qwen-imagelisted
Install: claude install-skill popnow-ai/popnow-skills
# Qwen Image generation and editing
Qwen Image from Alibaba renders text in both Chinese and English unusually well and handles posters, packaging and signage. Qwen Image 2.1 Pro can return up to six detailed 2K images from one prompt; Turbo is the fast tier; 3.0 and 3.0 Pro add stronger multi-reference editing; LoRA variants accept custom styles.
## 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 |
|---|---|
| `alibaba/qwen-image-3.0-pro/text-to-image` | Newest, highest quality |
| `alibaba/qwen-image-3.0-pro/edit` | Multi-reference edit |
| `alibaba/qwen-image-2.1-pro/text-to-image` | Up to six 2K images per request |
| `alibaba/qwen-image-2.1-turbo/text-to-image` | Fast tier |
| `alibaba/qwen-image-2.1-lora/text-to-image` | Custom LoRA styles |
## Prompt tips
- Put any text to render in quotes and name the script, for example a red banner reading "Happy New Year" in both English and Chinese characters.
- Ask for several variations in one request where the schema has an image-count field; it is cheaper than repeated calls.
- For edits, say exactly which region changes: "replace only the label text on the bottle".
## Setup and cost
Requires Python 3.8+ and a PopNow API key in `POPNOW_API_KEY`. Create a dedicated key at https://popnow.ai/api/console/keys and restrict its models, IPs and spending caps. Keep the key in the agent's secret or environment setti