JoyCaption is an image captioning Visual Language Model (VLM) being built from the ground up as a free, open, and uncensored model for the community to use in training Diffusion models.
- captioning
- vlm
- joycaption
100,822 visible repositories in the index
2,089–2,112 of 3,834 · Most stars
JoyCaption is an image captioning Visual Language Model (VLM) being built from the ground up as a free, open, and uncensored model for the community to use in training Diffusion models.
:couple: Joint Discriminative and Generative Learning for Person Re-identification. CVPR'19 (Oral) :couple:
Official implementations for paper: Zero-shot Image Editing with Reference Imitation
Official Repository for "Mish: A Self Regularized Non-Monotonic Neural Activation Function" [BMVC 2020]
MICCAI 2019-2026 Open Source Papers
Project page of paper "Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning"
A collection of resources on applications of Transformers in Medical Imaging.
Fluentd daemonset for Kubernetes and it Docker image
StarDist - Object Detection with Star-convex Shapes
[NeurIPS 2025] Direct3D‑S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention
Inpaint Anything extension performs stable diffusion inpainting on a browser UI using masks from Segment Anything.
Streamlit app demonstrating an image browser for the Udacity self-driving-car dataset with realtime object detection using YOLO.
☁️ Kotlin Multiplatform blur and liquid glass effect library for Compose, with GPU-accelerated rendering and CPU fallback for older devices.
React Navigation bindings for react-native-shared-element 💫
Official implementation of HYPIR: Harnessing Diffusion-Yielded Score Priors for Image Restoration (SIGGRAPH 2025)
A script that cleans docker containers, images, volumes, and networks.
Interactively explore unstructured datasets from your dataframe.
[CVPR 2024 Oral, Best Paper Runner-Up] Code for "pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction" by David Charatan, Sizhe Lester Li, Andrea Tagliasacchi, and Vincent Sitzmann
A Processing/Java library for high performance GPU-Computing (GLSL). Fluid Simulation + SoftBody Dynamics + Optical Flow + Rendering + Image Processing + Particle Systems + Physics +...
Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.
:triangular_ruler: Create beautiful generative image patterns from a string in golang.
Detecting Text in Natural Image with Connectionist Text Proposal Network (ECCV'16)
High-Resolution Image Inpainting using Multi-Scale Neural Patch Synthesis
Repository for few-shot learning machine learning projects