ComfyUI Node
OpenAI Image Generation
A ComfyUI node in ERPK/OpenAI with 9 inputs and 2 outputs.
OpenAI Image Generation
- client
- image
- revised_prompt
◄prompt►
◄seed-1►
◄modelgpt-image-2►
◄size1024x1024►
◄qualityauto►
◄backgroundauto►
◄moderationauto►
◄n1►
CategoryERPK/OpenAI
Inputs (9)
| Name | Type | Default | Description |
|---|---|---|---|
| prompt | STRING | Description of the image to generate | |
| seed | INT | -1-1–2147483647 | Seed for reproducible outputs (best-effort). Randomizes by default. |
| clientopt | OPENAI_API_CLIENT | OpenAI API client from OpenAI API Config node (uses API key from config) | |
| modelopt | COMBO | gpt-image-2 | Image generation model. gpt-image-2: latest flagship, 4K output, multilingual text. gpt-image-1.5: previous flagship, supports transparent background. |
| sizeopt | STRING | 1024x1024 | Image size as WIDTHxHEIGHT (e.g. "1024x1024", "1536x864"). Standard GPT Image sizes: 1024x1024, 1536x1024, 1024x1536. gpt-image-2 accepts arbitrary sizes: both edges divisible by 16, aspect ratio between 1:3 and 3:1, total pixels 655,360 to 8,294,400, max edge 3840px. Use "auto" to let the model choose. |
| qualityopt | COMBO | auto | Image quality. auto/low/medium/high for GPT Image family; hd/standard are legacy DALL-E values, kept for compatibility. |
| backgroundopt | COMBO | auto | Background type for the generated output (GPT Image models only). 'transparent' requires an output format that supports transparency (png or webp). |
| moderationopt | COMBO | auto | Content moderation level (GPT Image models only). 'auto' uses OpenAI's default safety filters; 'low' relaxes them for permissive content. |
| nopt | INT | 11–10 | Number of images to generate per call (OpenAI supports 1-10). |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| image | IMAGE | — |
| revised_prompt | STRING | — |