ComfyUI Blog

ComfyUI Blog

Share this post

ComfyUI Blog
ComfyUI Blog
ComfyUI Now Supports GPT-Image-1 via API Nodes (Beta)
Copy link
Facebook
Email
Notes
More

ComfyUI Now Supports GPT-Image-1 via API Nodes (Beta)

Jo Zhang's avatar
Jo Zhang
Apr 23, 2025
24

Share this post

ComfyUI Blog
ComfyUI Blog
ComfyUI Now Supports GPT-Image-1 via API Nodes (Beta)
Copy link
Facebook
Email
Notes
More
12
1
Share

AGI (All Ghibli Images) is coming to a ComfyUI instance near you!

OpenAI just announced GPT-Image-1 API (the same model that powered the ChatGPT 4o image model) 10 minutes ago. We’re excited to share that ComfyUI now supports the latest OpenAI image generation model via our native API Nodes (beta) — allowing you to access state-of-the-art capabilities directly inside your node graph without complicated API keys.

This feature is now in beta, and we’re opening it up for early experimentation.

GPT-Image-1 Highlights:

OpenAI’s multimodal flagship that is behind GPT-4o:

  • Supports 3 image dimensions: Square (1024×1024), Portrait (1024×1536), Landscape (1536×1024), and Auto

  • Three quality levels: low, medium, high

  • Supports transparent backgrounds and mask image editing in ComfyUI

To try out this integration, you’ll need to register/log in to your Comfy Org account. This is required because the model runs through OpenAI’s paid API service. The API integration is optional and designed for access to external models.

ComfyUI will always remain fully open source and free for local users.

Get Started

  1. Update ComfyUI or Desktop to the latest.

  2. Log In: To use the API nodes, you need to be logged in. Go to Settings → User → Login. Don’t have an account? Hit Create New Account.

  3. Top Up Credits: Settings → Credits → Buy Credits. We use a prepaid model and credits will only be consumed for each run. No surprise charges.

  4. Add the “OpenAI GPT Image 1“ node to your canvas and run!

  5. Image input and mask editing are also enabled by adding a “Load Image“ node.

Workflow Showcases

One of the most exciting use cases now is combining powerful external models like gpt-image-1 with existing local models and local workflows.

In this example workflow, we used OpenAI’s image generation API to create a restyled image from an image input and text prompt, then passed it through a local ComfyUI Wan2.1 image-to-video or Wan2.1 VACE control video generation workflow.

GPT Image 1 + Wan2.1 I2V Workflow

Workflow by Purz

GPT Image 1 + Wan2.1 VACE Control Workflow

Workflow by Milan Kastenmüller

Token Cost & Quality Options

$5/1M text tokens for input, $10/1M image tokens for input, and $40/1M image tokens for output, same as OpenAI’s listing price.

Token Cost by Resolution and Quality:

More Models Coming Soon

This is just the beginning. We’re actively expanding support for a broader range of external models — so stay tuned for upcoming integrations that will further unlock the potential of ComfyUI as a universal generative AI interface.

As always, we’d love to hear your thoughts and use cases — your feedback helps shape the future of ComfyUI!

Thanks for reading ComfyUI Blog! Subscribe for free to receive new posts and support my work.

Stephane Chung's avatar
Gaurav Seth's avatar
Ida Silfverskiold's avatar
Jo Zhang's avatar
Christian Byrne's avatar
24 Likes∙
1 Restack
24

Share this post

ComfyUI Blog
ComfyUI Blog
ComfyUI Now Supports GPT-Image-1 via API Nodes (Beta)
Copy link
Facebook
Email
Notes
More
12
1
Share

Discussion about this post

User's avatar
Bradley Munn's avatar
Bradley Munn
Apr 23

Can you connect your own OpenAI API key, or do you have to use Comfy credits?

Expand full comment
Like (4)
Reply
Share
2 replies by Robin and others
zoombb's avatar
zoombb
Apr 24

is the moderation parameter available with comfy?

Expand full comment
Like (2)
Reply
Share
10 more comments...
Wan2.1 Video Model Native Support in ComfyUI!
14B and 1.3B video generation workflows available now! Accessible for consumer GPUs!
Feb 26 â€¢ 
Jo Zhang
46

Share this post

ComfyUI Blog
ComfyUI Blog
Wan2.1 Video Model Native Support in ComfyUI!
Copy link
Facebook
Email
Notes
More
37
Introducting ComfyUI Native API Nodes (and New Brand!)
One platform, 11 models, 65 nodes, all at once!
May 6 â€¢ 
Robin
39

Share this post

ComfyUI Blog
ComfyUI Blog
Introducting ComfyUI Native API Nodes (and New Brand!)
Copy link
Facebook
Email
Notes
More
23
Running Hunyuan with 8GB VRAM and PixArt Model Support
Latest model support updates and office hour news from ComfyUI!
Dec 28, 2024 â€¢ 
Jo Zhang
30

Share this post

ComfyUI Blog
ComfyUI Blog
Running Hunyuan with 8GB VRAM and PixArt Model Support
Copy link
Facebook
Email
Notes
More
1

Ready for more?

© 2025 Comfy Org
Privacy ∙ Terms ∙ Collection notice
Start writingGet the app
Substack is the home for great culture

Share

Copy link
Facebook
Email
Notes
More

Create your profile

User's avatar

Only paid subscribers can comment on this post

Already a paid subscriber? Sign in

Check your email

For your security, we need to re-authenticate you.

Click the link we sent to , or click here to sign in.