Update README.md

README.md

@@ -9,4 +9,56 @@ tags:
 - transformers
 - pytorch
 - gpt2
----
+---
+
+>  date trained: March, 2024
+
+A lightweight prompt-generating model for generating danbooru tag-based prompts from few input tags.
+
+
+
+The model is trained with the consideration of being a supplementary **lightweight** model for prompt refinements:
+
+- **small**: with only **335M** parameters, the model offers an lightweight solution of prompt filling compared to much larger models such as phi-3 or llama 8b.
+- **fast**: the model generates fairly quickly to not interfere with the main text generation as possible
+- **low vram requirement**: the model takes less vram, so it saves more vram for the main image generation model.
+
+
+
+The model is capable of:
+
+- **character refinement**: filling more details about characters by inputting a danbooru character tag (eg. `hatsune miku`)
+- **filling small details**: Filling creative details onto a faily thought out scene (add small details)
+- **creative inspirations**: adding randomness to a short prompt for inspirations
+- **prompt-to-prompt**: refine prompt elements to steer toward a better generation
+
+
+
+## Training details
+
+
+
+The model is finetuned on GPT2-medium, using 10M prompts from a refined full pixiv dataset, in the format of:
+
+- **rating**: [safe | nsfw]
+- **chara**: [danbooru character tags]
+- **date**: [2020s | 2010s | 2000s]
+- **quality**: [normal | good | excellent]  (by image aesthetic ratings)
+- **tags**: [rest of the danbooru general tags]
+- **output**: model output
+
+
+
+Some example training entries would look like this:
+
+```
+'<input rating="safe" chara="" date="2020s" quality="excellent" tags="1girl, long hair, white hair"><output>'
+'<input rating="safe" chara="" date="2020s" quality="excellent" tags="1girl, purple hair, white hair"><output>'
+'<input rating="safe" chara="" date="2020s" quality="excellent" tags="gothic lolita"><output>'
+'<input rating="safe" chara="hatsune miku" date="2020s" quality="excellent" tags=""><output>'
+```
+
+
+
+You can find the full dataset soon.
+