コンテンツにスキップ

Gemini 3 Pro Image | Mona Lisa Portrait

メタ情報

  • Date: 2026-04-30
  • Tool: Google Antigravity (macOS app)
  • Model: Gemini 3 Pro Image via Gemini 3 Flash

プロンプト

[IMAGE TASK]
prompt = """
A captivating, hyper-realistic close-up portrait photograph reimagining the Mona Lisa as a real woman. Her skin is luminous, with flawless texture and natural makeup, revealing subtle pores. She possesses delicate, refined features and that iconic, enigmatic smile with a gentle gaze. Illuminated by flattering, soft studio lighting, creating a perfect balance. Captured with a shallow depth of field and a beautifully soft bokeh background. Cinematic clarity, ultra-high detail, photorealistic masterpiece.
"""
result = client.images.generate(
model="gemini-3-pro-image-preview",
prompt=prompt,
size="1024x1024",
aspect_ratio="1:1",
)

出力

Gemini 3 Pro Image の baseline

プロンプト

/mtp <args>
[AGENT INSTRUCTION]
This request contains an MTP invocation.
Before generating or composing the image prompt, run the MTP compiler using the /mtp arguments.
Apply the compiler stdout as silent constraints to the image-generation task, specifically regarding composition, lighting, style, subject framing, and subjects.
Do not infer MTP settings from the image prompt.
Do not include this instruction, /mtp arguments, or MTP XML in the final image prompt.
[IMAGE TASK]
prompt = """
A captivating, hyper-realistic close-up portrait photograph reimagining the Mona Lisa as a real woman. Her skin is luminous, with flawless texture and natural makeup, revealing subtle pores. She possesses delicate, refined features and that iconic, enigmatic smile with a gentle gaze. Illuminated by flattering, soft studio lighting, creating a perfect balance. Captured with a shallow depth of field and a beautifully soft bokeh background. Cinematic clarity, ultra-high detail, photorealistic masterpiece.
"""
result = client.images.generate(
model="gemini-3-pro-image-preview",
prompt=prompt,
size="1024x1024",
aspect_ratio="1:1",
)

composition, lighting, style, subject framing, and subjects

左側ノード中央ノード右側ノード
Gemini 3 Pro Image の open:100 open:100Gemini 3 Pro Image の power:100 power:100Gemini 3 Pro Image の return:100 return:100
Gemini 3 Pro Image の grow:100 grow:100Gemini 3 Pro Image の helix:100 helix:100Gemini 3 Pro Image の focus:100 focus:100
Gemini 3 Pro Image の enter:100 enter:100Gemini 3 Pro Image の flow:100 flow:100Gemini 3 Pro Image の close:100 close:100
左側ノード中央ノード右側ノード
Gemini 3 Pro Image の still:100 still:100Gemini 3 Pro Image の void:100 void:100Gemini 3 Pro Image の surge:100 surge:100
Gemini 3 Pro Image の wither:100 wither:100Gemini 3 Pro Image の collapse:100 collapse:100Gemini 3 Pro Image の haze:100 haze:100
Gemini 3 Pro Image の drift:100 drift:100Gemini 3 Pro Image の abyss:100 abyss:100Gemini 3 Pro Image の fade:100 fade:100