PopNowAPI 文件
主要內容

FLUX.1 Dev LoRA API 呼叫參考

經典的 FLUX.1 Dev，最多掛三個你自己的 LoRA

只要一把 PopNow API 金鑰，就能在自己的程式裡呼叫 FLUX.1 Dev 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
Black Forest Labs
產出
圖片
起價
2.7 點 每張圖 ($0.027)
一般耗時
約 15 秒
呼叫名稱

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

black-forest-labs/flux-1-dev-lora/text-to-image

價格

選項點數 (每張圖)美元
預設2.7$0.027

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, composition and lighting. If a LoRA has a trigger word, put it first.
aspect_ratio選填string1:11:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9, 9:21Output aspect ratio.
loras選填array<object>[]最多 3 項Up to three LoRA weight files, each with its own strength.
guidance_scale選填number3.50 到 20How closely the image follows the prompt, from 0 to 20.
steps選填integer281 到 50Denoising steps, from 1 to 50. Fewer steps return faster and a little softer.
output_format選填stringjpegjpeg, png, webpContainer of the returned image.
seed選填integer—0 到 2147483647Random 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。

POST /api/v1/jobs/createTask
curl -X POST "https://api.popnow.ai/api/v1/jobs/createTask" \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "black-forest-labs/flux-1-dev-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。

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"

編輯圖片

black-forest-labs/flux-1-dev-lora/edit

價格

選項點數 (每張圖)美元
預設2.7$0.027

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 whole image you want back; with a mask, describe what belongs in the white area.
image_url必填string (uri)——Source image to edit. The result keeps its shape.
mask_url選填string (uri)——Optional black-and-white mask the size of the source: white areas are redrawn, black areas are kept.
strength選填number0.80 到 1How far to move away from the source, from 0 to 1.
loras選填array<object>[]最多 3 項Up to three LoRA weight files, each with its own strength.
guidance_scale選填number3.50 到 20How closely the image follows the prompt, from 0 to 20.
steps選填integer281 到 50Denoising steps, from 1 to 50. Fewer steps return faster and a little softer.
output_format選填stringjpegjpeg, png, webpContainer of the returned image.
seed選填integer—0 到 2147483647Random 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_url 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。

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": "black-forest-labs/flux-1-dev-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_url": "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。

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"

接下來

本頁內容

總覽生成圖片編輯圖片接下來