v1.6.0

SparkAudio/Spark-TTSv1.6.0Apr 20, 2026by shrimbly

AI Summary

This release enhances Seedance 2.0 and 2.0 Fast image-to-video nodes by introducing richer media input options and resolving logic errors with reference-only runs.

Key Highlights

Added support for Last Frame, Reference Images (up to 9), Reference Videos (up to 3), and Reference Audio (up to 3) inputs for Seedance 2 I2V.
Fixed issue where reference-only runs were incorrectly rejected by the Kie backend.
Improved handle descriptions to document mutual-exclusivity rules for First/Last Frame vs Reference Images.

New Features

Richer media input handles for Seedance 2 I2V generation nodes

Full Release Notes

### Added

- **Seedance 2 I2V: richer media inputs** — The ByteDance Seedance 2.0 and 2.0 Fast image-to-video nodes now expose Last Frame, Reference Images (up to 9), Reference Videos (up to 3), and Reference Audio (up to 3) handles alongside First Frame. Handle descriptions document the First/Last Frame vs Reference Images mutual-exclusivity rule.

### Fixed

- **Seedance 2 I2V: reference-only runs no longer rejected** — When connecting images only to Reference Images, the request no longer duplicates them into `first_frame_url`, which Kie was rejecting as a mutually-exclusive combination.