AI Assistance
The editor’s footer has an AI input with a provider picker. Five options:
| Apple Intelligence | On-device (macOS 26+, Apple silicon). No data leaves your Mac. Must be enabled in System Settings → Apple Intelligence & Siri. |
| Google Gemini | Cloud, requires an API key (Settings). Image edits use gemini-3.1-flash-image (Nano Banana 2) — fast, good for iteration. |
| Google Gemini (Pro) | Same key, image edits use gemini-3-pro-image (Nano Banana Pro) — better for complex edits (higher cost and latency). |
| OpenAI (Fast) | Cloud, requires an API key (Settings). Image edits use gpt-image-2.5-flare — extremely fast and responsive. |
| OpenAI (Quality) | Same key, image edits use gpt-image-2.5-sunburst — best for intricate or high-fidelity edits (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 cloud providers (Gemini or OpenAI), this is a separate, text-only call to a classification model. So, each user prompt triggers two API calls — one tiny and one “real”.
The response panel narrates the decision. If a prompt gets misclassified, rephrase toward the verb — “draw a box around…” routes to annotations, “remove / replace / recolor…” to image editing.
With cloud providers, your prompts and responses form a running conversation, so you can build on earlier context (“replace the sky with a sunset” → “now make it warmer”). Each editor keeps up to ~10 prior turns. To start fresh, click Clear Session in the panel; switching providers (or tiers) resets it as well.
Ask questions
Apple Intelligence reads the image through OCR (precise about text, less about pictures).
| Read text | “What text is in the second paragraph?” |
| Find things | “Find and sum up all the dollar values” |
Cloud models see the actual pixels, so you can try asking about anything.
| Read text | “What does the highlighted text say?” |
| Extract info | “What fonts and colors are used here?” |
| Summarize | “Summarize what this dialog is asking” |
Edit the image
What “edit” means depends on the provider: Apple Intelligence applies whole-image filters on-device; Gemini and OpenAI do generative edits — replacing, removing, and restyling content.
In all cases, the response panel tells you what took place, and the whole edit is one undo step.
With Apple Intelligence
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, not generative edits — no targeted fine-tuning, content additions, or object removal. For those, use Gemini or OpenAI.
With Gemini and OpenAI
There are two ways to direct an edit:
1. 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”. |
2. BETTER: Annotation-guided — annotate the canvas first (text notes, arrows, shapes/overlays), then tell the model to follow the markup:
| Follow markup | “Apply image edits per the annotations”. |
| Targeted remove | “Remove everything inside the red box”. |
| Targeted edits | “Replace the circled area with grass”. |
PowerPic’s killer feature: Visible annotations are sent alongside the image as a separate layer; not baked in. PowerPic also sends a short text transcription of the markup, so the model is also told about each annotation in words and coordinates.
Tip — point with arrows. When asking questions or generating edits, use arrows for better specificity. PowerPic reads that as “‹your note› → this region” and passes it to the model. For exact associations, bind the arrows to the text and target areas. The same applies when you ask questions about marked-up areas.
AI Inpainting Masks (currently OpenAI only) — Right-click any annotation and choose Set/Clear AI inpainting mask. When set, it clearly defines a permitted edit region, to ensure the rest remains untouched. Your prompt or markup then describes what to generate inside the masked area(s).
As soon as the first mask is set, the app enters mask layer preview mode — you can toggle the layer on/off using the footer’s checkerboard button. Similarly to the annotation toggle, the mask layer must be visible to be sent to the model.
Marking an annotation as a mask is additive — the shape is still sent through the normal markup layer and transcription, per above. Currently, only OpenAI receives it as an additional pixel-editing boundary; Gemini has no mask support yet — a masked shape behaves exactly like a regular annotation.
Output size — Cloud models render at their own native resolutions and can’t produce exact pixel dimensions. PowerPic handles this for you:
- Normal edits come back resampled to your image’s original size, as long as the aspect ratio holds.
- If you ask to upscale / enhance, or change the aspect ratio (“make it 16:9”), the new result is kept (and your annotations scale to match).
- For exact dimensions, finish with Edit Image → Resize.
Draw 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 still fairly limited and experimental.
Input tips
- ↑ / ↓ recall previous prompts; Return submits; Esc closes the panel.
- The ⓘ button shows provider-specific tips (click again to dismiss).