Tool
Visit website →
Wan 2.6 - JXP
Wan 2.6 - jxp is a multimodal AI video generator that converts text, images, and reference video into audio‑synced, multi‑shot footage with automatic shot segmentation and reference‑based character control for visual consistency. Delivers single‑pass synchronized audio and multilingual lip‑sync, exports MP4/MOV/WEBM at 1080p/720p/480p and 16:9/9:16/1:1, and offers 5B/14B model sizes for consumer GPUs and richer 15s narratives for social, ads, and education.
Features
- 🧩 Multimodal conversion of text, images, and reference video into audio‑synced, multi‑shot video.
- 🧩 Automatic shot segmentation for structured storytelling.
- 🧩 Reference‑based character control for visual consistency across scenes.
- 🧩 Single‑pass synchronized audio with accurate multilingual lip sync.
- 🧩 Configurable model sizes (5B, 14B) and output options including resolutions (1080p/720p/480p), aspect ratios (16:9, 9:16, 1:1), and export formats (MP4, MOV, WEBM).
- Starter (one-time) plan : $10
- Starter (monthly) plan : $10/mo
- Premium (one-time) plan : $30
- Premium (monthly) plan : $30/mo
- Ultimate (one-time) plan : $99
- Ultimate (monthly) plan : $99/mo
Use Cases
- 🟢 Turn product descriptions and brand images into polished, audio-synced multi-shot product videos using a reference actor for consistent on-screen character control, automatic shot segmentation, multilingual lip-sync, and export-ready 1080p/720p/480p MP4/MOV/WEBM files.
- 🟢 Create localized training and e-learning videos from lesson scripts and slide images with automatic shot segmentation and multilingual lip-sync for global learners, while controlling on-screen presenters via reference video and exporting production-quality MP4/MOV/WEBM.
- 🟢 Produce eye-catching social media ads and short films by combining text, images, and reference clips to generate multi-shot, lip-synced visuals that match brand talent, optimize for different platforms with 1080p/720p/480p outputs, and rapidly iterate using automatic shot segmentation.