diffusers and azula

Diffusers is a mature, production-ready framework that provides pre-built pipelines and model implementations, while Azula is a lower-level research library focused on core diffusion model components and theory—making them complementary tools where Azula could be used to build custom diffusion models that Diffusers then packages and deploys at scale.

diffusers
87
Verified
azula
56
Established
Maintenance 22/25
Adoption 15/25
Maturity 25/25
Community 25/25
Maintenance 10/25
Adoption 10/25
Maturity 25/25
Community 11/25
Stars: 33,029
Forks: 6,832
Downloads:
Commits (30d): 85
Language: Python
License: Apache-2.0
Stars: 128
Forks: 10
Downloads:
Commits (30d): 0
Language: Python
License: MIT
No risk flags
No risk flags

About diffusers

huggingface/diffusers

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

This library helps developers and researchers create or use AI models that generate new images, audio, or even molecular structures. You provide text descriptions or existing data, and it outputs novel visual, auditory, or structural content. It's designed for machine learning practitioners and AI artists.

AI-art-generation synthetic-media AI-research computational-chemistry

About azula

probabilists/azula

Diffusion models in PyTorch

Azula is a specialized tool that helps machine learning researchers and practitioners generate new, realistic data samples from existing datasets. It takes your raw data, learns its underlying patterns, and then outputs novel data points that resemble the original, such as creating new images or other complex data structures. This is ideal for those working on advanced generative AI.

generative-ai machine-learning-research data-synthesis deep-learning image-generation

Scores updated daily from GitHub, PyPI, and npm data. How scores work