yandex-research/adaptive-diffusion

[CVPR'2024] Adaptive Teacher-Student Collaboration for Text-Conditional Diffusion Models

27
/ 100
Experimental

This project helps content creators and digital artists generate high-quality images from text descriptions more efficiently. You provide a text prompt describing the desired image, and it intelligently decides whether a fast, 'student' image model is sufficient or if a slower, more detailed 'teacher' model is needed for better results. The output is a high-fidelity image that balances speed and visual quality.

No commits in the last 6 months.

Use this if you need to generate high-quality images from text prompts and want to optimize for a balance between speed and image fidelity, rather than always waiting for the slowest, most detailed model.

Not ideal if you prioritize absolute fastest image generation regardless of quality, or if you exclusively need the highest possible quality for every image without any time constraints.

AI-art-generation digital-content-creation text-to-image generative-AI creative-workflow
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 4 / 25

How are scores calculated?

Stars

33

Forks

1

Language

Python

License

Apache-2.0

Last pushed

Apr 03, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/yandex-research/adaptive-diffusion"

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