PopNowAPI 文档
正文

MiniMax H3 Image LoRA API 调用参考

H3 出图和改图，最多挂三个你自己的 LoRA

用一个 PopNow API 密钥，就能在自己的代码里调用 MiniMax H3 Image LoRA。下面列出要填的调用名、这个型号接受的每个输入字段、每次请求花多少积分，以及一段可以直接粘进终端运行的请求。

参数说明直接取自型号的输入 schema，暂时只有英文。

一览

出品方
MiniMax
产出
图片
起价
6.3 积分 每张图 ($0.063)
一般耗时
约 13 秒
调用名

1 积分 = 0.01 美元。任务受理时先冻结可能的最高费用，完成后按实际用量结算、向上取整到整积分，多冻的退回；失败的任务不扣积分。想在运行前知道确切数字，先调 POST /api/v1/jobs/quote。

生成图片

minimax/h3-image-lora/text-to-image

价格

选项积分 (每张图)美元
1k6.3$0.063
2k13.5$0.135

参数

字段类型默认值取值范围作用
prompt必填string—最多 5000 个字符Describe the subject, composition and lighting.
aspect_ratio可选string1:11:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9, 9:21, 2:1, 1:2, 3:1, 1:3, 5:4, … (+1)Output aspect ratio.
resolution可选string1k1k, 2kOutput resolution tier: 1k is about one megapixel, 2k about four.
loras可选array<object>[]最多 3 项Up to three LoRA weight files trained for MiniMax H3, each with its own strength.
output_format可选stringjpegjpeg, png, webpContainer of the returned image.
seed可选integer—0 到 2147483647Random seed for controlled comparisons.

请求示例

这段请求原样就能运行，没写的字段都用默认值。运行前先把密钥放进环境变量 POPNOW_API_KEY。

POST /api/v1/jobs/createTask?wait=60
curl -X POST "https://api.popnow.ai/api/v1/jobs/createTask?wait=60" \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "minimax/h3-image-lora/text-to-image",
  "input": {
    "prompt": "A cozy reading nook beside a rain-streaked window, warm lamp light, a sleeping orange cat on a knitted blanket, soft film grain",
    "resolution": "1k"
  }
}'

响应里会立刻带回 taskId。之后用 GET /api/v1/jobs/recordInfo 取结果，或者在请求里加上 callBackUrl 等通知。

GET /api/v1/jobs/recordInfo
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=TASK_ID_FROM_CREATE_TASK" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

编辑图片

minimax/h3-image-lora/edit

价格

选项积分 (每张图)美元
1k8.1$0.081
2k18.9$0.189

参数

字段类型默认值取值范围作用
prompt必填string—最多 5000 个字符Say what to change. Refer to the references as <Picture 1>, <Picture 2> and so on.
image_urls必填array<string (uri)>—最多 9 项One to nine reference images. Each one after the first raises the quote.
aspect_ratio可选string—1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9, 9:21, 2:1, 1:2, 3:1, 1:3, 5:4, … (+1)Output aspect ratio. Leave it unset to follow the first reference image.
resolution可选string1k1k, 2kOutput resolution tier: 1k is about one megapixel, 2k about four.
loras可选array<object>[]最多 3 项Up to three LoRA weight files trained for MiniMax H3, each with its own strength.
output_format可选stringjpegjpeg, png, webpContainer of the returned image.
seed可选integer—0 到 2147483647Random seed for controlled comparisons.

请求示例

这段请求原样就能运行，没写的字段都用默认值。运行前先把密钥放进环境变量 POPNOW_API_KEY。

示例里的 image_urls 用的是 PopNow 的示例素材，换成你自己的公开 HTTPS 链接、上传文件或已保存的素材即可。

POST /api/v1/jobs/createTask?wait=60
curl -X POST "https://api.popnow.ai/api/v1/jobs/createTask?wait=60" \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "minimax/h3-image-lora/edit",
  "input": {
    "prompt": "Change the orange jacket to deep forest green and add soft golden-hour light; keep the face, pose and background unchanged",
    "image_urls": [
      "https://media.popnow.ai/influencer/examples/marco.webp"
    ],
    "resolution": "1k"
  }
}'

响应里会立刻带回 taskId。之后用 GET /api/v1/jobs/recordInfo 取结果，或者在请求里加上 callBackUrl 等通知。

GET /api/v1/jobs/recordInfo
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=TASK_ID_FROM_CREATE_TASK" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

接下来

本页内容

一览生成图片编辑图片接下来