SaaSHub helps you find the best software and product alternatives Learn more →
Top 23 Python Pytorch Projects
-
Link (Github): https://github.com/AUTOMATIC1111/stable-diffusion-webui
-
Stream
Stream - Scalable APIs for Chat, Feeds, Moderation, & Video. Stream helps developers build engaging apps that scale to millions with performant and flexible Chat, Feeds, Moderation, and Video APIs and SDKs powered by a global edge network and enterprise-grade infrastructure.
-
transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
python3.12 -m venv new_venv_312 source new_venv_312/bin/activate pip install --upgrade pip pip install https://github.com/huggingface/transformers/archive/main.zip torchaudio peft soundfile torchcodec ### and also pip install librosa
-
ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Project mention: Nvidia DGX Spark: great hardware, early days for the ecosystem | news.ycombinator.com | 2025-10-15It's very likely worth trying ComfyUI on it too: https://github.com/comfyanonymous/ComfyUI
Installation instructions: https://github.com/comfyanonymous/ComfyUI#nvidia
It's a webUI that'll let you try a bunch of different, super powerful things, including easily doing image and video generation in lots of different ways.
It was really useful to me when benching stuff at work on various gear. ie L4 vs A40 vs H100 vs 5th gen EPYC cpus, etc.
-
nn
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
-
Keras 3 multi-backend
-
Project mention: DeepSeek-OCR: When a Picture Is Actually Worth 10 Fewer Tokens | dev.to | 2025-10-26
One gotcha: if you're using vLLM, you'll need the 0.8.5 wheel for CUDA 11.8. Download it from vLLM releases before installing.
-
-
InfluxDB
InfluxDB – Built for High-Performance Time Series Workloads. InfluxDB 3 OSS is now GA. Transform, enrich, and act on time series data directly in the database. Automate critical tasks and eliminate the need to move data externally. Download now.
-
Project mention: Labellerr YOLOv8: Cars and Number Plate Detection — Practical, Step-by-Step | dev.to | 2025-11-05
YOLOv8(by Ultralytics) is one of the most widely used state-of-the-art object detection models. It is known for delivering high accuracy, while still being fast enough for real-time detection.
-
Project mention: Show HN: Using YOLO to Detect Office Chairs in 40M Hotel Photos | news.ycombinator.com | 2025-01-25
They did it on their own computer. https://github.com/ultralytics/ultralytics
-
Project mention: 2025 Voice AI Guide: How to Make Your Own Real-Time Voice Agent (Part-1) | dev.to | 2025-09-20
XTTS-v2 — Zero-shot voice cloning, 17 languages, streaming support
-
DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
-
Ray
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
Not currently, but it is being worked on https://github.com/ray-project/ray/issues/53976.
-
-
MockingBird
🚀AI拟声: 5秒内克隆您的声音并生成任意语音内容 Clone a voice in 5 seconds to generate arbitrary speech in real-time
-
Project mention: Show HN: Plug-and-play Python utils for any computer-vision pipeline | news.ycombinator.com | 2025-07-21
-
pytorch-image-models
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
Project mention: This PR content was generated automatically using cover-agent | news.ycombinator.com | 2024-11-19Those are some pointless tests.
E.g. test_activation_stats_functions [1] that just checks that the returned value is a float, and that it can take random numbers as input.
test_get_state_dict_custom_unwrap [2] is probably supposed to check that custom_unwrap is invoked, but since it doesn't either record being called, or transform its input, the assertions can't actually check that it was called.
[1] https://github.com/huggingface/pytorch-image-models/pull/233...
[2] https://github.com/huggingface/pytorch-image-models/pull/233...
-
Real-ESRGAN
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
-
I haven’t tried it myself, but NLLB-200 has various sizes going down to 600M params:
https://github.com/facebookresearch/fairseq/tree/nllb/
If running locally is too difficult, you can use llm to access hosted models too.
-
-
diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
Diffusers Documentation
-
There certainly are issues on Linux as well. The Detectron2 library alone has several hundred issues related to incorrect versions of something: https://github.com/facebookresearch/detectron2/issues
The mmdetection library (https://github.com/open-mmlab/mmdetection/issues) also has hundreds of version-related issues. Admittedly, that library has not seen any updates for over a year now, but it is sad that things just break and become basically unusable on modern Linux operating systems because NVIDIA can't stop breaking backwards and forwards compatibility for what is essentially just fancy matrix multiplication.
-
pytorch-lightning
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
-
EasyOCR
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
NOTE:
The open source projects on this list are ordered by number of github stars.
The number of mentions indicates repo mentiontions in the last 12 Months or
since we started tracking (Dec 2020).
Python Pytorch discussion
Python Pytorch related posts
-
Deep universal probabilistic programming with Python and PyTorch
-
Notes on the margins
-
Labellerr YOLOv8: Cars and Number Plate Detection — Practical, Step-by-Step
-
Using “ibm-granite/granite-speech-3.3–8b” 🪨 for ASR
-
Show HN: City2Graph – Spatial Network for GNN in Python
-
DeepSeek-OCR: When a Picture Is Actually Worth 10 Fewer Tokens
-
Installing FFCV and Fastxtend on Windows with Micromamba and MSVC
-
A note from our sponsor - SaaSHub
www.saashub.com | 16 Nov 2025
Index
What are some of the best open-source Pytorch projects in Python? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | stable-diffusion-webui | 158,141 |
| 2 | transformers | 152,508 |
| 3 | ComfyUI | 93,674 |
| 4 | nn | 64,273 |
| 5 | Keras | 63,551 |
| 6 | vllm | 62,592 |
| 7 | Real-Time-Voice-Cloning | 58,832 |
| 8 | yolov5 | 56,018 |
| 9 | ultralytics | 48,563 |
| 10 | TTS | 43,441 |
| 11 | DeepSpeed | 40,641 |
| 12 | Ray | 39,825 |
| 13 | GFPGAN | 37,167 |
| 14 | MockingBird | 36,745 |
| 15 | supervision | 35,881 |
| 16 | pytorch-image-models | 35,766 |
| 17 | Real-ESRGAN | 33,058 |
| 18 | fairseq | 31,949 |
| 19 | pytorch-tutorial | 31,911 |
| 20 | diffusers | 31,604 |
| 21 | mmdetection | 31,579 |
| 22 | pytorch-lightning | 30,432 |
| 23 | EasyOCR | 27,968 |
Sponsored
Stream - Scalable APIs for Chat, Feeds, Moderation, & Video.
Stream helps developers build engaging apps that scale to millions with performant and flexible Chat, Feeds, Moderation, and Video APIs and SDKs powered by a global edge network and enterprise-grade infrastructure.
getstream.io