模型市场支持← 返回应用

Wan

Wan 模型通过一个统一的异步任务 API 调用。用 POST /api/generate 发起任务，再轮询 GET /api/generate/{taskId} 直到完成。本系列提供 19 个端点。

概览

每个端点共享相同的外层结构 —— 只有 model 和 input 字段不同。可在模型市场的 playground 中运行任意一个。

认证

在 /api-keys 创建 API 密钥，然后作为 Bearer token 发送。已登录时从浏览器发起的请求也可通过会话 cookie 生效。

Authorization: Bearer <YOUR_API_KEY>

创建任务

POST
POST https://api.lithovas.com/api/generate

请求体：{ "model": "<slug>", "input": { … } }

响应：{ "taskId": "<id>", "state": "waiting" }

查询结果

GET
GET https://api.lithovas.com/api/generate/<taskId>

响应：{ "taskId", "state": "waiting" | "success" | "fail", "resultUrls": [ … ], "creditsConsumed", "failMsg", "balance" }

异步
创建任务返回 200 只表示任务已被接受 —— 并非已完成。请轮询此端点，直到 state 变为 success 或 fail。失败任务不计费。

端点

模型任务model slug
Wan 2.7 ImageText to Imagewan/2-7-image
Wan 2.7 Image ProText to Imagewan/2-7-image-pro
Wan 2.2 A14BImage to Videowan/2-2-a14b-image-to-video-turbo
Wan 2.2 A14BSpeech to Videowan/2-2-a14b-speech-to-video-turbo
Wan 2.2 A14BText to Videowan/2-2-a14b-text-to-video-turbo
Wan 2.2 Animate MoveLip Syncwan/2-2-animate-move
Wan 2.2 Animate ReplaceLip Syncwan/2-2-animate-replace
Wan 2.6Image to Videowan/2-6-image-to-video
Wan 2.6Text to Videowan/2-6-text-to-video
Wan 2.6Video to Videowan/2-6-video-to-video
Wan 2.6 FlashImage to Videowan/2-6-flash-image-to-video
Wan 2.6 FlashVideo to Videowan/2-6-flash-video-to-video
Wan 2.5Image to Videowan/2-5-image-to-video
Wan 2.5Text to Videowan/2-5-text-to-video
Wan 2.7Text to Videowan/2-7-text-to-video
Wan 2.7Image to Videowan/2-7-image-to-video
Wan 2.7 VideoeditVideo Editingwan/2-7-videoedit
Wan 2.7 R2VVideo to Videowan/2-7-r2v
Wan 3.0 VideoText to Videowan3.0-video

Wan 2.7 Image · Text to Image

POSTText to Imagewan/2-7-image
input 字段
promptstring必填

Prompt for image generation or editing (max 5000 chars)

input_urlsarray<string>可选

Array of input image URLs (max 9 images)

aspect_ratioenum<string>可选

Output aspect ratio when no image input provided

enable_sequentialboolean可选

Enable sequential/group image mode

ninteger可选

Number of images (1-4 default; 1-12 if sequential)

resolutionenum<string>可选

Output resolution

thinking_modeboolean可选

Enable thinking mode (not with sequential or input images)

color_palettearray<object>可选

Custom color theme; 3-10 colors each with hex and ratio

bbox_listarray<array>可选

Interactive editing bounding boxes; max 2 per image [x1,y1,x2,y2]

watermarkboolean可选

Add watermark to generated images

seedinteger可选

Random seed; range 0-2147483647

nsfw_checkerboolean可选

Content filtering toggle; disabled if false

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan/2-7-image",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "input_urls": [
      "https://example.com/file"
    ],
    "aspect_ratio": "1:1",
    "enable_sequential": false,
    "n": 4,
    "resolution": "2K",
    "thinking_mode": false,
    "color_palette": [],
    "bbox_list": "example",
    "watermark": false,
    "seed": 0,
    "nsfw_checker": false
  }
}'

Wan 2.7 Image Pro · Text to Image

POSTText to Imagewan/2-7-image-pro
input 字段
promptstring必填

Prompt for image generation or editing (max 5000 chars)

input_urlsarray<string>可选

Array of input image URLs (max 9 items)

aspect_ratioenum<string>可选

Output aspect ratio when no image input provided

enable_sequentialboolean可选

Enable sequential/group image mode

ninteger可选

Number of images (1-4 default; 1-12 if sequential)

resolutionenum<string>可选

Output resolution (4K for text-to-image only)

thinking_modeboolean可选

Enable thinking mode (text-to-image only)

color_palettearray<object>可选

Custom color theme (3-10 colors, 8 recommended)

bbox_listarray<array>可选

Interactive editing bounding boxes (max 2 per image)

watermarkboolean可选

Add watermark to output

seedinteger可选

Random seed (range 0-2147483647)

nsfw_checkerboolean可选

Disable content filtering when set to false

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan/2-7-image-pro",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "input_urls": [
      "https://example.com/file"
    ],
    "aspect_ratio": "1:1",
    "enable_sequential": false,
    "n": 4,
    "resolution": "2K",
    "thinking_mode": false,
    "color_palette": [],
    "bbox_list": "example",
    "watermark": false,
    "seed": 0,
    "nsfw_checker": false
  }
}'

Wan 2.2 A14B · Image to Video

POSTImage to Videowan/2-2-a14b-image-to-video-turbo
input 字段
image_urlstring必填

URL of input image; resized and center cropped if aspect ratio mismatch

promptstring必填

Text guidance for video generation (max 5000 chars)

resolutionenum<string>可选

Output video resolution

enable_prompt_expansionboolean可选

Use LLM to expand the prompt with additional details

seednumber可选

Random seed for reproducibility (0-2147483647)

accelerationenum<string>可选

Acceleration level; more acceleration is faster but lower quality

nsfw_checkerboolean可选

If false, content filtering disabled

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan/2-2-a14b-image-to-video-turbo",
  "input": {
    "image_url": "https://example.com/input.jpg",
    "prompt": "Animate the image with natural motion, subtle camera movement, and cinematic lighting.",
    "resolution": "720p",
    "enable_prompt_expansion": false,
    "seed": 0,
    "acceleration": "none",
    "nsfw_checker": false
  }
}'

Wan 2.2 A14B · Speech to Video

POSTSpeech to Videowan/2-2-a14b-speech-to-video-turbo
input 字段
promptstring必填

Text prompt for video generation (max 5000 chars)

image_urlstring必填

Input image URL; resized/center-cropped if needed (max 10MB)

audio_urlstring必填

Audio file URL for speech sync (max 10MB)

num_framesnumber可选

Frame count to generate; 40-120, multiple of 4

frames_per_secondnumber可选

Video FPS (4-60)

resolutionenum<string>可选

Output video resolution

negative_promptstring可选

Negative prompt to exclude content (max 500 chars)

seedinteger可选

Random seed for reproducible results

num_inference_stepsnumber可选

Sampling steps for quality/speed tradeoff (2-40)

guidance_scalenumber可选

Prompt adherence strength; 1-10 scale

shiftnumber可选

Video shift parameter (1.0-10.0)

nsfw_checkerboolean可选

Enable/disable content filtering

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan/2-2-a14b-speech-to-video-turbo",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "image_url": "https://example.com/input.jpg",
    "audio_url": "https://example.com/reference.mp3",
    "num_frames": 80,
    "frames_per_second": 16,
    "resolution": "480p",
    "negative_prompt": "example",
    "seed": 42,
    "num_inference_steps": 27,
    "guidance_scale": 3.5,
    "shift": 5,
    "nsfw_checker": false
  }
}'

Wan 2.2 A14B · Text to Video

POSTText to Videowan/2-2-a14b-text-to-video-turbo
input 字段
promptstring必填

Text prompt to guide video generation (max 5000 chars)

resolutionenum<string>可选

Generated video resolution setting

aspect_ratioenum<string>可选

Video output aspect ratio format

enable_prompt_expansionboolean可选

LLM-based prompt expansion for additional detail

seednumber可选

Random seed for reproducible results (0-2147483647)

accelerationenum<string>可选

Trade-off control between speed and quality

nsfw_checkerboolean可选

Toggle content filtering; false disables filtering

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan/2-2-a14b-text-to-video-turbo",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "enable_prompt_expansion": false,
    "seed": 0,
    "acceleration": "none",
    "nsfw_checker": false
  }
}'

Wan 2.2 Animate Move · Lip Sync

POSTLip Syncwan/2-2-animate-move
input 字段
video_urlstring必填

URL of the input video (mp4, quicktime, matroska; max 10MB)

image_urlstring必填

URL of input image; resized/center-cropped if aspect ratio mismatch (max 10MB)

resolutionenum<string>可选

Output video resolution selection

nsfw_checkerboolean可选

Enable/disable content filtering

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan/2-2-animate-move",
  "input": {
    "video_url": "https://example.com/reference.mp4",
    "image_url": "https://example.com/input.jpg",
    "resolution": "480p",
    "nsfw_checker": false
  }
}'

Wan 2.2 Animate Replace · Lip Sync

POSTLip Syncwan/2-2-animate-replace
input 字段
video_urlstring必填

URL of the input video (mp4, quicktime, matroska; max 10MB)

image_urlstring必填

URL of the input image (jpeg, png, webp; max 10MB)

resolutionenum<string>可选

Resolution of the generated video output

nsfw_checkerboolean可选

Enable/disable content filtering on results

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan/2-2-animate-replace",
  "input": {
    "video_url": "https://example.com/reference.mp4",
    "image_url": "https://example.com/input.jpg",
    "resolution": "480p",
    "nsfw_checker": false
  }
}'

Wan 2.6 · Image to Video

POSTImage to Videowan/2-6-image-to-video
input 字段
promptstring必填

Text prompts for video generation; supports Chinese and English (max 5000 chars)

image_urlsarray<string>必填

Input image files (JPEG/PNG/WebP, max 10MB, min 256x256px)

durationenum<string>可选

Duration of generated video in seconds

resolutionenum<string>可选

Video resolution tier

nsfw_checkerboolean可选

Content filtering; disabled when false

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan/2-6-image-to-video",
  "input": {
    "prompt": "Animate the image with natural motion, subtle camera movement, and cinematic lighting.",
    "image_urls": [
      "https://example.com/input.jpg"
    ],
    "duration": "5",
    "resolution": "1080p",
    "nsfw_checker": false
  }
}'

Wan 2.6 · Text to Video

POSTText to Videowan/2-6-text-to-video
input 字段
promptstring必填

Text prompts for video generation; supports Chinese and English (max 5000 chars)

durationenum<string>可选

Length of generated video in seconds

resolutionenum<string>可选

Video resolution tier

nsfw_checkerboolean可选

Toggles content filtering; false returns unfiltered output

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan/2-6-text-to-video",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "duration": "5",
    "resolution": "1080p",
    "nsfw_checker": false
  }
}'

Wan 2.6 · Video to Video

POSTVideo to Videowan/2-6-video-to-video
input 字段
promptstring必填

Text prompt for video transformation (2-5000 chars, Chinese/English)

video_urlsarray<string>必填

URLs of source videos to transform (max 3, MP4/QuickTime/Matroska, max 10MB each)

durationenum<string>可选

Generated video duration in seconds

resolutionenum<string>可选

Output video resolution tier

nsfw_checkerboolean可选

Toggle content filtering; false disables filtering

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan/2-6-video-to-video",
  "input": {
    "prompt": "Restyle the source footage with richer lighting, cleaner motion, and a cinematic grade.",
    "video_urls": [
      "https://example.com/reference.mp4"
    ],
    "duration": "5",
    "resolution": "1080p",
    "nsfw_checker": false
  }
}'

Wan 2.6 Flash · Image to Video

POSTImage to Videowan/2-6-flash-image-to-video
input 字段
promptstring必填

Text prompts for video generation (max 1500 chars)

image_urlsarray<string>必填

List of image URLs (min 256x256px, max 1 image, 10MB)

durationenum<string>可选

Video duration in seconds

resolutionenum<string>可选

Output video resolution tier

audioboolean必填

Whether to generate video with audio

multi_shotsboolean可选

Controls shot composition style (single vs multiple shots)

nsfw_checkerboolean可选

Enable/disable content filtering (default disabled)

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan/2-6-flash-image-to-video",
  "input": {
    "prompt": "Animate the image with natural motion, subtle camera movement, and cinematic lighting.",
    "image_urls": [
      "https://example.com/input.jpg"
    ],
    "duration": "5",
    "resolution": "1080p",
    "audio": false,
    "multi_shots": false,
    "nsfw_checker": false
  }
}'

Wan 2.6 Flash · Video to Video

POSTVideo to Videowan/2-6-flash-video-to-video
input 字段
promptstring必填

Text prompt for video generation (2-1500 chars, Chinese/English)

video_urlsarray<string>必填

URLs of videos to transform (max 3 items, up to 10MB each)

durationenum<string>可选

Generated video length in seconds

resolutionenum<string>可选

Video resolution tier

audioboolean可选

Whether to generate video with audio

multi_shotsboolean可选

Controls shot composition style (single vs multiple shots)

nsfw_checkerboolean可选

Content filtering toggle; false disables filtering

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan/2-6-flash-video-to-video",
  "input": {
    "prompt": "Restyle the source footage with richer lighting, cleaner motion, and a cinematic grade.",
    "video_urls": [
      "https://example.com/reference.mp4"
    ],
    "duration": "5",
    "resolution": "1080p",
    "audio": false,
    "multi_shots": false,
    "nsfw_checker": false
  }
}'

Wan 2.5 · Image to Video

POSTImage to Videowan/2-5-image-to-video
input 字段
promptstring必填

Text describing desired video motion (max 800 chars)

image_urlstring必填

URL of image to use as first frame (JPEG/PNG/WebP, max 10MB)

durationenum<string>必填

Generated video duration in seconds

resolutionenum<string>可选

Video output resolution

negative_promptstring可选

Content to avoid in generation (max 500 chars)

enable_prompt_expansionboolean可选

Enable LLM-based prompt rewriting

seedinteger可选

Random seed for reproducible results

nsfw_checkerboolean可选

Content filtering; disabled when false

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan/2-5-image-to-video",
  "input": {
    "prompt": "Animate the image with natural motion, subtle camera movement, and cinematic lighting.",
    "image_url": "https://example.com/input.jpg",
    "duration": "5",
    "resolution": "720p",
    "negative_prompt": "example",
    "enable_prompt_expansion": false,
    "seed": 42,
    "nsfw_checker": false
  }
}'

Wan 2.5 · Text to Video

POSTText to Videowan/2-5-text-to-video
input 字段
promptstring必填

Text prompt for video generation; supports Chinese and English (max 800 chars)

durationenum<string>必填

Duration of the generated video in seconds

aspect_ratioenum<string>可选

Video aspect ratio (landscape, portrait, or square)

resolutionenum<string>可选

Video resolution tier

negative_promptstring可选

Content to avoid in generation (max 500 chars)

enable_prompt_expansionboolean可选

Enable LLM prompt rewriting for improved short prompt results

seedinteger可选

Random seed for reproducible results

nsfw_checkerboolean可选

Disables content filtering when false

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan/2-5-text-to-video",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "duration": "5",
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "negative_prompt": "example",
    "enable_prompt_expansion": false,
    "seed": 42,
    "nsfw_checker": false
  }
}'

Wan 2.7 · Text to Video

POSTText to Videowan/2-7-text-to-video
input 字段
promptstring必填

Positive prompt (1-5000 chars)

negative_promptstring可选

Negative prompt (max 500 chars)

audio_urlstring可选

Custom audio track URL for video generation

resolutionenum<string>可选

Video output resolution

ratioenum<string>可选

Video aspect ratio

durationinteger可选

Video length in seconds (2-15)

prompt_extendboolean可选

Enable intelligent prompt rewriting

watermarkboolean可选

Add AI-generated watermark to video

seedinteger可选

Random seed for reproducibility (0-2147483647)

nsfw_checkerboolean可选

Content filtering toggle; disables safety filters when false

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan/2-7-text-to-video",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "negative_prompt": "example",
    "audio_url": "https://example.com/reference.mp3",
    "resolution": "1080p",
    "ratio": "16:9",
    "duration": 5,
    "prompt_extend": true,
    "watermark": false,
    "seed": 42,
    "nsfw_checker": false
  }
}'

Wan 2.7 · Image to Video

POSTImage to Videowan/2-7-image-to-video
input 字段
promptstring必填

Positive prompt (max 5000 chars)

negative_promptstring可选

Negative prompt (max 500 chars)

first_frame_urlstring可选

First frame image URL

last_frame_urlstring可选

Last frame image URL

first_clip_urlstring可选

First clip video URL for video continuation

driving_audio_urlstring可选

Driving audio URL

resolutionenum<string>可选

Video resolution output

durationinteger可选

Output video duration in seconds (2-15)

prompt_extendboolean可选

Enable intelligent prompt rewriting

watermarkboolean可选

Add AI-generated watermark to video

seedinteger可选

Random seed (0-2147483647)

nsfw_checkerboolean可选

Content filtering toggle

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan/2-7-image-to-video",
  "input": {
    "prompt": "Animate the image with natural motion, subtle camera movement, and cinematic lighting.",
    "negative_prompt": "example",
    "first_frame_url": "example",
    "last_frame_url": "example",
    "first_clip_url": "example",
    "driving_audio_url": "https://example.com/reference.mp3",
    "resolution": "1080p",
    "duration": 5,
    "prompt_extend": true,
    "watermark": false,
    "seed": 42,
    "nsfw_checker": false
  }
}'

Wan 2.7 Videoedit · Video Editing

POSTVideo Editingwan/2-7-videoedit
input 字段
promptstring可选

Text prompt describing expected elements and visual features (max 5000 chars)

negative_promptstring可选

Content that should not appear in the video (max 500 chars)

video_urlstring必填

URL of source video to edit (mp4/mov, 2-10s, 240-4096px)

reference_imagestring可选

Optional reference image for character/clothing/style guidance

resolutionenum<string>可选

Output video resolution tier

aspect_ratioenum<string>可选

Output video aspect ratio

durationinteger可选

Output duration in seconds (0 or 2-10; 0 uses full input)

audio_settingenum<string>可选

Model decides whether to regenerate audio or keep original

prompt_extendboolean可选

Whether to enable prompt rewriting/expansion

watermarkboolean可选

Add AI generated watermark to lower-right corner

seedinteger可选

Random seed (0-2147483647)

nsfw_checkerboolean可选

Enable/disable content filtering (defaults to disabled)

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan/2-7-videoedit",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "negative_prompt": "example",
    "video_url": "https://example.com/reference.mp4",
    "reference_image": "https://example.com/input.jpg",
    "resolution": "1080p",
    "aspect_ratio": "16:9",
    "duration": 0,
    "audio_setting": "auto",
    "prompt_extend": true,
    "watermark": false,
    "seed": 42,
    "nsfw_checker": false
  }
}'

Wan 2.7 R2V · Video to Video

POSTVideo to Videowan/2-7-r2v
input 字段
promptstring必填

Text describing desired video elements (max 5000 chars)

negative_promptstring可选

Unwanted elements to exclude (max 500 chars)

reference_imagearray<string>可选

URLs of reference images (max 5 total with videos)

reference_videoarray<string>可选

URLs of reference videos (max 5 total with images)

first_framestring可选

URL of first frame image; overrides aspect_ratio

reference_voicestring可选

Audio URL for voice timbre (wav/mp3, 1-10 sec, <=15MB)

resolutionenum<string>可选

Output video resolution tier

aspect_ratioenum<string>可选

Output video aspect ratio

durationinteger可选

Video duration in seconds (2-10)

prompt_extendboolean可选

Enable prompt rewriting for expansion

watermarkboolean可选

Add AI generated watermark to lower-right corner

seedinteger可选

Random seed for reproducibility (0-2147483647)

nsfw_checkerboolean可选

Enable content filtering (disabled when false)

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan/2-7-r2v",
  "input": {
    "prompt": "Restyle the source footage with richer lighting, cleaner motion, and a cinematic grade.",
    "negative_prompt": "example",
    "reference_image": [
      "https://example.com/input.jpg"
    ],
    "reference_video": [
      "https://example.com/reference.mp4"
    ],
    "first_frame": "example",
    "reference_voice": "example",
    "resolution": "1080p",
    "aspect_ratio": "16:9",
    "duration": 5,
    "prompt_extend": true,
    "watermark": false,
    "seed": 42,
    "nsfw_checker": false
  }
}'

Wan 3.0 Video · Text to Video

POSTText to Videowan3.0-video
input 字段
promptstring可选

Text prompt describing the desired video. Supports Chinese and English, up to 20,000 characters.

first_framestring可选

Optional first-frame image URL for image-to-video.

last_framestring可选

Optional last-frame image URL. Use together with first_frame for first-to-last-frame video.

reference_image_urlsarray<string>可选

Reference image URLs for all-in-one reference mode. Refer to them as Image1, Image2, etc. in the prompt.

reference_video_urlsarray<string>可选

Reference video URLs for all-in-one reference mode. Refer to them as Video1, Video2, etc. in the prompt.

reference_audio_urlsarray<string>可选

Reference audio URLs for voice, music, or ambience guidance.

file_urlstring可选

Optional public file URL, such as a PPTX, PDF, or other supported media file.

link_urlstring可选

Optional web link used as source material.

resolutionenum<string>可选

Output video resolution tier.

ratioenum<string>可选

Output aspect ratio. adaptive lets the model choose from the input and prompt.

durationinteger可选

Output duration in seconds. Use 2-30 for generated clips, or -1 for smart duration mode.

audioboolean可选

Whether the generated video includes audio.

seedinteger可选

Random seed from 0 to 2147483647.

watermarkboolean可选

Whether to add a watermark.

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan3.0-video",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "first_frame": "example",
    "last_frame": "example",
    "reference_image_urls": [
      "https://example.com/input.jpg"
    ],
    "reference_video_urls": [
      "https://example.com/reference.mp4"
    ],
    "reference_audio_urls": [
      "https://example.com/reference.mp3"
    ],
    "file_url": "example",
    "link_url": "example",
    "resolution": "1080P",
    "ratio": "adaptive",
    "duration": 5,
    "audio": true,
    "seed": 42,
    "watermark": false
  }
}'