AI 提示詞模型
按生成模式、输出类型、参数和示例浏览模型提示词。
Veo 3.1
Veo 3.1 is Google's state-of-the-art video generation model from DeepMind, capable of creating high-fidelity videos up to 4K resolution with natively generated audio from text prompts and reference images.
Seedance 2.0
ByteDance
Seedance 2.0 is ByteDance's revolutionary multi-modal AI video generation model. It supports text, image, video, and audio inputs for cinematic video creation with director-level control, native audio synchronization, consistent characters, and realistic motion.
Nano Banana 2
Google's latest state-of-the-art AI image generation and photo editing model (Gemini 3.1 Flash Image). Delivers Pro-level reasoning, subject/character consistency, accurate text rendering, and production-ready 4K visuals at Flash speed.
GPT Image 2
OpenAI
OpenAI 最先進的圖像生成與編輯模型，可產出照片級真實感的輸出，具備近乎完美的文字渲染、多語言支援、精確的指令遵循能力，以及彈性的高解析度功能，原生支援高達 2K（可擴展至 4K）。