Generative
- K2G-D-1Nano Banana (Gemini 2.5 Flash Image)Sep 5, 2026
Study note on "Nano Banana", the community name for Google's Gemini 2.5 Flash Image (announced 2025-08-26). A natively multimodal image generation + editing model built into the Gemini LLM (not a standalone diffusion model): multi-image blending, character consistency, natural-language local edits, world-knowledge grounding, SynthID watermark. Product release, no paper; note primers what "native multimodal image generation" means versus a diffusion model.
- K2G-D-2Nano Banana Pro (Gemini 3 Pro Image)Sep 5, 2026
Study note on "Nano Banana Pro", Google's Gemini 3 Pro Image (preview 2025-11-20, general availability 2026-05-28). The successor to Nano Banana, built on the Gemini 3 Pro reasoning model: best-in-class in-image text rendering (multilingual), blend up to 14 images, identity of up to 5 people, 1K/2K output (4K in preview), fine-grained camera/lighting/focus controls, SynthID + visible watermark. Product release, no paper; note contrasts it with the original Nano Banana.
- K2G-D-3Vision Banana: Image Generators are Generalist Vision LearnersSep 6, 2026
Paper note on "Image Generators are Generalist Vision Learners" (Vision Banana, arXiv:2604.20329, Google DeepMind). Instruction-tunes the Nano Banana Pro image generator, at a very low data-mix ratio, to solve visual-understanding tasks by generating the answer as an RGB image (segmentation masks as colored images, depth/normals as false-color). One shared set of weights, no task-specific heads or losses; reaches SOTA-level results on 2D segmentation, monocular metric depth, and surface normals while keeping its generation ability. Thesis: image-generation pretraining plays the role LLM pretraining plays for language.