Black Friday

任意套餐全年立减 50%

立即领取
eroq

eroq api · image

Pictures your users
are allowed to ask for.

13 models behind one endpoint — photoreal, anime, fast drafts and instruction edits — from 10 credits a render. Reference images hold a face across generations, and what renders is a policy question here, not a filter's.

From 10 credits · failed renders refund themselves

注册即送 40 积分 · 无需绑卡

curl https://eroq.ai/v1/images/generations \
  -H "Authorization: Bearer $EROQ_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "eroq-krea2",
  "prompt": "portrait of a starship mechanic, grease-stained overalls, warm hangar light, 35mm",
  "negative_prompt": "blurry, extra fingers"
}'

模型

13 个模型,价格固定。

Eroq Uncensored

image

eroq-uncensored

eroq 自研的无审查写实模型:在可接受使用政策范围内,场景完全按你写的内容生成,支持 CFG、原图编辑和最多四张参考图,完全私密。

10 积分 / 张

Krea2

image

eroq-krea2

Krea 2 是 Studio 的清爽写实底模:快速 turbo 采样、CFG 控制、最多四张参考图、原图编辑,热启动时约十五秒出图,是日常使用的角色图片模型。

10 积分 / 张

Eroq One

image

eroq-one

Eroq One 是参考图模型:基于最多十张参考图进行生成和自然语言指令编辑,让角色、场景和产品保持一致。

10 积分 / 张,每多一张图片 +1

Anima

image

eroq-anime

Anima 生成动漫和风格化插画,在政策范围内无审查:两阶段高清细节渲染,支持 CFG 和负面提示词控制。

10 积分 / 张

Flash Image

image

eroq-flash-image

Flash Image 是快速多模态模型:风格范围广,支持批量生成。

10 积分 / 张

Flux Image

image

eroq-flux-image

Flux Image 是高保真写实模型:细节锐利,光线自然。

12 积分 / 张

GPT Image 2.5 Sunburst

image

gpt-image-2-5-sunburst

GPT Image 2.5 Sunburst 是 OpenAI 的旗舰图片模型:提示词遵循度高,构图干净,图中文字是全系列最清晰的。文生图,五种画幅,Creator 套餐起可用。

31 积分 / 张

GPT Image 2.5 Flare

image

gpt-image-2-5-flare

GPT Image 2.5 Flare 是 OpenAI 富有表现力的图片模型:与 Sunburst 同样精准,渲染更大胆、更有戏剧感,适合海报、主视觉和电影感剧照。文生图,五种画幅,Creator 套餐起可用。

31 积分 / 张

Nano Banana 2.1

image

nano-banana-2-1

Nano Banana 2.1 是 Google 的快速多模态图片模型:出图快,风格灵活,自然语言理解能力强。文生图,五种画幅,Creator 套餐起可用。

31 积分 / 张

Seedream 5.0 Pro

image

seedream-5-0-pro

Seedream 5.0 Pro 是字节跳动的旗舰图片模型:细节密集,质感丰富,摄影级真实感出色。文生图,五种画幅,Creator 套餐起可用。

36 积分 / 张

Nano Banana Pro

image

nano-banana-pro

Nano Banana Pro 是 Google 保真度最高的图片模型:在 Nano Banana 系列中细节最锐利、文字最准确、提示词理解最好。文生图,五种画幅,Creator 套餐起可用。

124 积分 / 张

Flux 3 Image

image

flux-3-image

Flux 3 Image 是 Black Forest Labs 最新的 FLUX:自然的写实渲染,出色的光影,图中文字可靠。文生图,五种画幅,Hobby 套餐起可用。

32 积分 / 张

Grok Imagine 2.0

image

grok-imagine-2-0

Grok Imagine 2.0 是 xAI 的图片模型:出图快、有个性,风格辨识度高。文生图,五种画幅,Hobby 套餐起可用。

32 积分 / 张

你能得到什么

Image,为真正上线的产品而打造。

13 engines, one call

Krea2 for clean photoreal, Eroq Uncensored for uncensored photoreal, Eroq One for up to ten references and instruction edits, Anima for anime and illustration, Flash Image for fast drafts and Flux Image for high-fidelity detail — plus OpenAI's GPT Image 2.5, Google's Nano Banana Pro and 2.1, ByteDance's Seedream 5.0 Pro, Black Forest Labs' Flux 3 and xAI's Grok Imagine 2.0. Same request shape for all — the model id is the only thing that changes, and the price follows it.

The same face, twice

Pass a reference photo and the render keeps the likeness. Save one as a Character and every call that mentions it inherits the face, which is the only reliable way to make a character look like themselves across a catalogue.

Inline or hosted

Responses come back as base64 by default, or set store and get a CDN URL instead — useful when the image is headed straight into a feed and you would rather not proxy a megabyte through your own server.

Framed, not cropped

Five aspect ratios render as real compositions rather than a square trimmed after the fact. A 9:16 portrait is composed vertical, which matters when the output is going into a story or a card.

Flat, and refunded

A flat price per model at every size, from 10 to 124 credits an image. A generation that fails refunds itself and the refund lands in your usage ledger, so you are never paying for a blank.

Uncensored, private, no real people

Eroq Uncensored, Eroq One and Anima render uncensored within the written policy, and private: true returns an image once and keeps it nowhere. The hard limits are absolute and enforced at the account level — no minors, no real identifiable people — and a request that crosses one returns content_blocked without a charge.

常见问题

长话短说。

What does an image cost? +

From 10 to 124 credits depending on the model, the same at every aspect ratio. There is no size surcharge and no token math.

Can I edit an existing photo? +

Yes — on Eroq One, Krea2 and Eroq Uncensored: send the picture as the first reference with edit: true and describe the change. Eroq One keeps the source picture's frame; Krea2 and Eroq Uncensored render the edit at the aspect you ask for, or retain the source ratio.

Which aspect ratios are available? +

1:1, 3:4, 4:3, 9:16 and 16:9. The 21:9 ratio is video only.

Is there an upscaler? +

No. Renders come out at the model's native size, so choose the aspect ratio you need up front rather than planning to enlarge afterwards.

Are generated images kept? +

Yes — every render is saved to your own creation library with the prompt and settings that made it, which is what makes a later remix possible. It is private to your workspace and you can delete any of it.

5 分钟完成第一次调用。

注册、创建密钥、粘贴快速入门代码。开始就送 40 积分,套餐 $15 起。