跳到主要内容
Qwen检查中

Qwen Image 3.0 / Text to Image

qwen-image-3-0-text-to-image

文生图输出: 图像输入: 文本
正在加载价格…
官方原价 · 未验证

模型能力

Generate images from text.

Text-to-image · 1–6 images

输入参数

仅列出此模型接受的字段。必填字段必须提供。

字段类型必填默认值可选值与约束
prompt
string必填—

Positive prompt describing the desired image content, style, composition, and text rendering. Chinese and English are supported.

≤ 3000 chars

negativePrompt
string可选—

Negative prompt describing unwanted content.

≤ 600 chars

size
string可选—

Output resolution as width*height, from 262144 to 4194304 pixels, with aspect ratio between 1:8 and 8:1. Leave empty to let the model choose.

可选值: "1024*1024", "1600*1600", "768*1152", "1280*1920", "1152*768", "1920*1280", "768*1024", "1536*2048", "1024*768", "1792*1344", "576*1024", "1152*2048", "1024*576", "2048*1152"

262144–4194304 pixels; width*height · Aspect ratio 1:8–8:1

imageNum
integer可选1

Number of images generated per request. Defaults to 1.

可选值: 1, 2, 3, 4, 5, 6

promptExtend
boolean可选true

Whether to enable intelligent prompt rewriting. Enabled by default; improves results for short prompts.

promptExtendMode
string可选"direct"

Prompt rewriting mode, effective only when promptExtend is enabled. Use direct for direct rewriting or agent for agent-based rewriting.

可选值: "direct", "agent"

enableThinking
boolean可选true

Enable thinking mode for prompt rewriting. On by default: better quality, slower. Turn off to cut rewrite time to about 20s. Only takes effect when promptExtend=true. Supported for Direct T2I and Agent T2I.

seed
integer可选—

Random seed in [0, 2147483647]. Fixing the seed reproduces results; leave empty for random.

0–2147483647

限制与行为

  • 仅支持异步:先提交任务,再轮询结果。
  • prompt: ≤ 3000 chars
  • negativePrompt: ≤ 600 chars
  • size: 262144–4194304 pixels; width*height, Aspect ratio 1:8–8:1
  • seed: 0–2147483647