Lettering drafts
describe the words and their placement.
Image generation & editing
Explore text-led MOSS-Image-SFT drafts.
Loading model settings…
Your prompt, settings, and references stay together in a new Canvas.
01 / Meet the model
MOSS-Image-SFT creates a still image from a text prompt. It is suited to prompts describing Chinese or English lettering and structured layouts. Choose one of its supported aspect ratios and review the generated text and layout for accuracy before reuse.
02 / Choose it for
describe the words and their placement.
specify how visual elements should be arranged.
select a supported aspect ratio for the layout.
03 / Before you create
Model settings. Availability, input mode, and references can narrow the choices offered in Canvas.
04 / A closer look
No. This staging-only workflow accepts a text prompt rather than image references. Describe the lettering, layout and subject in the prompt and inspect the output carefully.
Text prompt. The input controls above show the options available for your selected mode.
1:1 · 4:3 · 3:4 · 16:9 · 9:16. Automatic; no resolution selector.
Start with the format you intend to publish, then choose the available output settings. Changing inputs can change the choices. Review the current Gem estimate before Generate; availability and cost can vary.