YOUR MODELS. YOUR COMPUTE

Private Cloud for AI Creators

Create with ComfyUI. Scale with Model APIs. Powered by dedicated cloud GPUs.
Launch ComfyUI →Rent a GPU →
🚀 Flux-3 Image Klein is now LIVE - TRY IT.

Run ComfyUI Models in One-click

Media workflows

ComfyUI
MiniMax H3Wan 2.2LTX 2.5
VideoImageWorkflows
From $0.58/hrOpen

Launch a GPU

Raw compute

H100 SXM
1x2x4x8x
80 GBvRAM
HopperTrainingFine-tune
From $2.88/hrLaunch

ComfyUI workflows in One-Click

Deploy pre-provisioned MiniMax H3, Wan 2.2 or LTX Video into ComfyUI on your own private GPU.

01

Choose a Workflow

Pick one from ready-to-run workflows catalog. Models, custom nodes, and dependencies come preconfigured.

MiniMax-H3Wan-2.2LTX-2.5
02

Select a GPU

Choose a cloud GPU with the VRAM and performance your workflow needs. Compare GPU options and pricing.

Flexible pricingDedicated compute
03

Launch ComfyUI

Get a private ComfyUI URL with your workflow ready to run. Models and custom nodes everything installed.

ComfyUI URLReady to generate

What people make here

ComfyUI in the Cloud.

It's the ComfyUI you already know, on a box only you can reach. Swap checkpoints, drop in LoRAs, install whatever node pack you found on GitHub last night, then queue a hundred seeds and walk away.

Ready-to-Run Workflows. Zero Setup.

Launch preconfigured workflows for MiniMax H3, Wan, LTX, and more. Models, custom nodes, and dependencies are already set up for you.

Create complex workflows.

Install any custom node, model, LoRA, or dependency. Customize your environment for complex or locked-down workflows.

Save your work. To pick up later.

Keep your models, custom nodes, workflows, and outputs in persistent storage. Stop your GPU and pick up right where you left off.

Camera movesCharacter consistencyPhysics that hold

Your workspace

MiniMax H3 on H100 SXM
comfy.hexgrid.cloud
Load Checkpointminimax_h3_video.safetensorsCLIP Text Encodeslow dolly through neon rain,35mm, shallow depth of fieldEmpty Latent Video1080p · 24fps · up to 10sKSamplersteps 30 · cfg 6.5sampler euler_aseed 84213907VAE Decodetiled · fp16Video Preview120 frames · 90s · next in queue
H100 SXM · 80 GB · queue 3

Weights, custom nodes and your output folder are already in place when the box comes up.

Weights preloaded
Install any custom node
Outputs persist
Nobody else on the box
PS: NSFW content creation is NOT allowed on the platform.
Deploy ComfyUI →

Trending models from Day-Zero

Deploy powerful generative models like H3, Wan, LTX, and FLUX etc. from day-zero. No waits.

MiniMax H3 - Text to VideoMiniMax
ComfyUIVideo
LTX 2.5 - Text to VideoLightricks
ComfyUIVideo
Wan 2.2 A14B - Text to VideoQwen
ComfyUIVideo
Flux2 - Text to ImageBlackforest Labs
ComfyUIImage
MiniMax H3 - Reference to VideoMiniMax
ComfyUIVideo
Krea2 - Text to ImageKrea
ComfyUIImage
Browse all models →

Launch any GPU in 60 seconds

Choose dedicated hardware by the hour, connect over SSH, and run your own stack with full root access.

Use cases

Your GPU. Any workload.

Use the machine directly with the tools and execution model you already have.

01Model training

Run your own training code, checkpoints, and distributed stack.

02Fine-tuning

Use LoRA, QLoRA, or full-parameter workflows without a managed runtime.

03Batch compute

Process datasets, embeddings, media, or scheduled CUDA jobs.

04Custom workloads

Bring containers, notebooks, renderers, or any CUDA-compatible stack.

Shell access

H100 SXM ready
root@gpu.hexgrid.cloud
$ ssh root@gpu.hexgrid.cloudConnected to Hexgrid GPU Cloudroot@hexgrid:~# nvidia-smi --query-gpu=name --format=csv,noheaderNVIDIA H100 SXMroot@hexgrid:~#

Direct SSH access with your keys, containers, and startup scripts.

Browse all GPUs →

Bring any framework, container, or training script. Hexgrid provides the machine; everything above it stays yours.

Certified Infrastructure

All our Datacenter partners are GDPR, ISO 27001, and SOC 2 Type II compliant.

Datacenters
Certified

SOC 2, ISO 27001, GDPR-ready infrastructure partners

Regions
US · EU · APAC

Deploy closer to users and data residency needs

GPU capacity
200+

B200, H200, H100, L40S-class servers across providers

Launch path
<1 min

From GPU selection to running pods