Text to Image — MOSS-Image-SFT is a text-to-image model specializing in Chinese and English text rendering and structured layout control for precise text placement and object arrangement.

≈ 44.811 kredi/görsel

Ayarlar

Negative Promptisteğe bağlı

Negative prompt. When empty, guidance uses transformer layer skipping for the negative branch.

Enable Prompt Expansionisteğe bağlı

Plan a structured layout from your prompt before generation. Preserves requested visible text and uses the selected image dimensions. If enhancement is unavailable, uses the original prompt.

Image Sizeisteğe bağlı

Output image size. Width and height are rounded to multiples of 16 between 512 and 2048 pixels.

Number of Inference Stepsisteğe bağlı

Number of denoising steps.

Guidance Scaleisteğe bağlı

Classifier-free guidance scale.

Seedisteğe bağlı

Random seed for reproducible generation.

Number of Imagesisteğe bağlı

Number of images to generate.

Enable Safety Checkeristeğe bağlı

Enable output content moderation. Disabling it requires account authorization; unauthorized requests are always checked, and images flagged as unsafe are returned as black images.

Output Formatisteğe bağlı

Output image format.

Üretmek için giriş yap

Modeli inceleyebilirsin; üretim için hesabınla giriş yapman gerekiyor.

Giriş yap