starts with them.
Yes. ComfyUI runs on an NVIDIA GPU in the cloud, not on your Mac. hinode open comfyui opens it in your own browser, and the Hinode app for Mac can also show the machine's whole desktop.
24 GB runs image generation and most ComfyUI workflows. 48 GB fits video models and bigger LoRAs. 96 GB is for long video and models that fit nowhere else. You pick the card per machine, so each workflow can get its own.
In ~/shared/ComfyUI/models, in the shared folder every machine in the workspace reads. Download a model once and every machine you start has it. It costs $0.11 per GB-month for what is stored.
Yes. The AI Toolkit installs from the same catalog. Train on one machine, save the LoRA to the shared folder, and ComfyUI on the next machine finds it in its list.
A paused machine resumes in a couple of minutes, and ComfyUI starts on it after that. Your nodes and models are already there, so nothing downloads again.
No. Its port is never open to the internet. hinode open forwards it over SSH to your own computer only.
A machine bills by the minute while it runs: from $1.75 an hour for 24 GB, $3.30 for 48 GB and $8.05 for 96 GB. It pauses itself after 15 idle minutes. There is no plan and nothing to cancel.
Install ComfyUI once. Open it from any computer.
Create a workspace, install ComfyUI in one click, and start a GPU when you render.
