Qwen Image 3.0
Create text-led visuals or edit an image with written instructions and up to three ordered references. Qwen Image 3.0 is an optional model in Other models, with no change to your default.
Best for
- text
- edits
- composition
Use when
- You want to try English or Chinese text in a generated visual.
- You want to change details using a written editing instruction.
- You want to combine up to three image references in a specified order.
Avoid when
- You need a mask, transparent output, or more than three references.
- You need exact seed, quality, or resolution controls in DayGen.
Inputs
- prompt
- up to three ordered image references
Outputs
- PNG, JPEG, or WebP image
DayGen surfaces
- /image/create
- /image/edit
- QuickEdit
- Agent image generation
- Brand, Team, Assets, and Direct keyframes
Available settings
- Aspect Ratio
- Auto, 1:1 (Square), 16:9 (Wide), 9:16 (Story), 4:3 (Classic), 3:4 (Portrait), 3:2 (Photo), 2:3 (Poster)
- Output Format
- PNG, JPEG, WebP
- Batch Size
- 1–4
- References
- Up to 3 images