evolink-image

Generate images from text prompts by running the bundled generate_image.py script, which sends your descriptive text to Evolink's gpt-image-2 model. The script handles task creation, asynchronous polling, and downloads the resulting bitmap images directly to a local directory.

You can edit existing images using the image-to-image and edit-with-reference scenarios supported by the script. By providing an optional reference image alongside your prompt, Evolink's gpt-image-2 model will refine and modify the original bitmap visuals according to your descriptive instructions.

Asynchronous AI image generation handles long processing times by creating a background task and polling for the status until completion. This approach prevents timeouts while the model processes your prompt, automatically downloading the final bitmap images to your local directory once the task succeeds.

You need an Evolink API key to authenticate requests for image generation. The script enforces environment-based API key usage, requiring you to configure the key in your local environment variables before creating tasks or downloading results.

You can customize the size, resolution, quality, and number of images when generating AI visuals. These flexible output options are passed to the script, allowing you to control the final dimensions and detail level of the bitmap images downloaded locally.

If the asynchronous image generation task fails, the script provides status and error reporting to indicate what went wrong. This reporting covers issues during task creation, polling, or downloading, helping you troubleshoot API connectivity or prompt processing failures.