dongzhuoyao/self-guided-diffusion-models

An official implementation of CVPR 2023 "Self-Guided Diffusion Models"

30
/ 100
Emerging

This project offers a way to generate new images that align with specific conditions, whether those conditions are broad categories (like "animals") or highly detailed instructions (like "a cat with a striped tail in a living room"). It takes existing image datasets and, through a process of 'self-guidance', learns to create novel images that fit precise descriptions or structural layouts. Image generation researchers and practitioners who work with generative AI models for creating visually coherent content would find this useful.

No commits in the last 6 months.

Use this if you need fine-grained control over the characteristics of generated images, from overall themes to specific object placements and pixel-level features.

Not ideal if you are looking for a simple, out-of-the-box solution for casual image generation without needing to delve into model training and configuration.

image generation generative AI computer vision conditional image synthesis deep learning research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

27

Forks

2

Language

Python

License

MIT

Last pushed

Jun 02, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/dongzhuoyao/self-guided-diffusion-models"

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