P-Image LoRA API 呼叫參考
P-Image 快速出圖和修圖,可掛一個你自己的 LoRA
只要一把 PopNow API 金鑰,就能在自己的程式裡呼叫 P-Image LoRA。以下列出要填的呼叫名稱、這個型號接受的每個輸入欄位、每次請求花多少點數,以及一段可以直接貼進終端機執行的請求。
參數說明直接取自型號的輸入 schema,目前只有英文。
總覽
- 開發商
- Pruna AI
- 產出
- 圖片
- 起價
- 0.9 點 每張圖 ($0.009)
- 一般耗時
- 約 8 秒
1 點 = 0.01 美元。任務受理時會先保留可能的最高費用,完成後依實際用量結算、無條件進位到整點,多保留的會退回;失敗的任務不扣點數。想在執行前知道確切數字,請先呼叫 POST /api/v1/jobs/quote。
生成圖片
pruna-ai/p-image-lora/text-to-image
價格
| 選項 | 點數 (每張圖) | 美元 |
|---|---|---|
預設 | 0.9 | $0.009 |
參數
| 欄位 | 型別 | 預設值 | 可用值 | 用途 |
|---|---|---|---|---|
prompt必填 | string | — | 最多 5000 個字元 | Describe the subject, clothing, place, light and lens in sentences. Put a LoRA trigger word first. |
aspect_ratio選填 | string | 1:1 | 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, custom | Output aspect ratio. Pick custom to set width and height yourself. |
width選填 | integer | — | 256 到 1440 | Output width in pixels for the custom aspect ratio, 256 to 1440 in steps of 16; 1024 when left out. |
height選填 | integer | — | 256 到 1440 | Output height in pixels for the custom aspect ratio, 256 to 1440 in steps of 16; 1024 when left out. |
loras選填 | array<object> | [] | 最多 1 項 | One LoRA weight file trained for P-Image text-to-image, with its strength. |
output_format選填 | string | jpeg | jpeg, png, webp | Container of the returned image. |
seed選填 | integer | — | 0 到 2147483647 | Random seed for controlled comparisons. |
請求範例
這段請求原樣就能執行,沒寫的欄位都用預設值。執行前請先把金鑰放進環境變數 POPNOW_API_KEY。
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": "pruna-ai/p-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"
}
}'回應會立刻帶回 taskId。之後用 GET /api/v1/jobs/recordInfo 取得結果,或在請求裡加上 callBackUrl 等候通知。
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=TASK_ID_FROM_CREATE_TASK" \
-H "Authorization: Bearer $POPNOW_API_KEY"編輯圖片
pruna-ai/p-image-lora/edit
價格
| 選項 | 點數 (每張圖) | 美元 |
|---|---|---|
預設 | 1.8 | $0.018 |
參數
| 欄位 | 型別 | 預設值 | 可用值 | 用途 |
|---|---|---|---|---|
prompt必填 | string | — | 最多 5000 個字元 | Say what to change and what to keep. With several images, refer to them as image 1, image 2 and so on. |
image_urls必填 | array<string (uri)> | — | 最多 5 項 | One to five source images. Without aspect_ratio the result follows the first one. |
aspect_ratio選填 | string | — | 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3 | Output aspect ratio. Leave it empty to follow the first source image. |
loras選填 | array<object> | [] | 最多 1 項 | One LoRA weight file trained for P-Image editing, with its strength. |
output_format選填 | string | jpeg | jpeg, png, webp | Container of the returned image. |
seed選填 | integer | — | 0 到 2147483647 | Random seed for controlled comparisons. |
請求範例
這段請求原樣就能執行,沒寫的欄位都用預設值。執行前請先把金鑰放進環境變數 POPNOW_API_KEY。
範例中的 image_urls 使用 PopNow 的範例素材,請換成你自己的公開 HTTPS 連結、上傳檔案或已儲存的素材。
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": "pruna-ai/p-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"
]
}
}'回應會立刻帶回 taskId。之後用 GET /api/v1/jobs/recordInfo 取得結果,或在請求裡加上 callBackUrl 等候通知。
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=TASK_ID_FROM_CREATE_TASK" \
-H "Authorization: Bearer $POPNOW_API_KEY"
