Jib Mix Qwen text-to-image makes one photoreal image from a written prompt on J1B's community merge of Alibaba's 20B Qwen-Image, tuned for natural faces and skin. Nine aspect ratios at up to 1536 pixels on the long side, about six seconds per image and no content filter.
Workbench
These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.
Outputempty-cinema-two Written as a two-shot: who stands where, how close, and one light source named as the only light. A prop out of focus in the foreground, the film reel, gives the frame depth, and the ages in the prompt show in both faces.
- 692
- 16:9
Outputcellar-sideways-glance Age, hair, freckles, dress and one bare bulb named as the only light, and the vault stayed dark around her. The freckles, the fine lines and the shine on the satin are the model, not retouching.
- 722
- 3:4
Outputtailor-after-closing Two practical lights in the prompt, a green desk lamp in front and blue streetlight through the window behind, and the model kept both colours. "Unsmiling" was needed for the steady gaze: without it he grinned.
- 601
- 2:3
Outputstay-the-night-poster The poster text is quoted in the prompt and came back reading "STAY THE NIGHT". A plain wall with one poster kept the frame clean; when we described a busy print shop, the walls filled up with made-up small print.
- 741
- 4:3
This example starts at $0.024 per image. The Playground updates the estimate when you change the settings.