Gustavosta's picture
Update model
6ce4e46
|
raw
history blame
1.57 kB

MagicPrompt - Stable Diffusion

This is a model from the MagicPrompt series of models, which are GPT-2 models intended to generate prompt texts for imaging AIs, in this case: Stable Diffusion.

🖼️ Here's an example:

This model was trained with 150,000 steps and a set of about 80,000 data filtered and extracted from the image finder for Stable Diffusion: "Lexica.art". It was a little difficult to extract the data, since the search engine still doesn't have a public API without being protected by cloudflare, but if you want to take a look at the original dataset, you can have a look here: Gustavosta/MagicPrompt-Dalle.

If you want to test the model with a demo, you can go to: "Gustavosta/spaces/MagicPrompt-Dalle".

💻 You can see other MagicPrompt models:

⚖️ Licence:

MIT

When using this model, please credit: Gustavosta

Thanks for reading this far! :)