Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
stable-diffusion-webui-promptgen
| Date | Stars |
|---|---|
| 2026-07-31 | 535 |
| 2026-08-05 | 536 |
| 2026-08-06 | 536 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Prompt generator
An extension for [webui](https://github.com/AUTOMATIC1111/stable-diffusion-webui) that lets you generate prompts.
## Getting more models online
You can add models from huggingface to the selection of models in setting. The setting field
is `Hugginface model names for promptgen, separated by comma`, and its default value is
just:
```
AUTOMATIC/promptgen-lexart, AUTOMATIC/promptgen-majinai-safe, AUTOMATIC/promptgen-majinai-unsafe
```
Those are GPT2 finetunes I did on various datasets:
- [AUTOMATIC/promptgen-lexart](https://huggingface.co/AUTOMATIC/promptgen-lexart): Finetuned distilgpt2 for 100 epochs on prompts scraped from lexica.art
- [AUTOMATIC/promptgen-majinai-safe](https://huggingface.co/AUTOMATIC/promptgen-majinai-safe): Finetuned distilgpt2 for 40 epochs on safe prompts scraped from majinai.art.
- [AUTOMATIC/promptgen-majinai-unsafe](https://huggingface.co/AUTOMATIC/promptgen-majinai-unsafe): Finetuned distilgpt2 for 40 epochs on unsafe prompts scraped from majinai.art.
To add more models, add more items to the setting, for example like this:
```
AUTOMATIC/promptgen-lexart, AUTOMATIC/promptgen-majinai-safe, AUTOMATIC/promptgen-majinai-unsafe, succinctly/text2image-prompt-generator, microsoft/Promptist
```
Reloading UI is required to apply this setting.
## Getting more models offline
Put your models into the `models` directort inside the extension. For example, my model can be
made fully offline by placing fines from https://huggingface.co/AUTOMATIC/promptgen-lexart/tree/main into
those directories:
```
📁 webui root directory
┗━━ 📁 extensions
┗━━ 📁 stable-diffusion-webui-promptgen
┗━━ 📁 models
┗━━ 📁 promptgen-lexart <----- any name can be used
┣━━ 📄 config.json <----- each model has its own set of required files;
┣━━ 📄 merges.txt mine requires all those
┣━━ 📄 pytorch_model.bin
┣━━ 📄 tokenizer_config.json
┗━━ 📄 vocab.json
```
Reloading UI is required to see new models.
Excerpt of 2,203 characters
Read on GitHub
4
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:2ef51961ebc78c26, name:stable diffusion, desc:stable diffusion