sayakpaul/caption-upsampling
This repository implements the idea of "caption upsampling" from DALL-E 3 with Zephyr-7B and gathers results with SDXL.
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.
Stars
159
Forks
3
Language
Python
License
Apache-2.0
Category
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.
Higher-rated alternatives
neggles/animatediff-cli
a CLI utility/library for AnimateDiff stable diffusion generation
sakalond/StableGen
Transform your 3D texturing workflow with the power of generative AI, directly within Blender!
victordibia/peacasso
UI interface for experimenting with multimodal (text, image) models (stable diffusion).
ai-forever/Kandinsky-2
Kandinsky 2 — multilingual text2image latent diffusion model
carefree0910/carefree-drawboard
🎨 Infinite Drawboard in Python