I used to be heavy Anki user but I find the setup a little hard to follow.
The image generation can do with ComfyUI integration. This will expand the illustration options beyond stable diffusion. It will also allow for more options within stable diffusion too.
Thanks for the interest! The idea was to fully automate the process of creating illustrations for the failed cards of the day based on few shot prompting alone, indeed adding support for external API like ComfyUI would help a lot. Maybe especially for finetunes on specific subjets I guess?
The image generation can do with ComfyUI integration. This will expand the illustration options beyond stable diffusion. It will also allow for more options within stable diffusion too.
I might raise a PR tomorrow if I have the time.