AI Assistance

The editor’s footer has an AI input with a provider picker. Three options:

Apple Intelligence On-device (macOS 26+, Apple silicon). No API key, no data leaves your Mac.
Google Gemini Cloud, requires an API key (Settings). Image edits use Nano Banana 2 — fast, good for iteration.
Google Gemini (Pro) Same key, image edits use Nano Banana Pro — better for complex edits, at higher cost and latency.

How prompts are routed

Every prompt is first run through a small intent classifier that picks one of three modes: question, image edit, or annotation edit.

Apple Intelligence classifies on-device. With Gemini, this is a separate, text-only call to the Flash model (typically < 1 sec). So, each user prompt triggers two API calls — one tiny and one “real”.

The response panel narrates the decision — you’ll see a line like » gemini-3.5-flash: imageEdit · 0.4s before the main call runs. If a prompt gets misclassified, rephrase toward the verb — “draw a box around…” routes to annotations, “remove / replace / recolor…” to image editing.

Ask questions

Read text “What does the highlighted text say?”
Summarize “What is this dialog asking me to decide?”
Find things “Find and sum up all the dollar values”

Apple Intelligence reads the image through OCR (precise about text, less about pictures); Gemini sees the actual pixels.

Draw/edit annotations

Mark one thing “Circle the lightbulb”, “box the title text”
Mark many things “Draw rectangles around every button”
Modify / remove “Make the red box blue”, “delete the arrow”

Shapes use your current toolbar style unless the prompt says otherwise. Each prompt request is a single Undo step. Gemini can batch mixed operations (create + delete + restyle) from one prompt.

Annotation drawing is fairly limited and experimental.

Adjust the image (Apple Intelligence)

Apple Intelligence supports basic adjustments, applied on-device through Core Image:

Sharpen “Sharpen the details.”
Brightness “Brighten this by 20%.”
Contrast “Bump the contrast significantly.”
Blur “Add a slight blur.”

These are image-wide “filters” rather than generative edits. They do not include targeted fine-tuning, content additions, or object removal. For those features, use Gemini below.

Edit the image (Gemini)

There are two ways you can direct edits to your image:

Plain prompts — describe the change in words:

Replace “Replace the sky with a sunset”.
Stylize “Make it look like a watercolor”.
Remove “Remove the person in the background”.

Annotation-guided — mark up the canvas first (boxes, arrows, text notes), then tell the model to follow your markup. Visible annotations are sent alongside the image as a separate layer, and are not baked into the result:

Follow markup “Apply the edits per the annotations”.
Remove marked “Remove everything inside the red box”.
Replace marked “Replace the circled area with grass”.

Output size

Gemini renders at its own native resolutions — it can’t produce exact pixel dimensions. PowerPic handles this for you:

  • Normal edits come back resampled to your image’s original size.
  • If you ask to upscale / enhance, or change the aspect ratio (“make it 16:9”), the larger result is kept and your annotations scale to match.
  • For exact dimensions, finish with Edit Image → Resize.

The response panel tells you what took place, and the whole edit is one undo step.

Input tips

  • ↑ / ↓ recall previous prompts; Return submits; Esc closes the panel.
  • The ⓘ button shows provider-specific tips (click again to dismiss).