Skip to main content

AI Model Guide

NGMC integrates multiple AI models for image, video, and audio generation. Each model has unique capabilities, strengths, and limitations. This guide helps you choose the right model and get the most out of it.

Image Models

Generate and edit still images from text prompts and reference images.

ModelSpeedMax ResolutionReference ImagesKey Strength
GPT Image 2~45s4K (3840x3840)YesPrompt-faithful generation + edits, three quality tiers
Nano Banana Pro~45s4K (6336x5504)Up to 6Professional quality, multi-turn editing
Nano Banana 2~15s4K (4096x4096)Up to 14Fastest, most reference images, 0.5K draft mode

Video Models

Generate videos from text, images, or extend existing clips.

ModelSpeedMax ResolutionDurationAudioKey Strength
Veo 3.1~2min4K4 / 6 / 8sNative audio + dialogueHighest quality, 4K, video extension
Veo 3.1 Fast~45s720p4 / 6 / 8sNative audio + dialogueFast iteration, video extension
Seedance 2.0~2min1080p4–15s (continuous)Optional native audioCinematic quality, multimodal references, mixed image + video + audio inputs
Seedance 2.0 Fast~45s1080p4–15s (continuous)Optional native audioFast Seedance variant with the same capability surface

Audio Models

Generate sound effects, music, and ambient audio.

ModelSpeedDurationKey Strength
Lyria 3 (Clip)~30sUp to 30sFast iteration for SFX and short music cues
Lyria 3 (Pro)~1minUp to 2minHigher-quality music and ambient soundscapes

Referencing Images in Prompts

You can use @-mentions in your prompt to tell the model exactly how to use each reference image.

How it works

Type @ in the prompt textarea to open the reference picker. Select an image, and a mention like @[Image 1] is inserted at that position. When generated, the model sees the actual image inline at that exact point in your text, giving it precise context.

Example:

Add one more ragdoll cat based on @[Image 2], and replace the background
with the scenery from @[Image 1].

The model receives Image 2 right after "based on" and Image 1 right after "scenery from", so it understands which image to use for which purpose.

Without @-mentions

If you don't use @, all reference images are appended after your prompt text. The model still sees them but has to infer how to use each one. For simple cases (single reference, style transfer) this works fine. Use @ when you need the model to distinguish between multiple images.

Provider behavior

Provider@-mention behavior
Image models (Nano Banana Pro/2)Full interleaving — images placed inline at the mentioned position
Video models (Veo 3.1/Fast, Seedance 2.0/Fast)Mentions are resolved to display names in the prompt text; images are passed as structured reference inputs
Audio models (Lyria 3 Clip/Pro)Not applicable (audio references only)

Choosing a Model
  • Iterating on ideas? Start with Nano Banana 2 (images) or a Fast video variant (Veo 3.1 Fast, Seedance 2.0 Fast) for speed.
  • Final output quality? Use Nano Banana Pro (images), Veo 3.1, or Seedance 2.0 (video) for production.
  • Need many reference images? Nano Banana 2 supports up to 14 reference images; Seedance 2.0 accepts up to 9.
  • Mixed reference inputs (image + video + audio)? Seedance 2.0 accepts all three modalities in the same run.
  • Need dialogue in video? Veo 3.1 / Fast generate speech from quoted text in your prompt.
  • Custom duration between 4 and 15 seconds? Seedance 2.0 accepts any integer duration in that range; Veo is fixed to 4 / 6 / 8 seconds.