OpenAIImage modelGPT-Image-1
GPT-Image-1 is a image model by OpenAI. It supports text to image, image to image, quality.
Model availability and access depend on your workspace and plan.
About the model
GPT-Image-1, explained.
GPT-Image-1 is a image model by OpenAI. It supports text to image, image to image, quality.
Supported capabilities
- Text to image
- Image to image
- Quality
What you get back. Your generated image appears directly in your Relam chat.
Working with GPT-Image-1
Shape the result.
Prompt
Required inputA text description of the desired image
User Id
Optional inputAn optional unique identifier representing your end-user. This helps OpenAI monitor and detect abuse.
Input Images
Optional inputA list of images to use as input for the generation
Number Of Images
Optional inputNumber of images to generate (1-10)
Output Compression
Optional inputCompression level (0-100%)
Output & configuration
The details you control.
These options come from GPT-Image-1’s model specification. Your workspace shows the options included with your plan.
- Quality
The quality of the generated image
Questions & answers
More about GPT-Image-1.
GPT-Image-1 is a image model by OpenAI. It supports text to image, image to image, quality.
OpenAI is the vendor behind GPT-Image-1, a image model available in the Relam catalogue.
A text description of the desired image This input is required.
An optional unique identifier representing your end-user. This helps OpenAI monitor and detect abuse.
A list of images to use as input for the generation
Number of images to generate (1-10)
Compression level (0-100%)
The quality of the generated image. Supported values are low, medium, high, auto. The model default is auto. Your workspace may offer a narrower selection depending on your plan.
Set whether the background is transparent or opaque or choose automatically. Supported values are auto, transparent, opaque. The model default is auto. Your workspace may offer a narrower selection depending on your plan.
Content moderation level. Supported values are auto, low. The model default is auto. Your workspace may offer a narrower selection depending on your plan.
The aspect ratio of the generated image. Supported values are 1:1, 3:2, 2:3. The model default is 1:1. Your workspace may offer a narrower selection depending on your plan.
Output format. Supported values are png, jpeg, webp. The model default is webp. Your workspace may offer a narrower selection depending on your plan.
Open your Relam workspace and look for GPT-Image-1 in the image model selector. Its required inputs are prompt. Available models, controls and access depend on your workspace and plan.