Reference-guided video from prompt plus optional images, videos, and audio references.

Nano Banana 2 Edit is an image editing model that enables blending multiple images, maintaining character consistency, targeted transformations using natural language, and leveraging world knowledge for precise edits.

Anthropic's most advanced model, excelling in coding, agentic workflows, computer use, reasoning, math, and domain expertise in finance, law, STEM.

Edit videos via text instructions or reference images with style transfer, up to 1080p, and flexible audio handling.

Animates images into videos up to 15s at 1080p with improved motion, scene fidelity, and optional end-frame or audio guidance.

Reference-guided video generation with character consistency, multi-character support, and multi-shot narration up to 1080p.

Text-to-video with improved quality, multi-shot generation, up to 1080p, 2-15s duration, and optional audio.

Image-to-video with optional start-to-end frame transitions, flexible duration and aspect ratio, resolution up to 720p, and optional synchronized audio.

Text-to-video with flexible duration and aspect ratio, resolution up to 720p, and optional synchronized audio.

Flagship 31B dense multimodal model supporting text, image, and video input with 256K context window. Achieves competitive performance with much larger models.