> ## Documentation Index > Fetch the complete documentation index at: https://docs.comfy.org/llms.txt > Use this file to discover all available pages before exploring further. # OpenAIGPTImageNodeV3 - ComfyUI Built-in Node Documentation > OpenAI GPT Image 2.6 generates images from a prompt, and edits them when you connect reference images, using OpenAI's GPT Image models. ## Overview OpenAI GPT Image 2.6 generates images from a prompt, and edits them when you connect reference images, using OpenAI's GPT Image models. The node offers four models: `gpt-image-2.6-flare`, `gpt-image-2.6-sunburst`, `gpt-image-2.5-flare` and `gpt-image-2.5-sunburst`. Draw annotations on the first reference image and connect them as a markup pair to show the model exactly where to edit. ## Inputs ### Common Inputs | Parameter | Description | Data Type | Required | Range | | - | - | - | - | - | | `model` | The GPT Image model to use. Selecting a model reveals the parameters for that model. | DYNAMIC\_COMBO | Yes | `"gpt-image-2.6-flare"` `"gpt-image-2.6-sunburst"` `"gpt-image-2.5-flare"` `"gpt-image-2.5-sunburst"` | ### gpt-image-2.6-flare and gpt-image-2.6-sunburst Inputs These inputs appear when `model` is set to `gpt-image-2.6-flare` or `gpt-image-2.6-sunburst`. Both models share the same parameters. | Parameter | Description | Data Type | Required | Range | | - | - | - | - | - | | `model.prompt` | What to generate, or the edit to make. (default: `""`) | STRING | Yes | N/A | | `model.size` | Image size. Select "Custom" to use the custom width and height. (default: `"auto"`) | COMBO | Yes | `"auto"` `"1024x1024"` `"1024x1536"` `"1536x1024"` `"2048x2048"` `"2048x1152"` `"1152x2048"` `"3840x2160"` `"2160x3840"` `"Custom"` | | `model.custom_width` | Used only when `model.size` is "Custom". Must be a multiple of 16. (default: `1024`) | INT | No | 480 to 3840 (step 16) | | `model.custom_height` | Used only when `model.size` is "Custom". Must be a multiple of 16. (default: `1024`) | INT | No | 480 to 3840 (step 16) | | `model.background` | Return the image with or without a background. (default: `"auto"`) | COMBO | Yes | `"auto"` `"opaque"` `"transparent"` | | `model.quality` | Image quality. Higher levels cost more and take longer. (default: `"low"`) | COMBO | Yes | `"low"` `"medium"` `"high"` `"xhigh"` `"max"` | | `model.complexity` | How much the model plans the image before rendering. (default: `"high"`) | COMBO | Yes | `"low"` `"medium"` `"high"` | | `model.images` | Optional reference images for editing. Up to 16. | AUTOGROW | No | 0 to 16 | | `model.markup` | Annotations drawn over the first reference image, showing where to edit. Must match that image's size, and must be connected together with `model.markup_alpha`. | IMAGE | No | N/A | | `model.markup_alpha` | White marks the annotations in `model.markup`. The Painter node's MASK output fits directly; a Load Image mask needs Invert Mask first. | MASK | No | N/A | | `model.seed` | Controls whether the node re-runs; results are non-deterministic regardless of seed. (default: `42`) | INT | Yes | 0 to 2147483647 | ### gpt-image-2.5-flare and gpt-image-2.5-sunburst Inputs These inputs appear when `model` is set to `gpt-image-2.5-flare` or `gpt-image-2.5-sunburst`. They match the 2.6 models except that `model.complexity` is not offered. | Parameter | Description | Data Type | Required | Range | | - | - | - | - | - | | `model.prompt` | What to generate, or the edit to make. (default: `""`) | STRING | Yes | N/A | | `model.size` | Image size. Select "Custom" to use the custom width and height. (default: `"auto"`) | COMBO | Yes | `"auto"` `"1024x1024"` `"1024x1536"` `"1536x1024"` `"2048x2048"` `"2048x1152"` `"1152x2048"` `"3840x2160"` `"2160x3840"` `"Custom"` | | `model.custom_width` | Used only when `model.size` is "Custom". Must be a multiple of 16. (default: `1024`) | INT | No | 480 to 3840 (step 16) | | `model.custom_height` | Used only when `model.size` is "Custom". Must be a multiple of 16. (default: `1024`) | INT | No | 480 to 3840 (step 16) | | `model.background` | Return the image with or without a background. (default: `"auto"`) | COMBO | Yes | `"auto"` `"opaque"` `"transparent"` | | `model.quality` | Image quality. Higher levels cost more and take longer. (default: `"low"`) | COMBO | Yes | `"low"` `"medium"` `"high"` `"xhigh"` `"max"` | | `model.images` | Optional reference images for editing. Up to 16. | AUTOGROW | No | 0 to 16 | | `model.markup` | Annotations drawn over the first reference image, showing where to edit. Must match that image's size, and must be connected together with `model.markup_alpha`. | IMAGE | No | N/A | | `model.markup_alpha` | White marks the annotations in `model.markup`. The Painter node's MASK output fits directly; a Load Image mask needs Invert Mask first. | MASK | No | N/A | | `model.seed` | Controls whether the node re-runs; results are non-deterministic regardless of seed. (default: `42`) | INT | Yes | 0 to 2147483647 | **Parameter Constraints and Limitations:** * With `model.size` set to "Custom", `model.custom_width` and `model.custom_height` must both be multiples of 16, the longest edge must not exceed 3840, the aspect ratio must not exceed 3:1, and the total pixel count must be between 655,360 and 8,294,400. * `model.markup` and `model.markup_alpha` must be connected together. Markup needs at least one reference image, and its width and height must match the first reference image. * Without `model.images` the node generates images from the prompt alone; with reference images it edits and combines them. * Reference images are downscaled before they are sent to the API. * `model.complexity` exists only on `gpt-image-2.6-flare` and `gpt-image-2.6-sunburst`; the 2.5 models use a fixed planning depth. ## Outputs | Output Name | Description | Data Type | | - | - | - | | `image` | The generated image or images. All returned images are stacked into one batch; if their dimensions differ, they are resized to match the first image. | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/OpenAIGPTImageNodeV3/en.md) *** **Source fingerprint (SHA-256):** `33f5d91af56c215cc7f7c704f9b123fe1c35bf287012072b818b76b551c04667` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.