---
id: spandrel
version: "0.4.2"
license: MIT
license_treatment: permissive
maintenance: active
---

# spandrel — Give your project support for a variety of PyTorch model architectures, including auto-detecting model architecture from just .pth files. spandrel gives you arch support.

License: permissive · Maintenance: active · Downloads: 1.6M/mo

## What it is and what it does

Spandrel is a PyTorch model loading library that automatically detects model architecture and hyperparameters from saved model files, then wraps them in a unified interface for inference. It originated from the chaiNNer project and now serves as a central package for architecture support across the community. The library focuses on image models (super-resolution, restoration) but is designed to be extensible for other architectures.

You provide a path to a model file (.pth, .pt, .ckpt, or .safetensors), and Spandrel identifies the architecture, returns a ModelDescriptor object with metadata, and lets you call the model directly. It does not handle image-to-tensor conversion or other preprocessing—you manage that yourself. The base package includes only permissive-license architectures (MIT, Apache 2.0, public domain); restrictive-license models require the optional spandrel_extra_arches package.

Use it for:

- Load and run ESRGAN, SwinIR, HAT, or other super-resolution models without manually implementing architecture detection.
- Build an image processing pipeline that supports multiple model formats and architectures through a single interface.
- Integrate community-trained PyTorch models into an application without hardcoding architecture-specific loading logic.
- Extend model support by contributing new architectures to a shared, centralized package rather than maintaining per-project implementations.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Spandrel loads and runs pre-trained PyTorch models by automatically detecting their architecture from model files and providing a unified interface for inference.

Yes, if you work with pre-trained PyTorch models and want to avoid architecture-specific loading boilerplate. The library is actively maintained, has low install friction, uses a permissive license, and supports a wide range of image models. Start with the base package; add spandrel_extra_arches only if you need non-commercial or restrictive-license architectures. Note that you must handle tensor preparation yourself—this is not an end-to-end inference library.

## Install

pip install spandrel
uv add spandrel
poetry add spandrel

## Installing spandrel

Before you install: Low install friction with a pure-Python wheel. Maintenance is active with a recent release (174 days ago). Requires Python 3.10 or later and depends on torch, torchvision, and several other standard ML libraries.

License in practice: MIT license (permissive) means you can use this freely in commercial and private projects without restriction or attribution requirement.

Quickstart:

pip install spandrel

from spandrel import ImageModelDescriptor, ModelLoader
import torch

model = ModelLoader().load_from_file("path/to/model.pth")
assert isinstance(model, ImageModelDescriptor)
model.cuda().eval()

with torch.no_grad():
    output = model(input_tensor)

Requires Python 3.10+. Torch and torchvision must be installed; they are not bundled. The model descriptor does not automatically convert images to tensors—you must handle tensor preparation yourself.

Verify before relying:

- Whether the package has comprehensive documentation beyond the GitHub README for all supported architectures.
- Performance characteristics when loading very large model files or running inference on CPU vs GPU.
- Whether spandrel_extra_arches is required for your specific model architecture or if the base package suffices.

## Package facts

- License: MIT (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 1.6M/month (top 5,000 on PyPI)
- Known vulnerabilities: none known

## Tags

pytorch model loader, auto-detect model architecture, load pth files, pytorch model inference, model architecture detection, unified pytorch interface, pre-trained model support, pytorch-models, model-loading, image-restoration

[View on SkillFed](https://skillfed.io/packages/spandrel) · [View on PyPI](https://pypi.org/project/spandrel/)