Skip to main content

PareDiffusers

Screenshot 2024-01-17 at 10 53 49 PM

parediffusers on PyPI

The library pared down the features of diffusers implemented the minimum function to generate images without using huggingface/diffusers functions to understand the inner workings of the library.

Why PareDiffusers?

PareDiffusers was born out of a curiosity and a desire to demystify the processes of generating images by diffusion models and the workings of the diffusers library.

I will write blog-style notebooks understanding how works using a top-down approach. First, generate images using diffusers to understand the overall flow, then gradually replace code with Pytorch code. In the end, we will write the code for the PareDiffusers code that does not include diffusers code.

I hope that it helps others who share a similar interest in the inner workings of image generation.

Versions

  • v0.0.0: After Ch0.0.0, inprement StableDiffusionPipeline.
  • v0.1.2: After Ch0.1.0, imprement DDIMScheduler.
  • v0.2.0: After Ch0.2.0, imprement UNet2DConditionModel.
  • v0.3.1: After Ch0.3.0, imprement AutoencoderKL.

Table of Contents

Ch0.0.0 PareDiffusersPipeline Open In Colab

version: v0.0.0

  • Generate images using diffusers
  • Imprement StableDiffusionPipeline
  • Imprement DDIMScheduler
  • Imprement UNet2DConditionModel
  • Imprement AutoencoderKL

Ch0.0.1 Test parediffusers Open In Colab

  • Test PareDiffusersPipeline by pip install parediffusers.

Ch0.0.2 Play prompt_embeds Open In Colab

  • Play prompt_embeds, make gradation images by using two prompts.

Ch0.1.0: PareDDIMScheduler Open In Colab

version: v0.1.3

  • Imprement images using diffusers
  • Imprement StableDiffusionPipeline
  • Imprement DDIMScheduler
  • Imprement UNet2DConditionModel
  • Imprement AutoencoderKL

Ch0.1.1: Test parediffusers Open In Colab

  • Test PareDiffusersPipeline by pip install parediffusers.

Ch0.2.0: PareUNet2DConditionModel Open In Colab

version: v0.2.0

  • Generate images using diffusers
  • Imprement StableDiffusionPipeline
  • Imprement DDIMScheduler
  • Imprement UNet2DConditionModel
  • Imprement AutoencoderKL

Ch0.2.1: Test parediffusers Open In Colab

  • Test PareDiffusersPipeline by pip install parediffusers.

Ch0.3.0: PareAutoencoderKL Open In Colab

version: v0.3.1

  • Generate images using diffusers
  • Imprement StableDiffusionPipeline
  • Imprement DDIMScheduler
  • Imprement UNet2DConditionModel
  • Imprement AutoencoderKL

Ch0.3.1: Test parediffusers Open In Colab

  • Test PareDiffusersPipeline by pip install parediffusers.

Usage

import torch
from parediffusers import PareDiffusionPipeline

device = torch.device("cuda")
dtype = torch.float16
model_name = "stabilityai/stable-diffusion-2"

pipe = PareDiffusionPipeline.from_pretrained(model_name, device=device, dtype=dtype)
prompt = "painting depicting the sea, sunrise, ship, artstation, 4k, concept art"
image = pipe(prompt)
display(image)

Contribution

I am starting this project to help me understand the code in order to participate in diffusers' OSS. So, I think there may be some mistakes in my explanation, so if you find any, please feel free to correct them via an issue or pull request.

Metadata

Release files for parediffusers 0.3.2

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

Source distribution (sdist)

Source distribution for parediffusers 0.3.2
File Size Uploaded Provenance Actions
parediffusers-0.3.2.tar.gz 22.8 kB Without provenance Details for parediffusers-0.3.2.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for parediffusers 0.3.2
File Interpreter ABI Platform Actions
parediffusers-0.3.2-py3-none-any.whl Python 3 none any Details for parediffusers-0.3.2-py3-none-any.whl

Total release size: 52.0 kB

Release files / parediffusers-0.3.2.tar.gz

Download URL parediffusers-0.3.2.tar.gz
Size 22.8 kB
Tags Source
SHA-256 checksum
How to use checksums
b36620bcbb4f1b715ec0a84a6cb7556ba4b4c0c69480836b4abae2153cab35f7
BLAKE2b-256 checksum
How to use checksums
6ca25ca58d685964c2e9f6ca8aff7fbd0b19df3455721242baf257552236b54e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.9.5

Release files / parediffusers-0.3.2-py3-none-any.whl

Download URL parediffusers-0.3.2-py3-none-any.whl
Size 29.1 kB
Tags Python 3
SHA-256 checksum
How to use checksums
de504f46f03e2810da15401f59fbca8e9ec38f9dfa675cf8a17fa7d47c23c85c
BLAKE2b-256 checksum
How to use checksums
9b4349ec19ae4e4579a67093ef31e8e1d2ab0c6598330b05379a96f489c1fa10
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.9.5

Security for parediffusers 0.3.2

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