ai-image-generatorlisted
Install: claude install-skill popnow-ai/popnow-skills
# AI image generation with any PopNow model
One PopNow API key reaches dozens of image models. This skill helps the agent choose the right one for the request, quote the exact USD price and generate after the user says yes.
## Models
These are the PopNow model paths at the time of writing. Confirm them with `models` before use; newer versions appear there first.
| Model path | Best for |
|---|---|
| `google/nano-banana-2.1/text-to-image` | Fast all-rounder, good text |
| `google/nano-banana-pro/text-to-image` | Infographics, dense layouts |
| `openai/gpt-image-2.5-sunburst/text-to-image` | Typography, UI, logos |
| `bytedance/seedream-5.0-pro/text-to-image` | Detail, consistent series |
| `black-forest-labs/flux-2-max/text-to-image` | Photorealism, brand colors |
| `alibaba/qwen-image-2.1-pro/text-to-image` | Bilingual text, batches |
## Prompt tips
- Match the model to the job: text-heavy → Nano Banana Pro or GPT Image; photoreal → FLUX.2 Max; character or product series → Seedream; budget drafts → Seedream Lite, Qwen Turbo or FLUX Klein.
- Run `models --modality image` to see everything currently available, including vector (SVG) and 3D models.
- If the user names a style but no model, quote two candidates and let them choose on price and look.
- Always state aspect ratio and size; social posts are usually 1:1 or 4:5, thumbnails 16:9, stories 9:16.
## Setup and cost
Requires Python 3.8+ and a PopNow API key in `POPNOW_API_KEY`. Create a dedicated key at https://popn