ComfyUI Node
OpenAI Image Generation (Responses)
A ComfyUI node in ERPK/OpenAI with 13 inputs and 3 outputs.
OpenAI Image Generation (Responses)
- client
- image
- revised_prompt
- reasoning_summary
◄prompt►
◄seed-1►
◄mainline_modelgpt-5.5►
◄image_modelgpt-image-2►
◄reasoning_effortnone►
◄verbositydefault►
◄size1024x1024►
◄qualityauto►
◄backgroundauto►
◄output_formatpng►
◄moderationauto►
◄enable_web_searchfalse►
CategoryERPK/OpenAI
Inputs (13)
| Name | Type | Default | Description |
|---|---|---|---|
| prompt | STRING | Image description. The mainline model may auto-revise it before passing to the image model. | |
| seed | INT | -1-1–2147483647 | Cache-bust seed. Randomizes by default. |
| clientopt | OPENAI_API_CLIENT | OpenAI API client from OpenAI API Config node | |
| mainline_modelopt | COMBO | gpt-5.5 | Text/reasoning model that drives the Responses API call. Not the image model — this picks prompt interpretation, reasoning, and (optionally) web search. gpt-5.5 is the current premium flagship with the highest reasoning tier; gpt-5.4 is a cheaper alternative for cost-sensitive workflows. |
| image_modelopt | COMBO | gpt-image-2 | Underlying GPT Image model used for pixel generation inside the tool. |
| reasoning_effortopt | COMBO | none | Mainline-model reasoning depth. 'none' skips reasoning (cheapest, fastest). 'low' to 'xhigh' increase prompt-interpretation quality at token cost. Only supported by reasoning-capable mainline models (gpt-5.x, o3, o4-mini). Note: when enabled, reasoning_summary output contains the model's raw chain-of-thought, which often includes orchestration-level thinking (output channels, response format) rather than only creative rationale. |
| verbosityopt | COMBO | default | Mainline-model output verbosity (gpt-5.x family). Shapes how chatty the response is independent of max_tokens. 'default' lets the model pick. Silently dropped for older mainlines. |
| sizeopt | COMBO | 1024x1024 | Image size. Same constraints as direct endpoint (gpt-image-2: min 655,360 pixels). |
| qualityopt | COMBO | auto | Image quality tier. |
| backgroundopt | COMBO | auto | Background type. gpt-image-2 rejects 'transparent' — auto-coerced to 'opaque' with a warning log. |
| output_formatopt | COMBO | png | Output image format. |
| moderationopt | COMBO | auto | Content moderation level. 'low' relaxes default safety filters. |
| enable_web_searchopt | BOOLEAN | false | Add the web_search tool alongside image_generation. The mainline model can decide to look up reference material before generating. Adds $10/1000 calls when the model actually invokes it. |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| image | IMAGE | — |
| revised_prompt | STRING | — |
| reasoning_summary | STRING | — |