This release is a pre-release and may not be stable for production use.
Aggressor: Ultra-minimal autoregressive diffusion model for image generation
A simplest possible implementation of Autoregressive Image Generation without Vector Quantization.
Key Features
- Simple Architecture: A tiny transformer for autoregression and an MLP for diffusion.
- Single-File Implementation: Entire model in one Python file.
- Minimal Dependencies: Built from scratch using only basic MLX operations.
Components
Aggressor: Main model class combining transformer and diffusion.Transformer: Multi-layer transformer with attention and MLP blocks.Denoiser: MLP-based diffusion process with time embedding.Scheduler: Handles forward and backward processes for diffusion.Attention: Multi-head attention mechanism.MLP: Basic multi-layer perceptron with SiLU activation.
Usage
python aggressor.py
(Training on 60000 images x 20 epochs takes approximately 7~8 minutes on 8GB M2 MacBook.)
Acknowledgements
Thanks to lucidrains' fantastic code that inspired this project. The official implementation is available here.
Metadata
Release files for aggressor 0.0.1a0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| aggressor-0.0.1a0.tar.gz | 5.6 kB | Without provenance | Details for aggressor-0.0.1a0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| aggressor-0.0.1a0-py3-none-any.whl | Python 3 | none | any | Details for aggressor-0.0.1a0-py3-none-any.whl |
Total release size: 11.4 kB
Release files / aggressor-0.0.1a0.tar.gz
| Download URL | aggressor-0.0.1a0.tar.gz |
|---|---|
| Size | 5.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d2d48b8745f2159841956ecc3f21eafe963ecac9450f93ede3041dcf2ad77dd1
|
|
BLAKE2b-256 checksum How to use checksums |
b3d60a82440e138b61f05b206853a8e7b926d9d6a42386a26d76821193ddfa00
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.1.0 CPython/3.12.3
|
Release files / aggressor-0.0.1a0-py3-none-any.whl
| Download URL | aggressor-0.0.1a0-py3-none-any.whl |
|---|---|
| Size | 5.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
3651c92cf797bf4bd4d4ee5b1582ab72739efc41475cef28d0872dd5581defba
|
|
BLAKE2b-256 checksum How to use checksums |
50b0331aa22b0596181b7a38771df1b9ecda683e9ea700d2e018f16e4769fd01
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.1.0 CPython/3.12.3
|
Security for aggressor 0.0.1a0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.