Skip to main content

Image Generation

The Image Generation node creates images from text prompts using your choice of 6 AI image generation engines.

Inputs

Handle IDData TypeLabel
text-inTextPrompt
The node also accepts an optional image input (image-in) for reference-based generation.

Outputs

Handle IDData TypeLabel
image-outImageImage

Available engines

Engine IDLabelCost per image
fal-nano-bananaNano Banana8 credits (standard) / 12 credits (pro)
fal-gpt-image-1.5GPT Image 1.52 credits
grok-imagineGrok Imagine2 credits
fal-seedream-v5-liteSeedream v5 Lite3 credits
fal-qwen-image-2-proQwen Image 2 Pro2 credits
fal-fluxFLUX.13 credits (dev) / 5 credits (pro)

Configuration options

ParameterDescription
EngineSelect from 6 available image models
PromptText description of the image to generate

Advanced options

ParameterRangeDefault
TierNano Banana 2 / ProNano Banana 2
SeedAny integerRandom
Guidance Scale1–203.5
Inference Steps1–10030
ParameterRangeDefault
TierDev / ProDev
Sync ModeOn/OffOn
Number of Images1–41
SeedAny integerRandom
Guidance Scale1–203.5
Inference Steps1–10028
ParameterRangeDefault
SeedAny integerRandom

Credit cost

Varies by engine — see table above. Images are generated at 9:16 aspect ratio by default.

Tips

  • Prompts are automatically enhanced with cinematic lighting, camera angles, and style keywords
  • Use reference images (via the optional image input) for more consistent character generation
  • GPT Image 1.5 and Grok Imagine are the most cost-effective at 2 credits per image
  • Nano Banana produces the highest quality but costs more

Example use cases

  • Generating scene backgrounds for video creation
  • Creating character images for motion transfer
  • Producing thumbnails for YouTube videos
  • Creating consistent visual styles across shots