Skip to main content

The min_diffusion library

This library was put together for a series of experiments on Classifier-free Guidance.

Install

pip install min_diffusion

How to use min_diffusion

The library has a single main class MinimalDiffusion.

This class takes three arguments:

  • model_name
  • device
  • dtype

model_name is the string model name on the HuggingFace hub.
device sets the hardware to run on.
dtype is the torch.dtype precision for the torch modules.

# import the library
from min_diffusion.core import MinimalDiffusion

Loading a sample model

Below is an example to load the openjourney model from PromptHero.

The model will be loaded in torch.float16 precision and placed on the GPU.

# set the model to load and its options
model_name = 'prompthero/openjourney'
device     = 'cuda'
dtype      = torch.float32
revision   = "fp32"

Creating a MinimalDiffusion with these arguments:

# create the minimal diffusion pipeline
pipeline = MinimalDiffusion(model_name, device, dtype, revision)

Loading the pipeline:

# load the pipeline
pipeline.load();
Enabling default unet attention slicing.

Generating an image

Below is an example text prompt for image generation.

Note the keyword "mdjrny-v4 style" at the start of the prompt. This is how the openjourney model creates images in the style of Midjourney v4.

# text prompt for image generations
prompt = "mdjrny-v4 style a photograph of an astronaut riding a horse"

Calling MinimalDiffusion on the input text prompt

# generate the image
img = pipeline.generate(prompt);
Using the default Classifier-free Guidance.

  0%|          | 0/50 [00:00<?, ?it/s]

Here is the generated image:

# view the output image
img

Notes:

The pipeline assumes you have logged in to the HuggingFace hub.

Metadata

Release files for min-diffusion 0.0.3

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for min-diffusion 0.0.3
File Size Uploaded Provenance Actions
min_diffusion-0.0.3.tar.gz 16.3 kB Without provenance Details for min_diffusion-0.0.3.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for min-diffusion 0.0.3
File Interpreter ABI Platform Actions
min_diffusion-0.0.3-py3-none-any.whl Python 3 none any Details for min_diffusion-0.0.3-py3-none-any.whl

Total release size: 32.2 kB

Release files / min_diffusion-0.0.3.tar.gz

Download URL min_diffusion-0.0.3.tar.gz
Size 16.3 kB
Tags Source
SHA-256 checksum
How to use checksums
a05ead6610b178ea0d1da1e4661808e9c311c2d7424a80da4e77662203e9994d
BLAKE2b-256 checksum
How to use checksums
a4f10a9d767f37ba525c3a956bb178b34d6cd0609a9619758b3b7403c576b710
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.1 CPython/3.10.8

Release files / min_diffusion-0.0.3-py3-none-any.whl

Download URL min_diffusion-0.0.3-py3-none-any.whl
Size 15.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
8e463c0db7b193a0c77bab3754ab4b30fec8e88b81df773e5a8a6db776a5eb5b
BLAKE2b-256 checksum
How to use checksums
2db0c3a43c05896d1be7b729f0ef0d14da5877b3db8c30f00130d3aea1baee70
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.1 CPython/3.10.8

Security for min-diffusion 0.0.3

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.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page