LTX Video 2.5
供应商: Lightricks
视频
适合快速迭代、有原生音频的视频草稿
- 典型耗时
- 15-45s
- 参考输入
- 最多 2 个
- toolId
- ltx-video
输入模式
text-to-videoimage-to-video
变体
Fast Text to Video
Fast LTX text-to-video generation with optional native audio
text-to-video
Fast Image to Video
Animate one image quickly with LTX 2.5 Fast
image-to-video
First & Last Frame
Control the first and optional final frame for LTX generation
image-to-video
参数
| 参数 | 类型 | 默认值 | 取值 | 说明 |
|---|---|---|---|---|
| duration | select | 6 | 2 | 3 | 4 | 5 | 6 | 8 | 10 | 12 | 14 | 16 | 18 | 20 | Clip length. Longer clips cost more; re-quote after changing. |
| resolution | select | 1080p | 720p | 1080p | 2k | 4k | Higher resolution looks sharper and costs more. Keep one resolution across a series. |
| aspect_ratio | select | 9:16 | 16:9 | 9:16 | Output frame shape. Keep one ratio across a series. |
| generate_audio | toggle | true | — | Include AI-generated audio |
| fps | select | 25 | 24 | 25 | 48 | 50 | Frame rate. 24/25 fps reads as cinema; keep one rate across a series. |
定价
价格即将公布 —— 联系我们获取抢先体验价格
价格更新于: —
API 示例
POST /v1/generations — ltx-video
curl -X POST https://api.mukelabs.com/v1/generations \
-H "Authorization: Bearer $MUKE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"toolId": "ltx-video",
"inputMode": "text-to-video",
"prompt": "your prompt here",
"params": { "duration": "2" },
"references": [],
"idempotencyKey": "a-unique-key-per-task",
"subjectId": "your-user-id"
}'常见问题
如何在 Muke Labs 上调用 LTX Video 2.5?
提交 POST /v1/generations,toolId 为 "ltx-video",选择一种输入模式(text-to-video, image-to-video),然后轮询 GET /v1/generations/{jobId} 获取结果。
LTX Video 2.5 的价格是多少?
该模型的公开定价正在敲定 —— 联系我们获取抢先体验价格。所有任务均从预充值美元余额扣费,失败任务自动退款。
任务失败会怎样?
任务返回 "failed" 状态和类型化错误码,费用自动退回余额。
在哪里获取 API key?
在开发者门户(https://portal.muke.name)创建,然后作为 Bearer token 携带在每个请求上。
相关模型
视频
Auto Video Watermark Remover
Alibaba
上传视频即可自动去除水印、字幕和角标,无需手动画遮罩
video-upscale
视频
Digital Human - HeyGen
HeyGen
用媒体素材加上传音频生成或重配数字人口型视频
image-to-videoomni-reference
视频
Digital Human - InfiniTalk
InfiniTalk
用人像图片加人声音频生成数字人说话视频
image-to-video
视频
Google Omni Flash
支持原生音频的多模态视频生成、参考与编辑
text-to-videoimage-to-videoomni-reference+1