Nano Banana Lite

An AI image-generation and image-editing model from Google, also known as Gemini 3 Pro Image. It generates images from text prompts and can create or modify specific visual compositions, such as depicting a model holding a supplied object.

Nano Banana is the informal name for Google's Gemini 2.5 Flash Image generative AI model, used to create and edit images from text and image prompts. It supports applications such as product concepts, landscape visualizations, virtual staging, and promotional graphics.

Omni Flash is an AI model available through Google's Gemini Interactions API for programmatically creating and editing videos and building generative-media applications.

Google AI Edge Gallery is an app for downloading and running Gemma models locally on Android and iOS devices. It supports image description, multilingual audio transcription, on-device function calling, and built-in skills such as games, haiku generation, weather queries, and calendar events. Inference runs on the device, using supported hardware accelerators rather than requiring an API call or sending data to a remote service. Google describes AI Edge as its platform for deploying machine-learning solutions across mobile, web, and embedded applications.

FreeVideo is an open-source local inference engine and ComfyUI plugin for generating videos with the MiniMax H3 model on consumer hardware. Built on OpenVDN's eight-step VDN-H3 model and Video DeltaNet's hybrid attention, it adapts weight placement, compute precision, attention kernels and acceleration to available hardware. Weight streaming, asynchronous prefetching and chunked computation reduce peak memory use, with the project reporting operation on systems with as little as 8 GB of VRAM and 16 GB of RAM. It accepts text prompts, first and last frames, and image, video and audio references, and supports MiniMax H3 LoRAs, two-pass sampling, batch generation, four quality levels and preview-first generation. Windows and Apple silicon launchers configure ComfyUI, the runtime and models, while Linux supports setup through a shell script and command-line generation. The code is licensed under Apache License 2.0; the model weights use the MiniMax H3 Community License.