Gemini 4 Argon recreates Manhattan photo as oil painting via multi-pass canvas renderer
_philschmid · x · 2026-10-14
Phil Schmid gave Gemini 4 Argon a photo of the Manhattan skyline and asked it to recreate it as an oil painting. Instead of emitting a single image, the model wrote a multi-pass canvas renderer: it starts with broad background strokes, blocks in the buildings and river, then finishes with fine specular highlights on the water. The staged, self-organized rendering approach is a notable demo of the model's image-creation capabilities.
More from Multimodal
- Hollywood sold the dream of anyone making movies—until AI made it real — VraserX · 2026-10-14
- Gemini 4 Argon edits raw assembly to build a new level in a 36-year-old SNES game — venturetwins · 2026-10-14
- VigenFlow runs FLUX and Z-Image locally on AMD Ryzen AI NPU, no GPU needed — Kelsey_test · 2026-10-14
- You can generate custom voices right inside Google AI Studio — kastnerkyle · 2026-10-14
- Gemini 4 Argon scores a perfect mAP@50 100% on lego object detection test — zacharynado · 2026-10-14
- FastH3-Omni Announced: Open Post-Trained Version of MiniMax's Realtime H3 Coming Oct 20 — ostrisai · 2026-10-14