curl-X POST 'https://pollo.ai/api/platform/v1/generation/qwen/qwen-image-3-pro/image'\-H'Content-Type: application/json'\-H'x-api-key: YOUR_API_KEY'\-d'{ "input": { "prompt": "A cinematic shot of a golden retriever running through a field of sunflowers at sunset, warm rim light, shallow depth of field", "aspectRatio": "1:1", "resolution": "1K" }}'
{"input":{"prompt":"A cinematic shot of a golden retriever running through a field of sunflowers at sunset, warm rim light, shallow depth of field","aspectRatio":"1:1","resolution":"1K"},"webhookUrl":"https://example.com/webhooks/pollo"}
模式
输入所选端点和模式的字段。
场地
类型
必需的
描述
prompt
string
支持
Text prompt describing the content to generate.
aspectRatio
string
不
Output aspect ratio, as width:height (e.g. 16:9).
resolution
string
不
Output resolution of the generated media (e.g. 720p, 1080p, 2K, 4K). Values are case-insensitive.
Editorial Page Concepts: Combine a lead photograph, inset imagery, headline, and short captions within a defined magazine-style hierarchy.
Multilingual Menu Designs: Arrange item names and descriptions in multiple languages, using supplied wording and clear section boundaries.
Packaging Presentation Boards: Show material treatments, a main pack visual, and explanatory labels together for design review.
Detailed Interface Mockups: Explore screens containing nested cards, navigation, and realistic content as image concepts for a later implementation.
Portrait-Led Profiles: Pair a textured photographic portrait with a restrained headline and supporting editorial content.
Information-Rich Exhibition Panels: Organize a central image, smaller detail views, and labeled descriptions into one coherent visual draft.
如何使用 Qwen Image 3.0 Pro API
Get an API Key: Create a Pollo API account and generate your API key from the developer dashboard.
Choose the Model: Send requests to the Qwen Image 3.0 endpoint at /generation/qwen/qwen-image-3-pro/image.
Add Your Inputs: Provide the layout brief and exact copy, plus supported images when needed. Set aspectRatio and resolution for the intended composition.
Generate and Retrieve: Submit the task, poll the returned task status, and download the finished images once it succeeds.
Qwen Image 3.0 Pro API 的提示词最佳实践
像页面规格一样组织提示词。先建立网格和阅读顺序，然后为每张图片、文本块和材质细节分配角色。
简单的提示词公式
Visual format + page grid + primary image + section content + exact multilingual copy + typographic hierarchy + material or lighting details
你应该注意什么
Content Map: Describe the top, middle, and lower sections before specifying decorative details inside them.
Text Ownership: Pair every line of copy with its location, language, and hierarchy to reduce ambiguity about where it belongs.
Detail Priority: Identify which fine features matter most, such as woven fabric or the lettering on one inset label.
Useful Density: Leave space between sections rather than treating every empty area as something to fill.
Delivery Format: Treat generated pages as raster design drafts; rebuild editable text and interactive elements in the appropriate production tool.
[`示例提示词`]
植物展览展板
创建一块平面博物馆展板，标题为“SEEDS ON THE MOVE”。在上半部分放置一张细致的蒲公英照片。下方，排列三个等大的插图分区，分别标注为“Wind”、“Water”和“Animals”。添加小型植物细节插图、深绿色标题、象牙色背景，并在各分区之间留出充足间距。
