Mixer AI
Recraft
Posters, illustrations and clean graphics from text, plus restyling of a single photo.
When to choose it
Recraft combines three tools: V4 and V4 Pro create an image from text only, V3 Image redraws one uploaded photo. V4 suits regular work; V4 Pro costs noticeably more and is meant for final frames. Choose the version first: it decides the inputs and the price.
- Clean graphics: posters, covers, illustrations and compositions with tidy shapes.
- V3 Image restyles a finished photo; the strength slider from 0 to 100 sets how far it goes.
- A prompt of up to 10,000 characters for V4 and V4 Pro.
Modes and settings
- V4 and V4 Pro: text only; aspect ratios 1:1, 4:3, 3:4, 16:9 and 9:16.
- V3 Image: exactly one photo (JPG, PNG or WebP up to 5 MB) and a short description of the changes, up to 1000 characters.
- 1, 2 or 4 results per run; each result counts as a separate generation.
Price in coins
| Version | Input | Coins / generation |
|---|---|---|
| V4 | Text | — |
| V4 Pro | Text | — |
| V3 Image | Photo editing | — |
Coins are Mixer AI balance units. The table shows a base request without extra variations. Multiple results and new attempts can increase the total; check it before submitting.
The dollar price follows the current coin rate.
What you can make
- Posters, covers and article illustrations from a text description.
- Changing the style or season of a finished photo: watercolor, winter, flat graphics.
How to direct the result
- For V4 name the subject, setting, light and style; for a poster add composition and colors.
- For V3 Image describe only the change and control the amount with strength: start at 40 and raise it.
Example: a concert poster
A minimalist poster for a jazz concert: a large high-contrast saxophonist silhouette, flat graphics, three colors — dark blue, ochre and white, clean composition with plenty of empty space at the top for a headline.
What to keep in mind
- V4 and V4 Pro accept no references: to change a finished photo, choose V3 Image.
- Check lettering inside the image after generating: text may contain mistakes.
Sources
Guides and comparisons using this model
FAQ
How is V4 different from V4 Pro?
Both create an image from text with the same aspect ratios. V4 Pro costs noticeably more and suits final frames; V4 suits rough exploration.
Can I upload my own photo?
Only in V3 Image, which needs one photo. V4 and V4 Pro work from text.
What does the strength slider do?
It sets how far the result moves from the source photo: 0 is almost identical, 100 is barely similar.
Which aspect ratios does V4 have?
1:1, 4:3, 3:4, 16:9 and 9:16.
How many results can I get per run?
1, 2 or 4. Each result is a separate generation with its own price.
How do I enlarge a finished image?
There is a separate model for that: Recraft Upscale.
What changes the price?
It depends on version, quality and mode. The table prices one generation at the listed settings. Additional results, new attempts and chargeable input materials can increase the total.
Do I need a separate model subscription?
No. In Mixer AI, you top up one coin balance and use it for the tasks you need. You do not need a separate subscription to this model.