Wan Flf2v

480p, 81 frames, from 240 credits
ae_wan_flf2v

Create a prompt-guided video that smoothly transitions from a starting image to an ending image.

VideoImage
480p, 81 frames, from 240 credits

Pricing

ConditionCharge
(if (resolution == not provided) then "720p", otherwise resolution == "480p") and (if (frame count == not provided) then 81, otherwise frame count == 81)240 credits/call
(if (resolution == not provided) then "720p", otherwise resolution == "480p") and (if (frame count == not provided) then 81, otherwise frame count >= 82) and (if (frame count == not provided) then 81, otherwise frame count <= 100)300 credits/call
(if (resolution == not provided) then "720p", otherwise resolution == "720p") and (if (frame count == not provided) then 81, otherwise frame count == 81)480 credits/call
(if (resolution == not provided) then "720p", otherwise resolution == "720p") and (if (frame count == not provided) then 81, otherwise frame count >= 82) and (if (frame count == not provided) then 81, otherwise frame count <= 100)600 credits/call

Each call selects one fixed price based on the request. The table lists the verified tiers. (if (resolution == not provided) then "720p", otherwise resolution == "480p") and (if (frame count == not provided) then 81, otherwise frame count == 81): 240 credits/call. (if (resolution == not provided) then "720p", otherwise resolution == "480p") and (if (frame count == not provided) then 81, otherwise frame count >= 82) and (if (frame count == not provided) then 81, otherwise frame count <= 100): 300 credits/call. (if (resolution == not provided) then "720p", otherwise resolution == "720p") and (if (frame count == not provided) then 81, otherwise frame count == 81): 480 credits/call. (if (resolution == not provided) then "720p", otherwise resolution == "720p") and (if (frame count == not provided) then 81, otherwise frame count >= 82) and (if (frame count == not provided) then 81, otherwise frame count <= 100): 600 credits/call.

Parameters

Optional parameters use the platform defaults when omitted.

ParameterTypeRequiredDescriptionDefault
request_bodyobjectYesNo parameter description.—
request_body.seedinteger | unknownNoRandom seed for reproducibility. If None, a random seed is chosen.—
request_body.shiftnumberNoShift parameter for video generation.5
request_body.promptstringYesThe text prompt to guide video generation.—
request_body.num_framesinteger | unknownNoNumber of frames to generate. Must be between 81 to 100 (inclusive). If the number of frames is greater than 81, the video will be generated with 1.25x more billing units.81
request_body.resolutionenum (480p | 720p)NoResolution of the generated video (480p or 720p). 480p is 0.5 billing units, and 720p is 1 billing unit.720p
request_body.guide_scalenumberNoClassifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality.5
request_body.accelerationenum (none | regular)NoAcceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'regular'.regular
request_body.aspect_ratioenum (auto | 16:9 | 9:16 | 1:1)NoAspect ratio of the generated video. If 'auto', the aspect ratio will be determined automatically based on the input image.auto
request_body.end_image_urlstringYesURL of the ending image. If the input image does not match the chosen aspect ratio, it is resized and center cropped.—
request_body.negative_promptstringNoNegative prompt for video generation.bright colors, overexposed, static, blurred details, subtitles, style, artwork, painting, picture, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, malformed limbs, fused fingers, still picture, cluttered background, three legs, many people in the background, walking backwards
request_body.start_image_urlstringYesURL of the starting image. If the input image does not match the chosen aspect ratio, it is resized and center cropped.—
request_body.frames_per_secondinteger | unknownNoFrames per second of the generated video. Must be between 5 to 24.16
request_body.num_inference_stepsintegerNoNumber of inference steps for sampling. Higher values give better quality but take longer.30
request_body.enable_safety_checkerbooleanNoIf set to true, the safety checker will be enabled.false
request_body.enable_prompt_expansionbooleanNoWhether to enable prompt expansion.false

Invocation example

Copy the request and explore its response example.

POST/agent-api/v1/tool/executeX-Api-Key

Submit first, then query with the returned task_id until the task completes.

Request coderequest.sh
curl --request POST \
  --url 'https://agentearth.ai/agent-api/v1/tool/execute?tool_name=ae_wan_flf2v' \
  --header "X-Api-Key: $AGENTEARTH_API_KEY" \
  --header 'Content-Type: application/json' \
  --data-raw '{
  "params": {
    "request_body": {
      "acceleration": "regular",
      "aspect_ratio": "9:16",
      "enable_prompt_expansion": false,
      "enable_safety_checker": true,
      "end_image_url": "https://v3b.fal.media/files/b/0ab1c05e/e7rBDv4tPOzaMLuJ0-_wU_CZ6SVp44.jpg",
      "fps": 16,
      "guide_scale": 5,
      "negative_prompt": "产品变形,鞋眼数量变化,毛领变色,鞋底变平,纹路消失,多出一只鞋,多出一只脚,第二个人,雪粒悬浮不落,悬浮,水珠滚落,文字,水印,字幕,影棚光,完美构图,CGI感,3D渲染感,AI绘画感,稳定器画面,过度锐化,HDR,美颜,滤镜,bright colors, overexposed, static, blurred details, subtitles, artwork, painting, still, worst quality, low quality, deformed, disfigured, malformed limbs, extra legs, walking backwards",
      "num_frames": 81,
      "num_inference_steps": 30,
      "prompt": "iPhone后置手机随手拍质感实拍视频,照片级写实,竖屏9:16,阴天6500K冷调漫射光,细雪飘落。低角度贴地固定机位,轻微手持呼吸抖动,视频中段出现一次约0.3秒的对焦犹豫(画面先略虚再合焦),曝光轻微跳动一次,边缘极轻暗角,轻微手机压缩噪点,构图略偏。动作:一只穿蓝色牛仔裤的脚穿着棕色雪地靴从画面上方缓缓踏入,鞋底压向湿雪地面,雪面下陷并压出浅浅水痕,几粒雪粒被鞋底短暂带起后落下,灰色毛绒靴领受压凹陷后自然回弹,裤脚随步伐滞后身体半拍,冷天极轻呼气白雾从画面边缘飘过。靴子落地后镜头缓慢推近约十厘米后停住。全程只有踩一步这一个动作,不切镜,不跑动,不出现第二只脚,靴子款式颜色细节全程不变。金属鞋眼有冷色反光,橡胶哑光,牛仔布斜纹可见。",
      "resolution": "720p",
      "start_image_url": "https://v3b.fal.media/files/b/0ab1c00d/LbKPHM55FcRAXtlshpeQ9_i57d9brg.jpg"
    }
  }
}'
Response exampleresponse.json
JSON
{
  "description": "task accepted; poll the result via query_tool with this task_id",
  "query_tool": "ae_get_result",
  "status": "created",
  "task_id": "35e88f67-b5b9-4be1-85eb-089a39142158"
}