open-webui icon indicating copy to clipboard operation
open-webui copied to clipboard

Published 20 hours ago • verified publisher icon open-webui

enhancement: better image generation UX (e.g. semantic routing)

Open colaber2 opened this issue 1 year ago • 6 comments

The current method of generating images doesn't feel natural.

Screen Shot 2024-05-07 at 5 14 16 PM

My suggestions would be (either/or):

  1. adding a separate page for image generation
  2. start the prompt with something like: "/imagine: {PROMPT}" just like Midjourney with discord

Thanks for your efforts and for the amazing work!!

colaber2 avatar May 07 '24 14:05 colaber2

The current method of generating images doesn't feel natural.

Thanks for your ideas.. agreed 100%, I too have felt it might be more appropriate to have image generation be a part of our "Playground" interface, which itself is in need of expansion (please see #2000). We're open to suggestions and especially PRs!

justinh-rahb avatar May 07 '24 14:05 justinh-rahb

This is actively being worked on! I appreciate your patience!

tjbck avatar May 07 '24 18:05 tjbck

Related: #2004

tjbck avatar May 07 '24 18:05 tjbck

I wish we could just "fork a conversation" . Like you do in LLM Studio.

AdaptiveStep avatar May 14 '24 07:05 AdaptiveStep

The current method of generating images doesn't feel natural.

Thanks for your ideas.. agreed 100%, I too have felt it might be more appropriate to have image generation be a part of our "Playground" interface, which itself is in need of expansion (please see #2000). We're open to suggestions and especially PRs!

Noted! I will check it.

colaber2 avatar May 16 '24 09:05 colaber2

This is actively being worked on! I appreciate your patience!

Great to know!! can't wait to use it.

colaber2 avatar May 16 '24 09:05 colaber2