BLACKFRIDAY 来了!

    领取40%优惠
    Armox
    Armox Academy 📚
    介绍
    快速入门指南
    理解Brain
    节点
    AI模型
    画布编辑器
    训练 LoRA
    Train MiniMax H3 LoRA
    提示词工程
    Nano Banana ProFlux模型视频提示词音频提示词
    文本节点
    图像节点
    视频节点
    音频节点
    上传节点
    工具节点
    Academy.canvas3dNodes
    连接节点
    运行工作流
    什么是应用?
    创建您的第一个应用
    运行应用
    创意人士的应用创意
    API 参考入门
    身份验证模型端点应用端点任务端点账户端点Webhook错误与速率限制
    图库
    下载与导出
    使用AI聊天
    与AI进行头脑风暴
    文本模型
    GPT-5.4Gemini 3.1 ProClaude Opus 4.6GPT-5Gemini 2.5 FlashClaude 4.5 SonnetDeepSeek V3.1Grok 4Llama 3 70BLlama 3 8B
    图像模型
    Nano BananaNano Banana 2Nano Banana ProGPT Image 2.5Flux 2 ProKrea 2 LargeKrea 2 MediumFlux 2 FlexFlux 2 DevFlux 1.1 Pro UltraGrok ImagineFlux Kontext MaxFlux Kontext ProSeedream 4Seedream 4.5Wan 2.2 ImageQwen ImageQwen Image Edit AnglesStable Diffusion XLGrok 2 ImageGen4 Image
    视频模型
    Kling V2.5 Turbo ProKling 2.6 ProGrok VideoVeo 3.1Veo 3.1 FastSeedance 1 ProSeedance 1 Pro FastSeedance 1 LiteSeedance 2.0Wan 2.6 I2VWan 2.6 T2VWan 2.5 I2VWan 2.5 T2VSora 2 ProSora 2Hailuo 2.3Hailuo 2.3 FastVideo-01 DirectorGen4 Aleph
    音频模型
    MusicGenMusic 1.5Music-01Lyria 2Speech-02 TurboSpeech-02 HDVoice CloningXTTS-v2
    工具模型
    Topaz Image UpscalerPrunaAI UpscaleCrystal UpscalerRemove BackgroundFace SwapImage FiltersProfessional HeadshotText RemovalInpaintAdd WatermarkVideo Upscale (Runway)Video Upscale (Topaz)Video Upscale (Bytedance)Lip Sync ProAuto CaptionReplace CharacterMotion Transfer
    Academy.models3d
    Hunyuan3D V3
    社交媒体内容
    产品摄影
    营销活动
    视频制作
    音频与音乐
    多步骤工作流
    图像到图像
    一致风格
    积分优化
    常见错误
    键盘快捷键
    示例画廊
    提示词库
    Seedance 2.0 for AEC
    企业版概述
    管理员控制台
    申请积分
    常见问题
    理解积分
    故障排除
    AI模型参考图像模型GPT Image 2.5

    GPT Image 2.5

    GPT Image 2.5 is OpenAI's precision-focused image model. It is built for premium visual work, extra fidelity on intricate detail, and edits that stay scoped to the instruction while preserving subject and composition across many rounds of revision.

    Overview

    PropertyValue
    ProviderOpenAI
    Cost40 (low), 200 (medium), 400 (high), 800 (extra high), 1200 (max)
    ModalityImage
    Prompt RequiredYes
    ModesText-to-image + image editing
    OutputBlue Image

    Endpoint Routing

    Armox automatically switches endpoint at runtime:

    • No input image -> openai/gpt-image-2.5/sunburst/text-to-image
    • With input image(s) -> openai/gpt-image-2.5/sunburst/edit

    You do not need to pick a separate model for edit mode.

    What It's Best For

    • Premium stills with fine typography and intricate detail
    • Instruction-scoped edits that keep the original subject and composition
    • Multi-round revisions with reference images
    • Transparent-background cutouts

    Inputs

    Required Inputs

    InputTypeDescription
    PromptYellow TextDescribe what to generate or how to edit the image

    Optional Inputs

    InputTypeDescription
    Input ImagesBlue ImageUp to 16 reference images. Attaching any image switches to edit mode

    Configuration

    SettingTypeDefaultDescription
    Image SizeselectautoUse Auto in edit mode to match the input image
    QualityselectmediumHigher settings increase detail, latency, and credit cost
    BackgroundselectautoAuto, opaque, or transparent
    Output Formatselectpngjpeg, png, or webp

    Quality

    OptionCredits
    Low40
    Medium200
    High400
    Extra High800
    Max1200
    Auto200

    Medium is 200 credits and High is 400. High is the default in Canvas and the Edit App. Extra High and Max cost more because they use more image tokens.

    Background

    Use Transparent with PNG output when you need a cutout. In the Edit App, background removal already requests a transparent background from this model.

    Output

    The model outputs a Blue Image that can connect to:

    • Other image models
    • Image tools such as upscalers
    • Video models that accept an image input

    Tips & Best Practices

    • Keep quality at High unless you want a cheaper or more expensive tier
    • Attach a clean source plus an annotated guide when editing in the Edit App or the Inpaint tool — GPT Image 2.5 follows the instruction instead of a binary inpainting mask
    • Prefer PNG when requesting a transparent background

    Related Models

    • Inpaint
    • Nano Banana 2
    • Nano Banana Pro
    • Flux 2 Pro
    上一页Nano Banana Pro
    下一页Flux 2 Pro

    准备好转变 您的创意工作流了吗?

    无需信用卡500免费积分

    本页内容

    OverviewEndpoint RoutingWhat It's Best ForInputsRequired InputsOptional InputsConfigurationQualityBackgroundOutputTips & Best PracticesRelated Models