Loading...
Qwen Image 3.0
Qwen Image 3.0
Qwen text-to-image and image-to-image
Qwen Image 3.0 maps to KIE qwen3/text-to-image and qwen3/image-to-image, not qwen or qwen2. Prompts can be Chinese or English. Resolution is 1K or 2K. Image-to-image accepts up to three images, 10MB each. Aspect ratios: 1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 21:9.
Verified capabilities
Only capabilities that are live and checked with a cheapest real task are listed.
Text-to-image
Generate from a prompt. Verified at 1K.
Image-to-image
Up to three reference images. Verified at 1K.
1K and 2K
Default 1K. SuperMaker's default 3 credits maps to 6 credits at 1K here; 2K is 12 credits.
Aspect ratios
1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 21:9. Default 16:9.
How to use Qwen Image 3.0
Pick the model, add a prompt or up to three images, set resolution and aspect ratio, then submit.
1
1. Select Qwen Image 3.0
Choose Qwen Image 3.0 in the image studio. It is not the older Qwen or Qwen2 endpoints.
2
2. Add a prompt or reference images
Text-to-image needs a prompt. Image-to-image accepts up to three images plus instructions.
3
3. Generate and download
Choose 1K or 2K, then download the PNG.
FAQ
Model version, image-to-image, and credits.
Is this Qwen or Qwen2?
Neither. This site uses KIE qwen3 text-to-image and image-to-image, matching SuperMaker's Qwen-Image 3.0.
Does it support image-to-image?
Yes, up to three reference images, 10MB each.
How many credits does one image cost?
6 credits at 1K and 12 credits at 2K. SuperMaker's default 3 credits maps to the 1K tier times two.
Can I use a Chinese prompt?
Yes. KIE qwen3 accepts Chinese and English prompts.
Were the examples generated with 3.0 just now?
Feature images reuse published site assets. Pollo is behind a Cloudflare challenge, so new files were not downloaded. Copy only describes verified capabilities.
Generate images with Qwen Image 3.0
Text-to-image or image-to-image with up to three references. 6 credits at 1K.
