Knowledge base · images
Wan
Generating and editing images from text, a universal model for different styles.
Open in studio →What it can do
- ✓Text-to-image: photorealism, art, product shots.
- ✓Editing an uploaded image by description (image-to-image).
- ✓Works with different styles and scenes.
How to write a prompt
For generation: subject → environment → style → lighting → angle. For editing, attach a photo and describe only the change.
A prompt that works
Portrait of a girl in a red coat on an autumn street, soft diffused light, film aesthetic, medium shot
Avoid this
“a beautiful photo”
Too general: add a subject, style and lighting.
Examples
Editing
(attach a photo) Replace the background with a winter city in the evening, keep the person and the lighting
Variants within the group
- Wan 2.6 / 2.5 · T2I and I2I, Fresh generations; the I2I mode edits an uploaded image.
Tips
- →A specific prompt = a more stable result.
FAQ
How much does a generation in Wan cost?
from 2 to 4 tokens per generation, depending on the chosen version and settings. Current plans and token packs are on the /en/pricing page.
Can the results of Wan be used commercially?
Yes, with an active Pixyn subscription. Note that some models have provider restrictions by industry, check the terms of the specific version.