Spirula Studio

QuerySplat is an open-source implementation for predicting and rendering 3D Gaussian splats from multiple images of a scene while decoupling geometry and appearance representations. Its inference pipeline preprocesses custom images, predicts 3D Gaussians, and uses VGGT-Omega components for camera and depth prediction; optional test-time optimization can refine the result. It can export Gaussian PLY files, predicted input cameras, per-view depth and confidence data, and depth-derived point clouds. The repository requires Linux, an NVIDIA CUDA-capable GPU, and CUDA-enabled PyTorch.

4DAnyone is an open-source generative AI pipeline from ant-research that converts a casual monocular video of one person into synchronized videos from multiple virtual camera views for downstream 3D or 4D Gaussian-splatting reconstruction. It supports configurable camera layouts, including full 360-degree or frontal-arc coverage, multiple pitch layers, adjustable yaw ranges, and flexible view counts. The repository provides inference scripts, automatically downloadable models and examples, motion-recovery outputs, camera metadata, skeleton videos, and generated target-view videos. Input footage should be at least 720p, preferably 1080p, use a 9:16 portrait aspect ratio, contain a single person in a full-body or upper-body shot, include at least 121 frames, and have only mild camera motion.

Unsloth is an open-source local desktop and web tool for running, training, fine-tuning, and deploying language, diffusion, embedding, audio, and vision models. It supports Windows, macOS, Linux, WSL, multi-GPU setups, NVIDIA, AMD, and Intel GPUs, CPUs, and the Vulkan backend. The project is distributed as Unsloth Desktop, Unsloth Studio, and Unsloth Core. It can run local models, provide an OpenAI-compatible API, connect models to agents and MCP tools, perform search and RAG, and offer remote or LAN access. Its training functions cover reinforcement learning, LoRA, QLoRA, full fine-tuning, pretraining, GRPO, DPO, and FP8, with export formats including GGUF, NVFP4, and FP8. The repository claims that its fine-tuning workflows use two times less training time and 70% less VRAM.

Colite is an experimental C++17 structure-from-motion and multi-view stereo system that reconstructs 3D scenes from overlapping images. Its pipeline performs incremental structure-from-motion with support for multiple models, continuation, and Sim(3) merging; feature extraction and matching; PatchMatch stereo with geometric consistency; stereo fusion; meshing; simplification; and texture-atlas generation. It produces COLMAP-compatible sparse models, RGB and normal dense point clouds, Poisson or Delaunay meshes, and textured OBJ models with MTL and atlas PNG files. CPU and optional CUDA implementations are provided for SIFT, descriptor matching, and PatchMatch Stereo, and resumable stage manifests allow processing to continue from saved stages. The repository describes the current build as alpha-quality, primarily developed and tested on Ubuntu 22.04 and WSL2; native Windows builds are not yet validated as a supported release target.

stable-diffusion.cpp is a pure C/C++ inference implementation for diffusion image and video models, based on ggml and designed to work similarly to llama.cpp. It provides a command-line executable for generating and editing images from text or image inputs, with support for model families including Stable Diffusion, SDXL, SD3, FLUX, Qwen Image, Wan, LTX, and other listed image and video models. The project supports PyTorch checkpoints, Safetensors, and GGUF weights, and can convert weights to GGUF or Safetensors. It runs on CPU, CUDA, Vulkan, Metal, OpenCL, and SYCL backends across Linux, macOS, Windows, and Android via Termux; features include LoRA, ControlNet, IP-Adapter, latent-consistency models, VAE tiling, ESRGAN upscaling, quantization, and an embedded web UI. The repository is under active development, so its API and command-line options may change frequently.