diffusers

https://github.com/aiaidada/diffusers

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

✓
CITATION.cff file
Found CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
○
DOI references
○
Academic publication links
○
Academic email domains
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (13.3%) to scientific vocabulary

Last synced: 10 months ago · JSON representation ·

Repository

Basic Info

Host: GitHub
Owner: aiaidada
License: apache-2.0
Language: Python
Default Branch: main
Size: 33.1 MB

Statistics

Stars: 2
Watchers: 2
Forks: 0
Open Issues: 1
Releases: 0

Created about 3 years ago · Last pushed over 2 years ago

Metadata Files

Readme Contributing License Code of conduct Citation

This is HuggingFace diffusers plus a new pipeline called Estim. This new pipeline will generate images very similar to those generated with 1000 steps, by estimating the steps that it won't take instead of just skipping them.

Prepration

You first have to install a few things (This goes if you want to use any of the diffusers pipelines)

bash pip install diffusers transformers accelerate scipy safetensors

Modes

This pipeline has two modes for skipping the steps in diffusion models, the first one is the standard uniform skipping in which you can state the number of steps that you are willing to take. The second one, on the other hand, decides the best number of steps, on the fly, based on different factors, and it can reduce the number of steps to as low as 40.

Generating Images

This is the same as any other pipeline, the only thing is that you can use Estim now.

```python from diffusers import EstimDiffPipeline

pipe = EstimDiffPipeline.from_pretrained("google/ddpm-cat-256").to("cuda")

im = pipe(numinferencesteps= 50 , threshold= args.Skip_threshold , uniform= True ) ```

If you want to test it for different cases, you can also use the mai.py file presented here.

Credits

This is the HuggingFace library and I just added the EstimDiff Pipeline to it.

Citation

bibtex @misc{von-platen-etal-2022-diffusers, author = {Patrick von Platen and Suraj Patil and Anton Lozhkov and Pedro Cuenca and Nathan Lambert and Kashif Rasul and Mishig Davaadorj and Thomas Wolf}, title = {Diffusers: State-of-the-art diffusion models}, year = {2022}, publisher = {GitHub}, journal = {GitHub repository}, howpublished = {\url{https://github.com/huggingface/diffusers}} }

Owner

Login: aiaidada
Kind: user

Repositories: 1
Profile: https://github.com/aiaidada

Citation (CITATION.cff)

cff-version: 1.2.0
title: 'Diffusers: State-of-the-art diffusion models'
message: >-
  If you use this software, please cite it using the
  metadata from this file.
type: software
authors:
  - given-names: Patrick
    family-names: von Platen
  - given-names: Suraj
    family-names: Patil
  - given-names: Anton
    family-names: Lozhkov
  - given-names: Pedro
    family-names: Cuenca
  - given-names: Nathan
    family-names: Lambert
  - given-names: Kashif
    family-names: Rasul
  - given-names: Mishig
    family-names: Davaadorj
  - given-names: Thomas
    family-names: Wolf
repository-code: 'https://github.com/huggingface/diffusers'
abstract: >-
  Diffusers provides pretrained diffusion models across
  multiple modalities, such as vision and audio, and serves
  as a modular toolbox for inference and training of
  diffusion models.
keywords:
  - deep-learning
  - pytorch
  - image-generation
  - diffusion
  - text2image
  - image2image
  - score-based-generative-modeling
  - stable-diffusion
license: Apache-2.0
version: 0.12.1

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Open Source Science