OpenAI: GPT-Image-1 Multi Inputs

Generate images from multiple inputs using OpenAI GPT Image 1 API.

Download Workflow Try in Cloud API documentation

About

This ComfyUI workflow leverages the OpenAI GPT-Image-1 model to generate images from multiple input sources. By integrating various nodes such as OpenAIGPTImage1, LoadImage, and ImageBatch, the workflow efficiently processes and combines different types of inputs to produce a cohesive image output. The OpenAIGPTImage1 node serves as the core component, utilizing OpenAI's advanced image generation capabilities to interpret and synthesize visual data from textual descriptions or other image inputs.

This workflow is particularly useful for users who need to generate complex images that require input from multiple sources, such as text prompts and existing images.

Technically, the workflow begins with loading images using the LoadImage node, which can handle multiple image inputs simultaneously through the ImageBatch node. These inputs are then processed by the OpenAIGPTImage1 node, which applies OpenAI's sophisticated algorithms to generate new images based on the provided data.

Finally, the SaveImage node ensures that the output images are stored for further use. The inclusion of a MarkdownNote node allows users to annotate their workflow, providing context or instructions directly within the ComfyUI interface. This workflow is particularly beneficial in fields such as digital art, marketing, and content creation, where generating high-quality, contextually relevant images is crucial.

What you provide

Reading the workflow

Runs in ComfyUI. This workflow can't run on this page. Open it in Comfy Cloud with everything loaded, or download it for your own ComfyUI.

Try in Cloud

Output

Use this workflow from code

Generated from the workflow graph and inputs when possible; stored examples are shown otherwise. Review credentials and endpoints before running code, which may incur charges.

Get API key

What you need

Runs on: Comfy Cloud
Key: COMFY_API_KEY
Your files: Uploaded by the code from their urls

Needs a paid Cloud plan and credits.

Download API JSON

# Python 3.10+: pip install comfy-sdk==0.4.0
import os

from comfy_sdk import Comfy

api_key = os.environ.get("COMFY_API_KEY", "").strip()
if not api_key: raise RuntimeError("Set COMFY_API_KEY")
os.environ.setdefault("COMFY_BASE_URL", "https://cloud.comfy.org")
client = Comfy(api_key=api_key)
workflow = client.workflows.from_json({
    "1": {
        "class_type": "OpenAIGPTImage1",
        "inputs": {
            "background": "opaque",
            "custom_height": 1024,
            "custom_width": 1024,
            "image": [
                "3",
                0
            ],
            "model": "gpt-image-2",
            "n": 1,
            "prompt": "A cute cat sitting on a boat, holding a glass of champagne, with the vast ocean in the background, wearing a red hat and red - framed sunglasses, in the style of Studio Ghibli",
            "quality": "high",
            "seed": 1384371958,
            "size": "auto"
        },
        "_meta": {
            "title": "OpenAI GPT Image 2"
        }
    },
    "2": {
        "class_type": "LoadImage",
        "inputs": {
            "image": "UPLOADED_image_FILENAME"
        },
        "_meta": {
            "title": "Load Image"
        }
    },
    "3": {
        "class_type": "ImageBatch",
        "inputs": {
            "image1": [
                "4",
                0
            ],
            "image2": [
                "2",
                0
            ]
        },
        "_meta": {
            "title": "Batch Images (DEPRECATED)"
        }
    },
    "4": {
        "class_type": "LoadImage",
        "inputs": {
            "image": "UPLOADED_image_2_FILENAME"
        },
        "_meta": {
            "title": "Load Image"
        }
    },
    "6": {
        "class_type": "SaveImage",
        "inputs": {
            "filename_prefix": "ComfyUI",
            "images": [
                "1",
                0
            ]
        },
        "_meta": {
            "title": "Save Image"
        }
    }
})
# Replace each example.com URL with a public URL of your file.
workflow.set_input("2", "image", client.assets.from_url("https://example.com/replace-with-a-url/image"))
workflow.set_input("4", "image", client.assets.from_url("https://example.com/replace-with-a-url/image_2"))

# run() also passes api_key to the partner nodes in this workflow.
job = client.run(workflow, api_key=api_key)

API documentation

OpenAI: GPT-Image-1 Multi Inputs

About

What you provide

Inside the workflow

Requires custom nodes

Use this workflow from code

What you need

Questions & answers

About

What you provide

Inside the workflow

Requires custom nodes

Use this workflow from code

What you need

Questions & answers

What types of inputs can I use with this workflow?

Do I need an internet connection to use this workflow?

How can I ensure the security of my API credentials?

Can I save the generated images automatically?