Debanjum Singh Solanky 6c1861b319 Improve the prompt to generate images with DALLE3 and SD3
- Major
  - Ask for prompt in prose
  - Remove seed from SD3 image generation to improve diversity of output
    for a given prompt
    Otherwise for conversations with similar sounding
    prompts, the images would be almost exactly the same. This maybe
    another indicator of SD3's inability to capture detailed
    instructions
  - Consistently use "prompt" wording instead of "query" in improved
    image generation prompts.
    Previously a mix of those terms were being used, which could confuse
    the chat model

- Minor
  - Add day of week to prompt
  - Remove 2-5 sentence limit on instructions to SD3. It seems to be
    able to follow longer instructions just with less fidelity than
    DALLE. And the 2-5 sentence instruction limit wasn't being adhered to
  - Improve ability to edit, improve the image based on follow-up
    instructions by the user
  - Align prompts for DALLE and SD3. Only difference is to wrap text to
    be rendered in quotes for SD3. This improves it's ability to render
    requested text. DALLE cannot render text as well or consistently
2024-07-11 16:29:53 +05:30
2024-07-09 12:28:11 +05:30
2024-07-08 16:49:13 +05:30
2024-07-07 18:26:10 +05:30
2024-07-07 18:26:10 +05:30
2024-07-09 12:28:11 +05:30
2024-07-07 18:26:10 +05:30

Khoj Logo

test dockerize pypi Discord

The open-source, personal AI for your digital brain

🤖 Read Docs   •   🏮 Khoj Cloud   •   💬 Get Involved   •   📚 Read Blog


Khoj is an application that creates always-available, personal AI agents for you to extend your capabilities.

  • You can share your notes and documents to extend your digital brain.
  • Your AI agents have access to the internet, allowing you to incorporate realtime information.
  • Khoj is accessible on Desktop, Emacs, Obsidian, Web and Whatsapp.
  • You can share pdf, markdown, org-mode, notion files and github repositories.
  • You'll get fast, accurate semantic search on top of your docs.
  • Your agents can create deeply personal images and understand your speech.
  • Khoj is open-source, self-hostable. Always.

See it in action

Khoj Demo

Go to https://app.khoj.dev to see Khoj live.

Full feature list

You can see the full feature list here.

Self-Host

To get started with self-hosting Khoj, read the docs.

Contributors

Cheers to our awesome contributors! 🎉

Made with contrib.rocks.

Interested in Contributing?

We are always looking for contributors to help us build new features, improve the project documentation, or fix bugs. If you're interested, please see our Contributing Guidelines and check out our Contributors Project Board.

Sponsors

Shout out to our brilliant sponsors! 🌈

Description
No description provided
Readme AGPL-3.0 116 MiB
Languages
Python 51%
TypeScript 36.1%
CSS 4.1%
HTML 3.2%
Emacs Lisp 2.4%
Other 3.1%