TL;DR
- Ideogram 4.5 已在 HiAPI 上线,调用名为
ideogram-v4.5/text-to-image。打开 Ideogram 4.5,可用下面的品牌字标、活动海报、横幅和包装标签提示词开始生成。 - 每张价格:
low$0.043、medium$0.086、high$0.3145。价格与档位。四组商业案例均使用medium,下方另有三档交通信息图。 - 把必须出现的文字完整放进双引号;生成后逐字检查小字和模型额外添加的文案。接入方法见API 接入指南。
四组提示词与对应成图
下方链接只预填提示词。打开后仍需选择图注中的 image_size 与 quality;一次请求生成一张。更换品牌或活动信息时,同时修改引号里的主标题、副标题和按钮文字,避免保留示例中的日期或品牌。
品牌字标:NORTHWIND ROASTERS

A clean minimalist wordmark logo for a specialty coffee brand, the text "NORTHWIND ROASTERS" set in an elegant high-contrast serif, a small compass-rose icon integrated above the letter N, warm cream background, centered, flat vector-style design, generous negative space
image_size: "square" · quality: "medium" · $0.086/张。品牌名在画面中央,罗盘图形放在整段字标上方,没有贴在字母 N 上。底行的成立年份与说明文字是额外添加的内容,使用前需要核对。
活动海报:ECHO VALLEY FEST

A vertical concert poster for an indie music festival, large headline text "ECHO VALLEY FEST" across the top, below it two lines reading "AUGUST 14-16" and "RIVERSIDE PARK", retro 1970s psychedelic palette of orange, magenta and teal, layered sunburst background, bold condensed type, high detail
image_size: "portrait_4_3" · quality: "medium" · $0.086/张。标题、日期和地点分别成行,底部另有乐队名单与入场信息。提示词没有指定这些额外内容,不能直接当成真实活动信息。
健身应用横幅:MOVE MORE.

A horizontal social media ad banner for a fitness app, left-aligned headline text "MOVE MORE." in heavy bold uppercase, a smaller line reading "Start your 7-day free trial", and a rounded call-to-action button with the text "GET THE APP", energetic gradient from lime green to deep blue, clean modern UI style
image_size: "landscape_16_9" · quality: "medium" · $0.086/张。标题和试用说明在左侧,按钮在右侧。若用于自己的应用,须同步替换提示词里的试用期限和按钮文案。
辣椒酱标签:EMBER & ASH

A product label for a bottle of artisanal hot sauce, brand name "EMBER & ASH" in a vintage woodcut serif, product line "SMOKED HABANERO" below it, a small badge reading "SMALL BATCH - 150ML", kraft-paper texture background with charcoal and ember-orange ink, symmetrical layout
image_size: "square_hd" · quality: "medium" · $0.086/张。主品牌名与产品名分成两层。圆形小标增加了提示词没有要求的字符,最下方也补了一行说明;印刷前应单独核对标签小字。
三档交通信息图:大标题与小段落要分别检查
下面三张均为 720 × 1280 的 PNG,使用相同的交通信息图提示词。原案例记录为同一 seed;这里不补写未记录的具体 seed 值。它们展示的是这组输出的差异,不能据此保证某个档位每次都会拼写正确。要尝试相同的竖版构图,请选择 image_size: "portrait_16_9",再选择对应的 quality;这是试用建议,不补写为原图未记录的请求参数。
low · $0.043/张

A dense informational poster titled "CITY TRANSIT GUIDE" with three labeled columns headed "BUS", "METRO" and "TRAM", a short line of body text under each heading, clean Swiss grid layout, red and black ink on off-white paper, flat vector infographic style
大标题和三列标题可辨,路线标记出现重复。
medium · $0.086/张

A dense informational poster titled "CITY TRANSIT GUIDE" with three labeled columns headed "BUS", "METRO" and "TRAM", a short line of body text under each heading, clean Swiss grid layout, red and black ink on off-white paper, flat vector infographic style
三列说明和路线示意分别排列。仍需检查小字,不能把生成的交通描述当作真实路线资料。
high · $0.3145/张

A dense informational poster titled "CITY TRANSIT GUIDE" with three labeled columns headed "BUS", "METRO" and "TRAM", a short line of body text under each heading, clean Swiss grid layout, red and black ink on off-white paper, flat vector infographic style
大标题和图标清楚,但正文段落出现明显的拼词错误。提高档位不能代替文字校对。
用 API 提交字标提示词
示例明确指定 quality: "medium",每张 $0.086,num_images 为 1。enable_prompt_expansion 为 true 时允许扩展提示词;如果要评估扩展对文案的影响,可以单独改变这个字段再比较输出。下方 600 秒是示例程序的本地等待上限,不是模型耗时承诺;超时后保留 taskId 继续查,不要直接重复提交。
curl -s -X POST "https://api.hiapi.ai/v1/tasks" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "ideogram-v4.5/text-to-image",
"input": {
"prompt": "A clean minimalist wordmark logo for a specialty coffee brand, the text \"NORTHWIND ROASTERS\" set in an elegant high-contrast serif, a small compass-rose icon integrated above the letter N, warm cream background, centered, flat vector-style design, generous negative space",
"quality": "medium",
"image_size": "square",
"num_images": 1,
"enable_prompt_expansion": true
}
}'
import os
import time
import requests
base = "https://api.hiapi.ai/v1/tasks"
headers = {"Authorization": f"Bearer {os.environ['HIAPI_API_KEY']}"}
payload = {
"model": "ideogram-v4.5/text-to-image",
"input": {
"prompt": "A clean minimalist wordmark logo for a specialty coffee brand, the text \"NORTHWIND ROASTERS\" set in an elegant high-contrast serif, a small compass-rose icon integrated above the letter N, warm cream background, centered, flat vector-style design, generous negative space",
"quality": "medium",
"image_size": "square",
"num_images": 1,
"enable_prompt_expansion": True
}
}
response = requests.post(base, headers=headers, json=payload, timeout=30)
response.raise_for_status()
task_id = response.json()["data"]["taskId"]
deadline = time.monotonic() + 600
while time.monotonic() < deadline:
response = requests.get(f"{base}/{task_id}", headers=headers, timeout=30)
response.raise_for_status()
task = response.json()["data"]
if task["status"] == "success":
print(task["output"][0]["url"])
break
if task["status"] == "fail":
raise RuntimeError(task)
time.sleep(2)
else:
raise TimeoutError(f"Local wait ended; keep taskId {task_id} for later queries")
常见问题
可以指定任意像素宽高吗?
使用 image_size 的六个预设:square_hd、square、portrait_4_3、portrait_16_9、landscape_4_3、landscape_16_9。请求不接受单独的 width 和 height。
一次可以生成多张吗?
当前 num_images 只能为 1。需要多个候选时分别提交任务,每张按选定的 quality 计费。
如何修改已有图片里的字?
使用 ideogram-v4.5/image-to-image,参数和价格应按编辑模式选择,见参考图编辑案例与价格与档位。不要直接把文生图的价格和字段搬到编辑请求。
哪个档位能保证所有文字正确?
没有这样的保证。先核对引号里的文字,再检查模型额外添加的小字;正式活动信息和包装说明应逐字确认。
复制字标提示词,打开 Ideogram 4.5,选择 square 与 medium 开始。



