ComfyUI Node
OpenAI Generate Image
Generate image using OpenAI API and return as torch.Tensor (h,w,c) and text
OpenAI Generate Image
- image
- image1
- image2
- image3
- image4
- history
- image
- images
- num_images
- text
- history
◄api_key►
◄base_url►
◄model_namegpt-image-1►
◄system_prompt—►
◄prompt—►
◄sizeauto►
◄qualityauto►
◄stylevivid►
◄n1►
◄response_formaturl►
◄retry_count1►
◄chat_template<-system->
{{system_instruction}}
<-/system->
<-user->
{{prompt}}
<-/user->►
◄proxy_url►
◄api_typeauto►
◄seed-1►
◄aspect_ratioauto►
◄timeout0►
◄extra{}►
◄image_send_modeupload►
CategoryYogurtNodes/LLM
Inputs (25)
| Name | Type | Default | Description |
|---|---|---|---|
| api_key | STRING | API key for accessing OpenAI API | |
| base_url | STRING | Base URL for OpenAI API (leave blank for official API) | |
| model_name | STRING | gpt-image-1 | OpenAI image generation model name |
| system_prompt | STRING | System-level prompt that affects the overall image generation style | |
| prompt | STRING | Main prompt content for image generation | |
| size | COMBO | auto | Size of the generated image |
| quality | COMBO | auto | Quality of the generated image |
| style | COMBO | vivid | Style of the generated image (dall-e-3 only) |
| n | INT | 11–10 | Number of images to generate (dall-e-2 only) |
| response_format | COMBO | url | Response format for generated images |
| retry_count | INT | 1 | Number of retries when request fails |
| chat_template | STRING | <-system-> {{system_instruction}} <-/system-> <-user-> {{prompt}} <-/user-> | Content template for the image generation prompt |
| proxy_url | STRING | 代理URL，格式: protocol://user:pass@addr:port，支持http,https,socks5,socks5h | |
| api_type | COMBO | auto | 选择使用的API类型: auto(自动根据模型选择), response(Responses API), image(Images API) |
| seed | INT | -1-1–2147483647 | Random seed for generation (-1 for random) |
| aspect_ratio | COMBO | auto | Aspect ratio for generated images, for nano banana only |
| timeout | INT | 00–2147483647 | Timeout for the request in seconds, 0 means no timeout |
| imageopt | IMAGE | — | |
| image1opt | IMAGE | — | |
| image2opt | IMAGE | — | |
| image3opt | IMAGE | — | |
| image4opt | IMAGE | — | |
| historyopt | HISTORY | — | |
| extraopt | STRING | {} | Extra parameters for the request, in JSON format |
| image_send_modeopt | COMBO | upload | 输入图像发送方式: upload(文件上传, OpenAI官方兼容), base64(JSON中data URL, x.ai兼容) |
Outputs (5)
| Name | Type | Description |
|---|---|---|
| image | IMAGE | — |
| images | IMAGE | — |
| num_images | INT | — |
| text | STRING | — |
| history | HISTORY | — |