Dall-e has the ability to edit an existing image using a prompt, see here https://www.educative.io/answers/how-to-edit-an-image-using-dalle-api

I tried to clone the project but I couldn't figure out how to actually run the CLI locally in development. Perhaps you could also include development instructions in the README?

As of now, only square images can be generated by dallecli. How about allowing for wide images as documented

namespace dalle {
// Create images from a text-only prompt.
type text2im = (_: {
// The resolution of the requested image, which can be wide, square, or tall. Use 1024x1024 (square) as the default unless the prompt suggests a wide image, 1792x1024, or a full-body portrait, in which case 1024x1792 (tall) should be used instead. Always include this parameter in the request.
size?: "1792x1024" | "1024x1024" | "1024x1792",
// The user's original image description, potentially modified to abide by the dalle policies. If the user does not suggest a number of captions to create, create four of them. If creating multiple captions, make them as diverse as possible. If the user requested modifications to previous images, the captions should not simply be longer, but rather it should be refactored to integrate the suggestions into each of the captions. Generate no more than 4 images, even if the user requests more.
prompts: string[],
// A list of seeds to use for each prompt. If the user asks to modify a previous image, populate this field with the seed used to generate that image from the image dalle metadata.
seeds?: number[], }) => any;
} // namespace dalle.

Is your feature request related to a problem? Please describe.
I am trying to automate setup of dallecli for termux and the only thing needing manual input is the setup of an API key, because the update command only allows interactive usage.

I see 2 solutions for this:

1. allow to provide the api key directly from commandline dallecli update myapikey
2. read OPENAI_API_KEY variable to update configuration automaticaly if not present.

How about an option to suppress the immediate opening of the generated image, in particular with many iterations? Instead, the paths could be given, or a (temp) directory containing them.

When i run dallecli generation --iterations 4, dallecli creates 4 temporary files in /tmp, but never moves them to ./images (or the path defined with --save-path)

#Expected Behavior
I expect dallecli to respect save path when creating more than one image.

dalle3 wen?

Hi, just started using this cli tool, and i have encountered this issue, don't know if it's because of the prompt in the size, but any time I try to put a specific size, outputs me an error. This have happened with any prompt I gave to it. Maybe I need to put more parameters, I would like to have some help with this

Prompt

dallecli generate --prompt 'my prompt' --size '1920x1080' # A size example

Output

Failed to generate image. Please try again with a different prompt.

I don't know how dallecli opens the image viewer. It seems to use my default application for images (qimgv).
But qimgv always opens without any actual image.

I am actually not sure what is causing this, but i suspect it's not properly telling the path to the image?

Also: maybe it would be a nice addition if one could specify an image viewer to use.