Skip to main content

AI Model Guide

NGMC integrates AI models across four families — image, video, audio, and chat. 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
GPT Image 2 Agent2–30min4K (3840x3840)Up to 6 (shared)AI-planned multi-frame sets — storyboards in one run
Nano Banana Pro~45s4K (6336x5504)Up to 6Professional quality, multi-turn editing
Nano Banana 2~15s4K (4096x4096)Up to 14Most reference images, 0.5K draft mode
Nano Banana 2 Lite~2s1KUp to 14Fastest + cheapest iteration
Grok Image Pro~15s2KUp to 3Multi-image merge, adaptive + phone ratios, 4 outputs/run
MAI Image 2.5~30s~1.3K1Photorealism + in-image text rendering
Seedream 5.0 Pro~30s2KUp to 10Sketch/region-guided edits, Layer Workbench

Video Models

Generate videos from text, images, or references — or edit existing footage.

ModelSpeedMax ResolutionDurationAudioKey Strength
Veo 3.1~2min4K4 / 6 / 8sNative audio + dialogueHighest quality, video extension
Veo 3.1 Fast~45s4K4 / 6 / 8sNative audio + dialogueFast iteration with full resolution tiers
Seedance 2.0~2min4K4–15s (continuous)Optional native audioCinematic quality, mixed image + video + audio references
Seedance 2.0 Fast~45s720p4–15s (continuous)Optional native audioFast Seedance iteration
Seedance 2.0 Mini~30s720p4–15s (continuous)Optional native audioCheapest Seedance drafts
HappyHorse 1.1~1min1080p3–15s (continuous)No9 reference images, physical realism, seed support
Grok Video 1.51–3min1080p1–15s (continuous)Native audio + lip-synced dialogue1-second minimum, adaptive aspect
Gemini Omni Flash~1min720pUp to 10sNative audioVideo editing + 30 reference images

Audio Models

Music, sound effects, and voiceover.

ModelCategorySpeedDurationKey Strength
Lyria 3 ClipMusic~30s30s fixedFast musical iteration, image references
Lyria 3 ProMusic~1minUp to 2minFull song structure, timestamped control
ElevenLabs Music V2Music~30s3s – 10min (exact)Exact-length tracks, royalty-free
ElevenLabs Sound EffectsSFX~10sUp to 30sFoley/braams/ambience, seamless loop
Seed Audio 1.0Multimodal~30sUp to 2minReference-audio style guidance, image-guided ambience
Gemini 3.1 Flash TTSVoiceover~10sUp to 3min30 voices, 2-speaker dialogue, audio tags
Qwen3 TTS FlashVoiceover~10sUp to 3min36 voices incl. 8 Chinese dialects
Qwen3 TTS InstructVoiceover~10sUp to 3minNatural-language delivery instructions

Chat Models

AI Chat nodes for writing, planning, and analyzing — with vision and long context.

ModelContextReasoning EffortKey Strength
Claude Opus 4.61M tokensNone – HighScreenwriting workhorse, fast + deep
Claude Fable 51M tokensLow – X-High (always thinking)Hardest reasoning + long-horizon writing (Max plan)
GPT 5.51M tokensNone – X-HighWidest effort range, structured planning

All three see connected images (up to 10), read connected documents (up to 100), and stream replies into the canvas conversation.

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.


Choosing a Model
  • Iterating on ideas? Nano Banana 2 Lite (~2s) for images; Seedance Fast/Mini, Veo 3.1 Fast, or Gemini Omni Flash for video.
  • Final output quality? Nano Banana Pro or Seedream 5.0 Pro (images); Veo 3.1 or Seedance 2.0 at 4K (video).
  • Need many reference images? Nano Banana 2 / Lite take 14; Seedream 5.0 Pro takes 10; Omni Flash takes 30 on the video side.
  • Mixed reference inputs (image + video + audio)? Seedance 2.0 accepts all three modalities in the same run.
  • Editing existing footage? Gemini Omni Flash is the only video-editing model.
  • Need dialogue in video? Veo 3.1 / Fast generate speech from quoted text in your prompt.
  • Whole storyboard in one run? GPT Image 2 Agent plans and renders up to 10 coherent frames.
  • Voiceover? Gemini TTS (dialogue, tags), Qwen3 TTS (Chinese dialects), or Seed Audio 1.0 (reference-audio style guidance).
  • Music to exact length? ElevenLabs Music V2 renders 3s–10min on the second.
  • Precise spatial edits? Seedream 5.0 Pro's sketch + coordinate-marker editing.