Image URLsisteğe bağlı
The URLs of the images to use for image-to-image generation or image editing.
Historyisteğe bağlı
Previous native user/model turns. Replay a returned conversation's messages unchanged, including thought signatures; the current prompt is appended as a new user turn.
Contextisteğe bağlı
Ordered text, original images, PDF or UTF-8 text documents appended to the current prompt. Uses a native provider. Images count toward the total 14-reference limit.
Return Historyisteğe bağlı
Return reusable native conversations with original image parts and provider thought signatures. Uses a native provider. Each generated conversation is independent; send its messages as history for the next turn.
Thinking Levelisteğe bağlı
Thinking effort. Pro Image supports only high; omit to retain its provider default. An explicit level requests summaries unless include_thoughts overrides it. Thinking cannot be disabled.
Image Passthroughisteğe bağlı
Send reference images and return provider images without resizing or re-encoding, preserving transparency and metadata. Uses direct Google or Vertex APIs; the returned image format may differ from output_format.
Include Thoughtsisteğe bağlı
Whether to include thought summaries. Omit to preserve the existing behavior: an explicit thinking_level requests summaries. Set limit_generations=false to return summary text in description. This does not disable thinking or return intermediate thought images.
Temperatureisteğe bağlı
Sampling temperature. Omit to use the provider default of 1. Explicit values use a direct Google or Vertex API.
Top Pisteğe bağlı
Nucleus sampling probability. Omit to use the provider default of 0.95. Explicit values use a direct Google or Vertex API.
Max Output Tokensisteğe bağlı
Maximum output tokens for the generation. Omit to retain the provider default. Explicit values use a direct Google or Vertex API.
Number of Imagesisteğe bağlı
The number of images to generate.
Seedisteğe bağlı
The seed for the random number generator.
Aspect Ratioisteğe bağlı
The aspect ratio of the generated image, including 1:4, 4:1, 1:8 and 8:1.
Output Formatisteğe bağlı
The format of the generated image.
Safety Toleranceisteğe bağlı
The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.
System Promptisteğe bağlı
Optional system instruction that steers the model's persona and output style across the request. Leave blank to omit; when provided, it is sent as the system instruction to Gemini (or as a system message on OpenAI-compatible providers).
Resolutionisteğe bağlı
The resolution of the image to generate.
Limit Generationsisteğe bağlı
Experimental parameter to limit the number of generations from each round of prompting to 1. Set to `True` to to disregard any instructions in the prompt regarding the number of images to generate.
Enable Web Searchisteğe bağlı
Enable web search for the image generation task. This will allow the model to use the latest information from the web to generate the image.
