logo
RunComfy
  • ComfyUI
  • Trainer
  • Models
  • MCPNew
  • Pricing
  • Seedance 2.5Hot
  • Seedream 5.5New

Workflows by Model

HotMiniMax H3Video with audio from text, images or referencesHotQwen Image 2.1Create images and edit photos with referencesWanVideo from text or images, motion transferFLUXImage generation, editing and character variationsLTXVideo with synced audio from text or imagesQwen Image EditPhoto editing with text and image referencesKrea 2Image creation, style transfer and reference editsZ-ImageFast portraits and concepts from text

Popular & New Workflows

NewMiniMax H3 Character Swap V1.5Swap video characters, keep the original audioNewP-H3-Image Reference EditEdit a photo guided by a reference imageHotMiniMax H3 Image-to-VideoOne image to cinematic video with synced audioHotLTX 2.5 Image-to-VideoOne frame to sharp video with synced audioHotMiniMax H3 Character Swap (SAM3)Swap video characters while following the motionQwen Image 2.1 Multi-Image EditingPrecise scenes from up to 10 reference imagesFLUX Klein Face SwapNatural, lifelike face swapsSeedVR2 Video UpscalerSharp, smooth video upscaling
View More Workflows

Train a Model

NewMOSS-Image BaseImage generation, newly supportedNewFLUX.3 KleinImage generation, newly supportedHotKrea 2The most-trained image modelHotKrea 2 TurboFew-step image generationHotQwen Image 2.1Image generation and editingZ-Image TurboFast portraits and concept imagesMiniMax H3Video with synchronized audio

Train & Deploy

Getting StartedYour first training job with Ostris AI ToolkitDatasetsUpload and manage training datasetsInferenceRun your trained models in a playground or via APIDeploymentsServe your trained models as dedicated endpoints
Train More Models

Image Models

NewGPT Image 2.65% OFF · Detailed text to image, GIF and SVG, up to 4KNewSeedream 5.510% OFF · Text to image up to 2K, with transparent PNGsHotSeedream 5.0 Pro41% OFF · Reference edits with multilingual textHotSeedream 4.520% OFF · Photoreal edits with brand consistencyHotWan 2.6 ImageInstruction-based image editingFLUX.2Precise, photorealistic image editsNano Banana Pro77% OFF · Precise 2K to 4K visuals from sketchesQwen Image EditLoRA-based, structure-aware image editing

Video Models

NewKling 4.010% OFF · Animate a still into a 3 to 30s clipHotWan 3.0 Prime13% OFF · Fast clips from reference videosHotSeedance 2.536% OFF · Longer, more consistent cinematic videoHotWan 3.0Clips from image, video and audio referencesHotMiniMax H3Animate a first frame into a 5 to 15s clipWan 2.510% OFF · Fluid motion with native audioFLUX 3 MaxClips from text, a still, or keyframesWan 2.6 FlashLifelike scenes from stills with dialogue sync
View More Models

API

Serverless (ComfyUI)Deploy ComfyUI workflows as serverless endpoints.Serverless (LoRA)Deploy LoRAs as serverless endpoints.Model APIRun hosted models on-demand with no deployment.Trainer APITrain, manage, and retrieve LoRAs via API.CLIRun RunComfy models from your terminal.
Follow us
  • LinkedIn
  • Facebook
  • Instagram
  • Twitter
Support
  • Discord
  • Email
  • System Status
  • Affiliate
Resources
  • Free ComfyUI Online
  • Auto Setup ComfyUI Workflow
  • ComfyUI Guides
  • RunComfy API
  • RunComfy MCP
  • RunComfy Skills
  • ComfyUI Tutorials
  • ComfyUI Nodes
  • Learn More
Legal
  • Terms of Service
  • Privacy Policy
  • Cookie Policy
RunComfy
Copyright 2026 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.

Trusted by 1M+ creators & devs

Fast, reliable, and
cost-efficient

One balance. Pay as you go. Better rates with Pro.

Pay as You Go

No subscription required

Standard rates apply to all GPU usage

Models & API

  • Access top open-source and commercial models in one place
  • Simple per-generation pricing, no extra subscriptions needed

ComfyUI & API

  • Full native ComfyUI, upload custom models and install any nodes
  • Dedicated private GPU machines with 16 to 141 GB VRAM
  • Save up to 10 workflow environments to share and reuse
  • One-click Serverless API from any workflow
  • 10 GB storage included (inactive assets removed after 90 days)

Trainer & API

  • Optimized GPU rates for long-running training jobs
  • 80 GB & 141 GB VRAM GPUs for large models and faster job
  • GPUs auto-release when training completes, no idle charges
  • Persistent checkpoints let you resume training anytime
Yearly-33%
Monthly

Pro

$29.99$19.99/mo

Billed $239.90/year (4 months free)

20%+ off all GPU rates, with 20 CPU hrs included ($10 value)

Everything in Pay as You Go, plus:

Pro Benefits

  • 20%+ discount on all GPU rates (ComfyUI & Trainer)
  • 20 CPU hours/month included for uploads & setup ($10 value at $0.5/hr)
  • $10 monthly credit for Models, ComfyUI, Trainer & APIs
  • Priority Discord & email support

ComfyUI & API

  • 20 free CPU hours/month for uploads & setup ($10 value)
  • Unlimited saved workflow environments
  • 200 GB storage with permanent retention

Trainer & API

  • 20%+ discount on all Trainer GPU hours

Products

ComfyUI & API Pricing

Billed by the second for GPU time.Rates below are shown per hour.How machine charges work ↗

H200 pricing was updated effective Jun 1, 2026 (14:00 UTC).

GPU MachinePay as You GoPro
Small: CPU
For uploads & workflow setup (20 hr/mo)
$0.5/hr
Free
Medium: T4, A4000
16 GB VRAM · 16 GB RAM · 8 vCPUs
$0.99/hr$0.79/hr
Large: A10G, A5000
24 GB VRAM · 32 GB RAM · 8 vCPUs
$1.75/hr$1.39/hr
X-Large: A6000
48 GB VRAM · 48 GB RAM · 28 vCPUs
$2.50/hr$1.99/hr
X-Large Plus: L40S, L40
48 GB VRAM · 64 GB RAM · 28 vCPUs (API only)
$2.99/hr$2.15/hr
2X-Large: A100
80 GB VRAM · 96 GB RAM · 28 vCPUs
$4.99/hr$3.99/hr
2X-Large Plus: H100
80 GB VRAM · 180 GB RAM · 28 vCPUs
$7.49/hr$5.99/hr
3X-Large: H200
141 GB VRAM · 240 GB RAM · 24 vCPUs
$9.59/hr$7.66/hr
100% private workspace
Native ComfyUI (synced with official releases)
Upload custom models & install any nodes
Saved workflow environmentsUp to 10Unlimited
Serverless API deployment
200+ ready-to-run workflows
Storage10 GB200 GB
Persistent storageCleared after 90 days
SupportDiscord & EmailPriority support

Trainer (AI-Toolkit) & API Pricing

Billed by the second for GPU time.Rates below are shown per hour.Training GPUs auto-release when jobs finish, so there are no idle charges.

H200 training pricing was updated effective Oct 20, 2026 (14:00 UTC).

Special rate for training runsPay as You GoPro
H100 (Training)$4.49/hr$3.59/hr
H200 (Training)$6.89/hr$5.49/hr
8×H100 (Training)

Models & API Pricing

Pay per generation.For example, per image or per second of generated video.

Why Creators Choose RunComfy

Frequently Asked Questions

How does RunComfy billing work?

RunComfy uses one shared balance across Models (including Model APIs), ComfyUI (including API), and Trainer (including Trainer APIs).

  1. Models & Model APIs: pay per generation (for example, per image or per second of generated video).
  2. ComfyUI & API: GPU compute rates are shown per hour, but usage is billed by the second on the selected machine. See how ComfyUI machine charges are calculated.
  3. Trainer & Trainer APIs: GPU training rates are shown per hour, but usage is billed by the second. GPUs auto-release when training completes, so there are no idle charges.

Pro is optional and gives discounted GPU rates plus perks like extra storage and monthly credits.

If I add money, can I use it in ComfyUI, Models, and Trainer?

Yes. When you add funds, they go into one shared balance that can be spent on Models (including Model APIs), ComfyUI (including API), and Trainer (including Trainer APIs), no transfers needed. You can view your balance on your profile page.
$29.99/hr
$23.99/hr
Auto-release GPUs, no idle charges
Persistent checkpoints for resumable training
For deployed inference (Dedicated endpoints)Pay as You GoPro
A6000 (Inference)$2.50/hr$1.99/hr
L40S/L40 (Inference)$2.99/hr$2.15/hr
A100 (Inference)$4.99/hr$3.99/hr
H100 (Inference)$7.49/hr$5.99/hr
H200 (Inference)$9.59/hr$7.66/hr
SupportDiscord & EmailPriority support
Video Model
Starting at
Output per $1
SyncNew
$0.149~6.7 sec
Seedance 2.5
$0.76433% OFF~1.3 sec
Wan 3.0 Prime
$0.0624Up to 13% OFF~16 sec
Kling V4
$0.145Up to 9% OFF~6.8 sec
HeyGen Video
$0.009$0.03Up to 70% OFF~111 sec
Avatar V
$0.07~14 sec
Image Model
Starting at
Output per $1
Seedream 5.5New
$0.0179$0.0210% OFF~55 images
Seedream 5.0 Pro
$0.04Up to 41% OFF

Starting prices are for the lowest resolution. See each model page for full pricing.

View all models

How do I add funds?

Go to your profile page and click Add Funds. Funds are available immediately after a successful payment and can be used for Models (including Model APIs), ComfyUI (including API), and Trainer (including Trainer APIs).

Do my funds expire?

Yes. Purchased funds expire 365 days after the purchase date.

Do I still need a balance if I subscribe to Pro?

Yes. Pro unlocks discounted GPU rates and perks, but usage is still pay‑as‑you‑go and deducted from your balance. Your subscription also includes $10 in credits each month, automatically added to your balance, and usable for Models (including Model APIs), ComfyUI (including API), and Trainer (including Trainer APIs).

Does the Pro discount apply automatically?

Yes. Once your Pro subscription is active, eligible GPU usage is billed automatically at the discounted rate (ComfyUI & API and Trainer & Trainer API).

Can I cancel my Pro subscription?

Yes. You can start or cancel your Pro subscription at any time from your profile page. Cancellation stops the next renewal, your current period remains active until it ends.

Can I use ComfyUI without a subscription?

Absolutely. ComfyUI works entirely on pay‑as‑you‑go; Pro is optional for discounted GPU rates and extra perks.

Is my ComfyUI environment private and isolated?

Yes. Your ComfyUI sessions and API deployments run in isolated instances dedicated to your account, and your data, models, and outputs remain private.

Can I upload custom models or LoRAs and install custom nodes in my ComfyUI environment?

Yes. Upload your own models/LoRAs and install any custom nodes. Assets are stored privately (pay‑as‑you‑go includes 10 GB storage; Pro includes 200 GB with permanent retention).

Can I deploy any ComfyUI workflow as an API?

Yes. Any ComfyUI workflow can be deployed as an API for integration into your apps and scripts. Usage is billed from the same balance based on GPU compute time (Pro discounts apply).

Why should I use RunComfy for my AI class/workshop/tutorials?

RunComfy is great for classes, workshops, and tutorials because students can start ComfyUI instantly in the cloud (no local installs) and you get a consistent environment for everyone.

It also supports the full stack: use Models for instant image/video generation demos, and Trainer for LoRA / fine‑tuning on dedicated GPUs.

Billing is flexible: one shared balance, pay as you go, with optional Pro discounts on GPU usage. Learn more here.

How do I get an invoice?

You can get invoices for your balance top‑ups and subscriptions by following this guide:

How do I get an invoice for my RunComfy payments?

More questions?

Check out: Detailed Pricing Plans Q&A

~25 images
Seedream 4.5
$0.032$0.0420% OFF~31 images
GPT Image 2.6
$0.064$0.0685% OFF~15 images
HeyGen Image
$0.25~4 images
Nano Banana 2.1
$0.039~25 images