DeepFellow DOCS

ImagesRequest

PropertyTypeRequiredDescription
promptstringYesA text description of the desired image(s).
backgroundenumNoAllows to set transparency for the background of the generated image(s).This parameter is supported on a subset of models.Must be one of transparent, opaque or auto (default value). When auto is provided, opaque will be used.If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp. One of: auto, transparent, opaque. Default: "auto".
modelstringNoThe model to use for image generation. Default: "".
moderationenumNoControl the content-moderation level for images generated. Must be either low for less restrictive filtering or auto (default value). Accepted for compatibility with the OpenAI API; currently has no effect. Support may be added in the future. One of: low, auto. Default: "auto".
nintegerNoThe number of images to generate. Must be between 1 and 10. Default: 1.
output_compressionintegerNoThe compression level (0-100%) for the generated images. This parameter is only supported with the webp or jpeg output formats, and defaults to 100. Default: 100.
output_formatenumNoThe format in which the generated images are returned. Must be one of png, jpeg, or webp. One of: png, webp, jpeg. Default: "png".
qualityenumNoThe quality of the image that will be generated. standard and hd are aliases for medium and high, kept for compatibility with the OpenAI API. auto (default value) will automatically select the best quality for the given model. One of: standard, hd, low, medium, high, auto. Default: "auto".
response_formatenumNoThe format in which generated images are returned. Must be one of url or b64_json. Currently url is not supported. One of: url, b64_json. Default: "b64_json".
sizestringNoThe size of the generated images. Default (auto) size is 512x512. Default: "auto".
stylestringNoThe style of the generated images. Must be one of vivid or natural. Vivid causes the model to lean towards generating hyper-real and dramatic images. Natural causes the model to produce more natural, less hyper-real looking images. Accepted for compatibility with the OpenAI API; currently has no effect. Support may be added in the future. Default: "vivid".
userstringNoA unique identifier representing your end-user, which can help to monitor and detect abuse. Accepted for compatibility with the OpenAI API; currently has no effect. Default: "".

We use cookies on our website. We use them to ensure proper functioning of the site and, if you agree, for purposes such as analytics, marketing, and targeting ads.