sayakpaul/caption-upsampling

This repository implements the idea of "caption upsampling" from DALL-E 3 with Zephyr-7B and gathers results with SDXL.

31
/ 100
Emerging

This helps text-to-image creators enhance their prompts. You provide a short, simple image description, and it generates a much richer, more detailed narrative. The result is a highly descriptive caption that leads to more nuanced and precise image generation. This is ideal for artists, marketers, or anyone creating visuals with AI.

159 stars. No commits in the last 6 months.

Use this if you want to transform basic image prompts into elaborate scene descriptions for better AI-generated artwork, without relying on expensive proprietary models.

Not ideal if you only need short, simple prompts or if you prefer to write every detail of your image descriptions manually.

AI art image generation creative writing digital marketing prompt engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

159

Forks

3

Language

Python

License

Apache-2.0

Last pushed

Oct 25, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/sayakpaul/caption-upsampling"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.