alibaba/wan2.6-t2v

wan2.6-t2v
Docs
Schema

Wan text-to-video model generates videos from text with rich artistic styles. Wan 2.6 adds multi-shot narrative, automatic dubbing, and custom audio support.

$0.0900~$0.1400/sec
text-to-video

Input

Negative prompt describing unwanted content
Video content description, supports Chinese and English
Custom audio URL (supports wav/mp3, 3-30 seconds, ≤15MB)
Hint: Drag and drop files, paste from clipboard (Ctrl/Cmd+V), or provide a URL.
Video duration in seconds (integer)
5
Enable prompt intelligent rewriting
Random seed for reproducibility
Shot type
shot_type
Video resolution in format 'width*height'
1920*1080

Result

No results yet

Run the model to preview the output here.

README

Parameters

Name Description Type Required Enums
negative_prompt Negative prompt describing unwanted content string No -
prompt Video content description, supports Chinese and English string Yes -
audio_url Custom audio URL (supports wav/mp3, 3-30 seconds, ≤15MB) string No -
duration Video duration in seconds (integer) integer No 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
prompt_extend Enable prompt intelligent rewriting boolean No true, false
seed Random seed for reproducibility integer No -
shot_type Shot type string No single, multi
size Video resolution in format ‘width*height’ string No 1280*720, 720*1280, 960*960, 1088*832, 832*1088, 1920*1080, 1080*1920, 1440*1440, 1632*1248, 1248*1632

Pricing

Unit: $/sec

Dimension Pricing
size: 1080*1920 0.1400
size: 1088*832 0.0900
size: 1248*1632 0.1400
size: 1280*720 0.0900
size: 1440*1440 0.1400
size: 1632*1248 0.1400
size: 1920*1080 0.1400
size: 720*1280 0.1400
size: 832*1088 0.1400
size: 960*960 0.0900
  • alibaba/wan2.6-r2v: Wan 2.6 Reference-to-Video model generates videos from reference URLs (images/videos) with multi-character interaction and role-playing capabilities. Generates silent videos by default.
  • alibaba/wan2.6-r2v-flash: Wan 2.6 Reference-to-Video Flash model provides faster generation with support for audio/silent video switching. Ideal for quick previews and cost-effective video generation.
  • alibaba/wan2.6-i2v: Wan image-to-video model generates videos from prompts and images with cinematic quality. Wan 2.6 adds multi-shot narrative, automatic dubbing, and custom audio.
  • alibaba/wan2.6-i2v-flash: Wan image-to-video model generates videos from prompts and images with cinematic quality. Wan 2.6 adds multi-shot narrative, automatic dubbing, and custom audio.
  • alibaba/wan2.6-image: The wan-2.6-image supports image editing and mixed text-image output, meeting diverse generation and integration needs.
  • alibaba/wan2.6-t2i: The wan2.6-t2i supports the newly added synchronization interface, while allowing free selection of dimensions within the constraints of total pixel area and aspect ratio.

More in this series