Downloads · 30 days
275
4% of all-time downloads
RichardErkhov/trojblue_-_gpt2-prompt-upscaler-v1-gguf
trojblue_-_gpt2-prompt-upscaler-v1-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
275
4% of all-time downloads
All-time downloads
6.4K
Public
Repo size
4.8 GB
Likes
1
Public
Click a slice to open those files.
.gguf5.8 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
gpt2-prompt-upscaler-v1 - GGUF
license: mit language:
Date Trained: March 2024
A lightweight model for generating Danbooru tag-based prompts from just a few input tags. It’s simple, fast, and (hopefully) useful for enhancing your text-to-image generations. Also, nsfw mode included.
The GPT2-Prompt-Upscaler-v1 is designed to extend and refine prompts, aligning them with the tag distribution you’d expect from Danbooru images. Think of it as a friendly helper that fills in the gaps when you’re stuck or want more details for your image generation.
hatsune miku) into a fully detailed prompt with hairstyles, outfits, and accessories.The model is finetuned on GPT2-medium with 10M prompts extracted from a refined Pixiv dataset for 5 epochs, with about ~2B tokens seen per epoch.
Training is done on a 8xH100 node for about 30 hours.
The training format looks something like this:
It’s a causal GPT2 model, so you prepare your input in a structured format, and it keeps generating until it sees </output>. Here’s what an input might look like:
<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>
The model generates extensions, filling in gaps with tags that feel natural and fitting.
Okay, so here’s the deal: this model isn’t perfect. Since it’s relatively small and (confession time) it’s technically my 5th attempt at training but the first one I thought was worth keeping, it has a few quirks:
So, yeah, this isn’t a “final form” model, but I think it’s still pretty handy. I might update it in the future, so stay tuned!
I’ll be sharing:
This model is for anyone who wants quick and lightweight prompt refinement without the heavy lifting of larger models. Play around with it, and let me know what you think!