prompts.

**Icon Generation**: Produce app icons in various sizes.

To generate an image based on a text prompt, you can use the following command:

一样在背景上硬贴图片的简陋做法。系统会提取原生图片的语义、数据结构和主体，作为 `reference_image` 强制丢给大模型进行**光影级别的自然重绘与融合**，让每一张配图都像好莱坞大片一样

**自带 12+ 高级内置风格**：系统原生内置了极高品质的设计流派。无论是苹果发布会风（`apple_keynote`）、温润知性的 Claude 风（`claude_minimalist`），还是新粗野主义（`neo_brutalism`）、科技液态玻璃（`liquid_glass`）、甚至新中式国潮，只需一句口令即可调用。

**全融合重绘架构 (All-Blend Redraw)**：告别像“狗皮膏药”一样在背景上硬贴图片的简陋做法。系统会提取原生图片的语义、数据结构和主体，作为 `reference_image` 强制丢给大模型进行**光影级别的自然重绘与融合**，让每一张配图都像好莱坞大片一样“长”在你的 PPT 背景里。

All long-running operations execute in background worker threads; the UI stays responsive.

You: "generate a gecko coding at night" │ ▼ ┌──────────────────────┐ │ Skill detects style │ → Cinematic / Photorealistic │ Builds JSON prompt │ → Camera, lens, lighting, film stock, mood... └──────────┬───────────┘ │ ▼ Gemini 3 Pro Image generates with the structured prompt │ ▼ 🖼️ Cinematic quality output

Generate a photo of a cat in a coffee shop

Draw me a dragon in watercolor style

**Consistent caching**: Same parameters always generate the same cache file

Both generate the same cache file, ensuring optimal cache utilization

A majestic golden retriever (subject) in close-up shot (composition) running through a field (action) during golden hour sunset (setting) in photorealistic style (style) with soft bokeh background, 4K resolution (details)

Design a vertical infographic explaining the water cycle...

This project is a carefully curated collection of 1000+ professional-grade Nano Banana Pro prompts covering product photography, UI/UX design, anime creation, infographics, and more.

✅ Detailed usage instructions

in close-up shot (composition)

Character Figure with Packaging

turn this photo into a character figure. Behind it, place a box with the character's image printed on it, and a computer showing the Blender modeling process on its screen. In front of the box, add a round plastic base with the character figure standing on it. Make the PVC material look clear, and set the scene indoors if possible.

Remove the face mask from the woman in the image

This project is a technical proof-of-concept for educational purposes. The workflow shown in the demo is intended to illustrate the capabilities of these AI models. The use of a commercial website and its content is for demonstration purposes only.

👔 **Virtual Try-On**: Multi-item photorealistic try-on with Gemini 2.5 Flash Image (Nano Banana)

3. **Visualize**: Gemini 2.5 Flash Image creates photorealistic try-on images

2. **Google Cloud Project** (optional, for Veo video generation)

4. **Generate Try-On**: AI creates photorealistic image of you wearing the items