Search Results for "pixels"
Sort By:
Showing 31 open source projects for "pixels"
View related business solutions-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
$300 Free Credits to Build on Google CloudStart your next project with $300 in free Google Cloud credit. Spin up VMs, run containers, query petabytes in BigQuery, or build agents with Gemini Enterprise Agent Platform. Once your credits are used, keep building with 20+ always-free tier products including Compute Engine, Cloud Storage, GKE, and Cloud Run functions. No commitment required—just sign up and start building.
-
1
Ark Pixel Font
Ark pixel font - Open source Pan-CJK pixel font
...Among them, 12 pixels are the main development target. 10, 16 pixels are experimental. Efforts are currently underway to achieve the availability of 12 pixels under the GB2312 character set. We have a temporary interim solution available for production until the full font is available, check out the Stitcher Pixel Font project. -
2
Perfect Pixel
Refine and quantize messy AI pixel art into clean, perfect pixels
...It tackles a common problem with AI pixel art: edges that look pixelated at first glance but are not actually aligned to a coherent pixel grid, which causes shimmer, blur, and uneven block sizes when you zoom in. The tool analyzes an image to infer the intended grid size, then refines and quantizes the artwork so pixels snap into consistent cells and the final result looks crisp and intentional. This makes it useful for game developers, sprite artists, and hobbyists who want to use AI-assisted ideation without shipping “almost pixel art” assets. It is designed to be easy to slot into an existing pipeline, whether you are batch-processing images or cleaning up a few key assets for a project. -
3
Video-subtitle-remover (VSR)
AI tool that removes hardcoded subtitles and text from videos locally
Video Subtitle Remover is an AI-based application designed to remove hardcoded subtitles from videos and generate new files without the embedded text. Video Subtitle Remover analyzes video frames and detects subtitle regions, then replaces the removed areas using an AI algorithm that fills the space with reconstructed visual content. This process aims to maintain the original resolution and visual continuity of the video after subtitle removal. It allows users to define a specific subtitle... -
4
VOID
Video Object and Interaction Deletion
VOID is an advanced AI video processing system developed by Netflix that focuses on removing objects from videos while preserving the physical and visual realism of the surrounding environment. Unlike traditional inpainting methods that only erase pixels or simple artifacts, VOID models the full interaction dynamics between objects and their environment, including shadows, reflections, and even physical consequences such as movement or balance changes. Built on top of transformer-based architectures and fine-tuned for video inpainting tasks, the system uses interaction-aware mask conditioning to ensure temporal consistency across frames. ... -
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
5
Pixal3D
Pixel-Aligned 3D Generation from Images
...It addresses a key weakness in image-to-3D generation: many models produce plausible 3D shapes but fail to preserve pixel-level faithfulness to the original image. Pixal3D improves this by explicitly lifting image features into 3D through back-projection, creating clearer correspondences between the input pixels and the generated asset. The system is designed to produce detailed geometry and physically based rendering textures rather than only coarse 3D approximations. It is useful for researchers, 3D artists, game asset workflows, and generative AI experiments focused on image-conditioned reconstruction. Its main value is combining generative flexibility with reconstruction-like visual fidelity. -
6
folderify
Generate pixel-perfect macOS folder icons in the native style
...There is currently no simple way to set an icon that will automatically switch between light and dark when you switch the entire OS. You can only assign one version of an icon to a folder. Dark color scheme is only supported for macOS 11.0 (and later) right now. Make sure the corner pixels of the mask image are transparent. They are used for empty margins. -
7
SAHI
A lightweight vision library for performing large object detection
...Here comes the SAHI to help developers overcome these real-world problems with many vision utilities. Detection of small objects and objects far away in the scene is a major challenge in surveillance applications. Such objects are represented by small number of pixels in the image and lack sufficient details, making them difficult to detect using conventional detectors. In this work, an open-source framework called Slicing Aided Hyper Inference (SAHI) is proposed that provides a generic slicing aided inference and fine-tuning pipeline for small object detection. -
8
JEPA
PyTorch code and models for V-JEPA self-supervised learning from video
JEPA (Joint-Embedding Predictive Architecture) captures the idea of predicting missing high-level representations rather than reconstructing pixels, aiming for robust, scalable self-supervised learning. A context encoder ingests visible regions and predicts target embeddings for masked regions produced by a separate target encoder, avoiding low-level reconstruction losses that can overfit to texture. This makes learning focus on semantics and structure, yielding features that transfer well with simple linear probes and minimal fine-tuning. ... -
9
vJEPA-2
PyTorch code and models for VJEPA2 self-supervised learning from video
VJEPA2 is a next-generation self-supervised learning framework for video that extends the “predict in representation space” idea from i-JEPA to the temporal domain. Instead of reconstructing pixels, it predicts the missing high-level embeddings of masked space-time regions using a context encoder and a slowly updated target encoder. This objective encourages the model to learn semantics, motion, and long-range structure without the shortcuts that pixel-level losses can invite. The architecture is designed to scale: spatiotemporal ViT backbones, flexible masking schedules, and efficient sampling let it train on long clips while remaining stable. ... -
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
10
Shopne-Arcade
A frontend for GnGeo emulator written purely in Python
Shopne Arcade is a front-end application designed to easily play Neo Geo system games on PC. It's interface is compatible for screens with low resolution such as 640x480 pixels. It lets users play Neo Geo system games from one interface where users will be able pick different game play experience settings such as Neo Geo games video resolutions, audio sampling rates, etc. Shopne Arcade is written in pure Python language without any external dependencies making it portable across various Linux Distributions. -
11
FLUX.1 Krea
Powerful open source image generation model
...It is a rectified-flow model distilled from the original Krea 1, providing enhanced sampling efficiency through classifier-free guidance distillation. The model supports generation at resolutions between 1024 and 1280 pixels with recommended inference steps between 28 and 32 for optimal balance of speed and quality. FLUX.1 Krea is fully compatible with the FLUX.1 architecture, making it easy to integrate into existing workflows and pipelines. The repository offers easy-to-use inference scripts and a Jupyter Notebook example to facilitate quick experimentation and adoption. ... -
12
Qwen-VL
Chat & pretrained large vision language model
Qwen-VL is Alibaba Cloud’s vision-language large model family, designed to integrate visual and linguistic modalities. It accepts image inputs (with optional bounding boxes) and text, and produces text (and sometimes bounding boxes) as output. The model variants (VL-Plus, VL-Max, etc.) have been upgraded for better visual reasoning, text recognition from images, fine-grained understanding, and support for high image resolutions / extreme aspect ratios. Qwen-VL supports multilingual inputs... -
13
Oblivion-Inverse
Open source e-mail tracker made with Flask, setup & run in 10 minutes
Oblivion-Inverse is a simple, free & open source e-mail tracking solution which based on the usage of web beacons or tracking pixels. Build with Flask and setup under 10 minutes on your own production environment. Designed to provide information about the email read status, time, IP address of the recipient's device or proxy, as well as request headers such as the user-agent, which can reveal details about the recipient's browser, operating system, and device. -
14
Aphantasia
CLIP + FFT/DWT/RGB = text to image/video
...Generating massive detailed textures, a la deepdream, fullHD/4K resolutions and above, various CLIP models (including multi-language from SBERT), continuous mode to process phrase lists (e.g. illustrating lyrics), pan/zoom motion with smooth interpolation. Direct RGB pixels optimization (very stable) depth-based 3D look (courtesy of deKxi, based on AdaBins), complex queries: text and/or image as main prompts, separate text prompts for style and to subtract (avoid) topics. Starting/resuming process from saved parameters or from an image. -
15
iJEPA
Official codebase for I-JEPA
i-JEPA (Image Joint-Embedding Predictive Architecture) is a self-supervised learning framework that predicts missing high-level representations rather than reconstructing pixels. A context encoder sees visible regions of an image and predicts target embeddings for masked regions produced by a slowly updated target encoder, focusing learning on semantics instead of texture. This objective sidesteps generative pixel losses and avoids heavy negative sampling, producing features that transfer strongly with linear probes and minimal fine-tuning. ... -
16
Fashion-MNIST
A MNIST-like fashion product database
...It was designed as a direct replacement for the original MNIST handwritten digits dataset, maintaining the same structure and image size so that researchers could easily switch datasets without modifying their experimental pipelines. The dataset consists of 70,000 images in total, with 60,000 examples used for training and 10,000 reserved for testing. Each image has a resolution of 28 by 28 pixels and belongs to one of ten clothing classes, making it suitable for evaluating classification models. Because the dataset represents real-world objects rather than handwritten digits, it offers a more challenging benchmark for testing machine learning algorithms. -
17
DensePose
A real-time approach for mapping all human pixels of 2D RGB images
...DensePose is widely used in augmented reality, motion capture, virtual try-on, and visual effects applications because it enables real-time 3D human mapping from 2D inputs. The model architecture builds on Mask R-CNN, using additional regression heads to predict UV coordinates that map image pixels to 3D surfaces. -
18
Image GPT
Large-scale autoregressive pixel model for image generation by OpenAI
Image-GPT is the official research code and models from OpenAI’s paper Generative Pretraining from Pixels. The project adapts GPT-2 to the image domain, showing that the same transformer architecture can model sequences of pixels without altering its fundamental structure. It provides scripts to download pretrained checkpoints of different model sizes (small, medium, large) trained on large-scale datasets and includes utilities for handling color quantization with a 9-bit palette. ... -
19
Consistent Depth
We estimate dense, flicker-free, geometrically consistent depth
Consistent Depth is a research project developed by Facebook Research that presents an algorithm for reconstructing dense and geometrically consistent depth information for all pixels in a monocular video. The system builds upon traditional structure-from-motion (SfM) techniques to provide geometric constraints while integrating a convolutional neural network trained for single-image depth estimation. During inference, the model fine-tunes itself to align with the geometric constraints of a specific input video, ensuring stable and realistic depth maps even in less-constrained regions. ... -
20
PixelCNN
Code for the paper "PixelCNN++: A PixelCNN Implementation..."
PixelCNN is the official implementation from OpenAI of the autoregressive generative model described in the paper Conditional Image Generation with PixelCNN Decoders. It provides code for training and evaluating PixelCNN models on image datasets, focusing on conditional image modeling where pixels are generated sequentially based on the values of previously generated pixels. The repository demonstrates how to apply masked convolutions to enforce autoregressive dependencies and achieve tractable likelihood-based training. It also includes scripts for reproducing key experimental results from the paper, such as conditional sampling on datasets like CIFAR-10. ... -
21
imgaug
Image augmentation for machine learning experiments
...Affine transformations, perspective transformations, contrast changes, gaussian noise, dropout of regions, hue/saturation changes, cropping/padding, blurring, etc. Rotate image and segmentation map on it by the same value sampled. Convert keypoints to distance maps, extract pixels within bounding boxes from images, clip polygon to the image plane, etc. Scale segmentation maps, average/max pool of images/maps, pad images to aspect ratios (e.g. to square them). Draw heatmaps, segmentation maps, keypoints, bounding boxes, etc. -
22
PyTorch pretrained BigGAN
PyTorch implementation of BigGAN with pretrained weights
An op-for-op PyTorch reimplementation of DeepMind's BigGAN model with the pre-trained weights from DeepMind. This repository contains an op-for-op PyTorch reimplementation of DeepMind's BigGAN that was released with the paper Large Scale GAN Training for High Fidelity Natural Image Synthesis. This PyTorch implementation of BigGAN is provided with the pretrained 128x128, 256x256 and 512x512 models by DeepMind. We also provide the scripts used to download and convert these models from the... -
23
Neural Photo Editor
A simple interface for editing natural photos
...The project implements the system described in the research paper Neural Photo Editing with Introspective Adversarial Networks, which introduces a generative model capable of modifying images in semantically meaningful ways. Instead of editing images by directly manipulating pixels, the software allows users to influence changes in the latent space of a trained generative model. This approach enables large and coherent modifications to images while preserving visual realism. The system relies on an Introspective Adversarial Network, a hybrid architecture combining elements of variational autoencoders and generative adversarial networks to improve reconstruction accuracy and generative quality. -
24
Universe
Software for measuring and training an AI's general intelligence
...It does this by packaging the program into a Docker container, and presenting the AI with the same interface a human uses: sending keyboard and mouse events, and receiving screen pixels. Our initial release contains over 1,000 environments in which an AI agent can take actions and gather observations. -
25
Simple xbm Image Editor
XBM images are displayed in actual size and in an enlarged edit grid.
...Background and foreground color selection is provided in order to experiment with colors for your application. The editor can display very large .xbm files in their actual size but the maximum bitmap size that can be edited is 2500 pixels. This limit is arbitrary and can easily be changed, but bitmap edit grid loading and, in particular, garbage collection become quite slow if the limit is a lot more than 2500 pixels. The gridMax constant sets max size.
