Tag

prompts and images demo of nano banana

An open-source repository from Stability AI that collects implementations, training configs, demos and inference scripts for multiple generative models (e.g. SDXL, SV3D, SV4D, SV4D 2.0, Stable Video Diffusion). It is modular and config-driven, provides sampling/demo scripts, training examples, and references to model weights on Hugging Face.

olmOCR is an open-source toolkit from the Allen Institute for AI (AI2) / AllenNLP team for converting image-based documents (PDF, PNG, JPEG) into clean, readable plain text or Markdown. It uses a 7B-parameter vision-language model to handle complex layouts, equations, tables and handwriting, removes headers/footers, and outputs text in natural reading order. The repo includes a processing pipeline, benchmark suite (olmOCR-Bench), training and RL components, Docker images, and an online demo. Licensed under Apache 2.0.

SAM 3 (Segment Anything with Concepts) is Meta's open-vocabulary foundation model for promptable image and video segmentation and tracking. It supports text and visual prompts (points, boxes, masks, exemplars) to detect, segment and track all instances matching a concept. SAM 3 introduces a presence token, a decoupled detector–tracker architecture, and is trained with a massive automatically annotated concept dataset (SA-Co). The GitHub repository provides code for inference, finetuning, example notebooks, and links to model checkpoints (Hugging Face access required).

Qwen-Image is an open-source image foundation model family (20B MMDiT) from QwenLM/Alibaba that excels at complex text rendering and precise image editing. It provides text-to-image and image-editing pipelines, HuggingFace/Diffusers support, multiple released checkpoints (e.g. Qwen-Image-2512 / Qwen-Image-Edit-2511), community acceleration tooling and LoRA integrations. Licensed under Apache-2.0.

A demo repository from Anthropic showcasing the Claude Agent SDK. It contains multiple example applications (Email Agent, Excel Demo, Hello World, Research Agent) that illustrate how to build agentic, multi-agent, and AI-assisted workflows with Claude. Intended for local development and learning; not for production. Requires Bun or Node.js 18+ and an Anthropic API key.