social-ai
baml
| social-ai | baml | |
|---|---|---|
| 3 | 3 | |
| 4 | 214 | |
| - | 18.7% | |
| 5.8 | 9.9 | |
| 6 months ago | 2 days ago | |
| C# | Rust | |
| MIT License | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
social-ai
-
Fuck You, Show Me the Prompt
I wrote some code to annotate the image with the text of the prompt. I couldn't find a convenient way to do it in EXIF.
For Midjourney: https://github.com/ernop/social-ai/tree/main/SocialAI
-
DALL·E 3
Yeah, it's really strange how hard they make it to manage, download, and get full prompts for your images on all these platforms. I made this discord bot for midjourney which with some easy configuration can download and annotate all your images, including as much info as I could grab about version, etc. https://github.com/ernop/social-ai/tree/main/SocialAI
Even then it's not perfect since I'm getting info off of the command you send, which may have fallen into whatever the defaults were at the time, and so when interpreted today, not easily possible to reconstruct the version/seed/etc. from that point in the past, if you didn't include it in the prompt. But still, I just like having a folder of 30k images that I can never lose, with at least the prompt, so I can go through and re-run them later (even manually) to get comparisons over time.
-
Midjourney AI Guide
Repo for my C# bot which you can use to download (and annotate) all your creations. https://github.com/ernop/social-ai/
baml
- BAML: A programming language to get structured data from LLMs
-
Fuck You, Show Me the Prompt
We felt this 100% so we built a DSL (called BAML) to solve the "prompt transparency" problem (amongst other issues). We have a VSCode playground that always shows you the full prompt -- kinda like a markdown preview works.
We are still in beta (and open source) but feel free to check it out! https://docs.boundaryml.com/ .
Some of these frameworks like instructor use like 80% more tokens or only work with OpenAI so we aim to tackle all these problems from the ground up.
- DSL for building AI and interacting with LLMs and other AI models
What are some alternatives?
Fooocus - Focus on prompting and generating
ControlNet - Let us control diffusion models!
sd-webui-cutoff - Cutoff - Cutting Off Prompt Effect