Composable sampling functions for diffusion models
Project description
Skrample 0.5.3
Composable sampling functions for diffusion models
Status
Mostly complete for common models, superseding all diffusers features in quickdif
Quickstart
Fastest way to jump in is examples. The classes and functions themselves have docstrings and type hints, so it's recommended to make liberal use of your IDE or python help()
Feature Flags
beta-schedule->scipy: For theBeta()schedule modifierbrownian-noise->torchsde: For theBrownian()noise generatorcdf-schedule->scipy: For theSigmoidCDF()schedulediffusers-wrapper->torch: For thediffusersintegration modulepytorch->torch: For thepytorchmodulepytorch.noise: Custom generators
all: All of the abovedev: For runningtests/
Samplers
- Euler
- DPM
- 1st order, 2nd order, 3rd order
- SDE
- Adams/IPNDM
- UniP & UniPC
- N order, limited to 9 for stability
- Custom solver via other SkrampleSampler types
- SPC
- Basic fully customizable midpoint corrector
Schedules
- Linear
- Scaled
uniformflag, AKA"trailing"in diffusers
- SigmaCDF
- ZSNR
Schedule modifiers
- Karras
- Exponential
- FlowShift
- Beta
- Hyper
Predictors
- Epsilon
- Velocity / vpred
- Flow
Noise generators
- Random
- Brownian
- Offset
- Pyramid
Integrations
Diffusers
- Compatibility for pipelines
- SD1
- SDXL
- SD3
- Flux
- Import from config
- Sampler
- Schedule
- Predictor
- Manage state
- Steps
- Higher order
- Generators
- Config as presented
Implementations
quickdif
My diffusers cli quickdif has full support for all major Skrample features, allowing extremely fine-grained customization.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file skrample-0.5.3.tar.gz.
File metadata
- Download URL: skrample-0.5.3.tar.gz
- Upload date:
- Size: 23.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.10.4 {"installer":{"name":"uv","version":"0.10.4","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Arch Linux","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
7210ab5d60743e9c11f39e0284c92c27088849b254e0729e1b4ce4c31c8df57e
|
|
| MD5 |
743a15cda251281f1027cd63f498a4a5
|
|
| BLAKE2b-256 |
0f78fa72036c096631a28a2126aded8cd023c3d3258a2f902d1b8c5e682eb989
|
File details
Details for the file skrample-0.5.3-py3-none-any.whl.
File metadata
- Download URL: skrample-0.5.3-py3-none-any.whl
- Upload date:
- Size: 28.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.10.4 {"installer":{"name":"uv","version":"0.10.4","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Arch Linux","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
dc13ce7dd5b5d9b635652569fa01c8bab5ad96052cfb523d694f447928a07dab
|
|
| MD5 |
a675e825bddd755a7b5b877fa7b40b36
|
|
| BLAKE2b-256 |
edfa0aeb2c66bcd11764ba168b8527288bf888b50b7c14f835e9a194ae55686a
|
