Image & video

The Image & video page — the AI Models panel — is where you choose which model powers each generation type. Open Configure → Image & video. Your choices are saved to your account and synced across devices.

The AI Models panel listing Reasoning, Image Generation, Video Generation, and Music Generation, each with its current model.
AI Models — the model behind each type of media, in one place.

The four generation types

Each row shows the type and its current model; rows with a open a picker.

  • ReasoningAuto — we pick the best model for each task. This is the model behind Zinley's thinking; manage it in depth under Performance.
  • Image Generation — the model for still images (e.g. Gemini 3.1 Flash Image). Click the row () to change it.
  • Video Generation — the model for video (e.g. Veo 3 Fast). Click the row () to change it.
  • Music Generation — the model for music (e.g. Suno v5.5).

Choosing an image model

Click Image Generation to open Select Image Model. Each option lists its rough credit cost per image, so you can trade quality against cost; the current pick is marked DEFAULT.

The Select Image Model dialog listing Gemini and GPT image models with credit costs, Gemini 3.1 Flash Image marked Default.
Select Image Model — trade quality against credits per image.
Model Cost Notes
Gemini 3 Pro Image ~27 credits / image Nano Banana Pro — highest quality, best for text and fine detail.
Gemini 3.1 Flash Image (default) ~14 credits / image Nano Banana 2 — fast, high-quality generation.
Gemini 3.1 Flash Lite Image ~7 credits / image Nano Banana Lite — fastest and most efficient.
GPT Image 2 ~11 credits / image OpenAI's latest — state-of-the-art generation and editing.
GPT Image 1.5 ~7 credits / image Advanced image generation.

Select an option and it becomes the model for every image you generate. Close with .

Choosing a video model

Click Video Generation to open Select Video Model. The current pick is marked RECOMMENDED.

The Select Video Model dialog listing Veo 3, Veo 3.1, and Veo 3 Fast, with Veo 3 Fast marked Recommended.
Select Video Model — quality versus tokens per clip.
Model Notes
Veo 3 Higher quality, more tokens.
Veo 3.1 Latest version with improved quality.
Veo 3 Fast (recommended) Faster generation, fewer tokens.

Related