30 秒でわかる
Matthew Berman demonstrates where to select Nano Banana 2.1 in the Google AI Studio playground and tries a portrait prompt. He says the model is paid and praises the detail in the resulting image. The interface and availability shown reflect the video’s October 2026 recording.
- 1Open the playgroundBerman opens Google AI Studio and locates the model selector on the right.
- 2Filter for imagesHe selects the Images filter and chooses Nano Banana 2.1, which he describes as paid.
- 3A portrait promptHe requests a hyperrealistic close-up and comments on the face, hair and jacket details.
ポイント
- In the shown interface, the model selector has an Images filter for finding Nano Banana 2.1.
- Berman says the model is paid in the demonstrated setup.
- The portrait is one example, and Berman’s assessment of its detail is subjective.
チャプターごとに整えた全文を読む
Find and select the model
Berman opens the Google AI Studio playground, selects the Images filter and chooses Nano Banana 2.1. He notes that the model is paid in the shown setup.
To find Nano Banana 2.1 in the Google AI Studio interface shown in October 2026, I open the playground and use the model selector on the right. I choose the Images filter and select Nano Banana 2.1. I note that the model is paid in this setup; the interface, availability and pricing can change.
Generate a portrait
He asks for a hyperrealistic close-up of a woman and examines the resulting detail. His positive assessment is based on this one example.
I ask it to generate a hyperrealistic close-up of a woman. Looking closely at the result, I notice facial texture, wrinkles around the eyes, individual hairs and fibers in the jacket. I find this image impressive, though it is one example rather than a systematic comparison.
同じチャンネルの記事
34:21EN
Matthew Berman· 2026年10月27日Matthew Berman Examines Anthropic’s IPO Filing, AI Growth and GovernanceMatthew Berman, Sam Altman · Forward FutureThe presenter reviews the S-1’s financial metrics, compute strategy and voting structure while questioning the tension between rapid AI development and safety.
0:36ENMatthew Berman· 2026年10月25日Kimi K3.1 and a Rubik’s Cube Solver DemonstrationMatthew Berman · Forward FutureMatthew Berman shows a scrambled virtual cube being solved and gives the Kimi K3.1 test a favorable assessment.
25:50ENMatthew Berman· 2026年10月24日Kimi K3.1 Pro Tested: Strong 3D Demos, Uneven Results and Competitive PricingMatthew Berman · Forward FutureMatthew Berman tests the open-weight model on coding, 3D rendering and visual explanations, then compares benchmark results and prices.
32:20ENMatthew Berman· 2026年10月23日Who Is Local AI For? The Costs, Trade-offs and a Hybrid FutureMatthew Berman · Forward FutureMatthew Berman weighs data control and independence against hardware cost, setup complexity and inference speed.
1:03:37ENMatthew Berman· 2026年10月23日Matthew Berman’s Team Tests Kimi K3.1 on Animation, Games, and ChartsMatthew Berman, Alex, Brian · Forward FutureA live team AMA turns into an informal test of Kimi K3.1, from personal-agent workflows to motion graphics, a browser game, and a benchmark chart.
0:53ENMatthew Berman· 2026年10月22日Sam Altman on AI and the Discovery of New KnowledgeSam Altman · OpenAIAltman expects progress in mathematical discovery to extend to biology, materials and energy.