Gemini 3 Pro Image
by Google
Reasoning-led generation for complex layouts, infographics and legible text.
Spec sheet
- Model ID
google/gemini-3-pro-image- Type
- Image
- Max output
- 4K
- Speed
- Max quality
- Capabilities
- Text to image
- Image editing
- Multi-reference
- Text rendering
About the model
Gemini 3 Pro Image plans before it draws, which makes it unusually good at diagrams, multi-panel layouts, packaging and anything with real text on it. It accepts many reference images at once and keeps characters and products consistent between edits.
Swap it anytime
Every model takes the same request, so moving to another one means changing the model ID and nothing else.
Call it in a few lines.
curl https://api.monogram.dev/v1/generations \
-H "Authorization: Bearer $MONOGRAM_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemini-3-pro-image",
"input": {
"prompt": "A crystal perfume bottle on black marble, gold rim light, 1920s poster",
"aspect_ratio": "4:5"
}
}'Skills that use Gemini 3 Pro Image
Virtual Try-On
Show any garment on a model, true to its fit and fabric.
- Isolate the garment
- Dress the model
- Refine fabric detail
Studio Headshot
Professional headshots from a few everyday photos.
- Build the likeness
- Shoot the portraits
- Retouch and sharpen
Storyboard to Film
Turn a shot list into matching clips, cut together with sound.
- Design key frames
- Animate each shot
- Assemble the cut
More image models
See allFLUX.2 [pro]
Black Forest Labs
Photoreal generation and multi-reference editing with production-grade consistency.
Imagen 4 Ultra
Highly detailed photoreal images with precise prompt adherence.
GPT Image 1.5
OpenAI
Instruction-following generation and editing with excellent text and layout.