Skip to main content
Take a screenshot from your 3D model, write one strong prompt, and produce a styled render. Then branch the prompt into variations and apply the locked-in style across other views of the same building. Time: 12 minutes You’ll need: A 3D model in Rhino (or any 3D tool), or just a screenshot to start with
For more on the techniques in this example, see also render variations (3 min) and producing render sets (8 min).

​
1. Get a strong baseline render

Start by feeding two things into a Create node with Nano Banana Pro:
  • A clean line drawing screenshot from Rhino (pen linework, not shaded). Colours and shading in your screenshot muddy the output.
  • A prompt that names three things: lighting, material, and a named reference.
Example prompt: 
Coloured editorial architectural photograph of a realistic house in the
forest, raking side light, deep shadow, tactile white materials,
large-format medium, Hélène Binet style. Surrounded by lush vegetation.
Steal this shape for your own prompts. Swap the lighting, material, and named reference and you have a new look without starting from scratch.

​
What controls the output

  • Aspect ratio: match the output aspect ratio to your screenshot. Output portrait if your screenshot is portrait.
  • Image order: Nano Banana is most influenced by the last image you provide. Put the screenshot you want to render last.
  • Switch to Pro for client work: Nano Banana Pro handles ambiguity better, especially when references and screenshots have different camera angles. The cost is worth it for ship-quality output.

​
2. When the model returns the wrong thing

Two failure modes are common when you’re rendering against a reference: The model returns the reference instead of editing the screenshot. Use the thumbnail technique: paste your screenshot as a small thumbnail inside the reference image. Now you have a single image with both, and the model pays attention to the main frame while staying influenced by the thumbnail. The model just returns the screenshot unchanged. This happens when the reference and screenshot are very similar. The thumbnail technique fixes this too. For a deep dive on these techniques and more, see the 12 ways to improve your Nano Banana images walkthrough.

​
3. Write a multi-step prompt for control

When you need fine control over photographic qualities (film grain, vignetting, light balance), write the prompt as a sequence of steps rather than one sentence: 
1. Produce a photograph of the line drawing.
2. Maintain the exact geometry and perspective of the line drawing.
3. Add people like in the reference image.
4. Match the photographic qualities: film grain, vignetting, light and
   shadow balance.
5. Remove the thumbnail from the final image.
Why this works: the model internally generates and checks against your prompt. A multi-step prompt gives it something to judge against at each step. When matching photographic qualities, name them specifically:
  • Film grain
  • Vignetting
  • Light and shadow balance
  • Colour palette
  • Activity and people
  • Greenery or context

​
4. Branch the prompt with an agent

Once your baseline render works, generate stylistic variations by feeding the prompt through an Agent node:
Agent node generating variations of an input prompt
  1. Add an Agent node
  2. Set output format to list
  3. Connect your original prompt as context
  4. Prompt the agent: Generate 4 variations of this prompt that explore different photographic styles.
  5. Connect the agent’s list output to a new Create node
  6. Each list item becomes a separate render
Four stylistic variations of the same building
You now have a series of stylistic options to pick from.

​
5. Carry the style across other views

Once one variation works, lock it in and apply it to other angles of the same building:
  1. Take the finished render and crop it to just the building (remove surroundings).
  2. Collage it into the top-left of a new screenshot from a different angle.
  3. Prompt Nano Banana Pro: “Apply the style from the top left to the main image. The screengrab shows the same building from a different angle. The vegetation and surroundings must match the new camera position.”
Keep this second prompt simpler than the first. The hard work was done in the baseline.
Rotating camera angles is one of the hardest things for any image model. Style-transferring many views in one batch usually fails. Work through them one at a time, tweaking prompts per view.

​
Quick tips

  • Use @ (or Tab) to inline reference any node’s output into a prompt. See Connecting Nodes.
  • Alt-drag to duplicate a node. Alt-shift-drag duplicates with connections.
  • Crop references before collaging. Less clutter, more focus.
  • Square aspect ratios for cropped references. Wild aspect ratios produce worse results.
  • Workshop long prompts with the chat agent when one isn’t producing what you want.

​
Next steps