wan2.7-image-pro

Wan2.7-Image-Pro is the flagship image generation and editing model of Wanxiang 2.7, which supports various tasks such as Vincentian pictures, Vincentian group pictures, Picture group pictures, image editing, multi-image reference generation and interactive editing. Its outstanding feature is that it supports image generation with resolutions up to 4K (4096×4096), and it also has a "thinking mode" to improve the quality of generation. It has stronger performance in text rendering, subject consistency and complex instruction following. It can generate up to 12 consecutive image groups at one time, which is suitable for the serial creation of characters in different scenes. Image editing and multi-image reference generation support up to 2K resolution, and 4K is only suitable for pure textual image scenes. The input modalities are text and images.

Context
0 tokens
Max output
0 tokens
Input
llm image
Output
image

Pricing

Price: $0.075 / request

Endpoints

  • openai

More models

  • gemini-3.1-flash-lite-image

    gemini-3.1-flash-lite-image 是 Gemini 3.1 Flash 系列的轻量图像模型标识,适合成本与速度优先的视觉原型和批量素材变体任务。它可用于早期分镜、背景替换、简单海报构思、商品图候选方案和多风格草图生成,再将选中的方向交由设计师或更高能力模型精修。提示词应聚焦一个明确的主体、场景和风格,并设置固定画幅与输出数量。所有拟公开或商用图片仍应经过版权、肖像、商标和质量审核。

  • seedream-5-0-260128

    Seedream 5.0 是 Seedream 系列最新一代图像创作模型,首次集成联网检索和深度推理能力。模型采用多模态统一架构,在理解、推理和生成方面全面提升,能够像人类设计师一样理解用户指令背后的意图,并将世界知识应用于图像与文本创作中。其核心亮点包括:视觉推理生图支持多步思考,让生成结果符合物理规律与内在逻辑;实时检索增强可通过联网获取最新知识,精准回应时效性创作需求;信息可视化能力大幅提升,适用于办公、教育与科研等生产力场景。

  • dola-seedream-5-0-pro-260628
  • gemini-3.1-flash-image

    gemini-3.1-flash-image 是 Gemini 3.1 Flash 系列的图像生成与编辑模型标识,适合需要较快迭代的视觉内容工作流。它可用于将营销创意转成视觉草稿、生成商品背景、改换局部元素、探索配色和制作多版本社交媒体素材。为了提高成片可控性,应先给出清晰的主体与风格约束,再逐步调整构图、光线和细节,而非一次叠加过多要求。涉及可识别人物、品牌资产或公开投放的图片,应加入人工复核和素材权利检查。