Tag

prompts and images demo of nano banana

Provides differentiable, GPU-accelerated computer-vision operators and geometric building blocks on top of PyTorch; includes 500+ ops, augmentation pipelines, and pre-trained models for detection, matching, and segmentation—suitable for research and production vision pipelines.

Real-time object detection and training toolkit in PyTorch — provides pretrained YOLOv5 models, training and evaluation scripts, and exporters to ONNX/TFLite/CoreML for fast inference and deployment across devices.

Provides modular PyTorch pipelines and tools for training and running diffusion models across image, video, and audio. Ships ready pipelines (Stable Diffusion, img2img, inpainting, video), hardware optimizations, safety checks, and community examples — good for researchers and product teams.

Produces real-time 3D reconstructions from multi-view images using Gaussian splatting, with on-device training and interactive viewing across native desktops, Android, and the browser. Uses WebGPU and the Burn ML framework to ship dependency-free binaries, a CLI, live training visualization, and streaming .ply support.

Generates high-quality, editable 3D assets from text or images and decodes to radiance fields, 3D Gaussians, or textured meshes. Ships pretrained models up to 2B parameters, a 500K asset dataset and training code; best used with image conditioning and a ≥16GB NVIDIA GPU.

Automates idea→script→storyboard→video with a multi-agent pipeline that handles long-script RAG segmentation, reference selection, consistency checks, and parallel shot generation. Best for prototyping end-to-end AI video workflows; depends on external model APIs.

Generates anime-style and other non-photorealistic illustrations from text prompts. A 2B-parameter diffusion base preview trained on millions of anime images (and ~800k non-anime art) and released under a non-commercial license; best used in ComfyUI around ~1MP resolution.

Turns photos into exportable 3D meshes using open-source AI models that run entirely on your GPU. Desktop app for Windows and Linux with an extension system to install local model generators and export common 3D formats.

An open text-to-image generation model built on an 8B Diffusion Transformer that focuses on layout-sensitive, text-heavy, and instruction-following image synthesis. Notable for accurate text rendering, structured/compositional generation (posters, comics), and ability to run on consumer 24GB GPUs when paired with prompt enhancement.

Generates and reconstructs navigable, editable 3D worlds from text, single images, multi-view photos, or video; outputs meshes and Gaussian Splatting assets and includes WorldMirror 2.0 for fast multi-view reconstruction. Suited for research and production pipelines that import assets into engines; requires substantial GPU resources.

Performs feed‑forward streaming 3D reconstruction from image sequences, combining coordinate grounding, dense geometric cues and trajectory memory to correct long‑range drift; uses paged KV‑cache attention for ~20 FPS inference at 518×378 and supports sequences >10,000 frames.