Currently we have to have LLM describe what we want our image to look like than generate the image by clicking the icon. Can we limit the process by using /image followed by the image description then pressing enter or clicking send will automatically generate the image? Are we any closer to just asking it to "create an image" of something rather than having to have it be described then clicking the image generation icon?
Originally created by @ItsNoted on GitHub (Jun 17, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/3236
Currently we have to have LLM describe what we want our image to look like than generate the image by clicking the icon. Can we limit the process by using /image followed by the image description then pressing enter or clicking send will automatically generate the image? Are we any closer to just asking it to "create an image" of something rather than having to have it be described then clicking the image generation icon?
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @ItsNoted on GitHub (Jun 17, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/3236
Currently we have to have LLM describe what we want our image to look like than generate the image by clicking the icon. Can we limit the process by using /image followed by the image description then pressing enter or clicking send will automatically generate the image? Are we any closer to just asking it to "create an image" of something rather than having to have it be described then clicking the image generation icon?
@tjbck commented on GitHub (Jun 17, 2024):
Related #2048