Skip to content

Conversation

@zakahan
Copy link
Collaborator

@zakahan zakahan commented Dec 26, 2025

  1. Upgraded the volcengine-python-sdk>=5.0.1 to support the sound field of seedance 1.5
  2. Modified video_generate to support the sound field, and ensured that a warning will be provided when the sound field is configured in the user's 1.0 model scenario.
  3. Added timeout configuration (not directly implemented through timing, but directly converting "maximum waiting time in seconds" into "maximum number of sleeps")
  4. Fixed some minor flaws: added seedream 4.5 to the doc-string of image_generate, and changed video_generate from time.sleep to asyncio.sleep to prevent blocking other tasks.

@zakahan zakahan requested a review from warm-wm December 26, 2025 09:37
@zakahan zakahan changed the title chore: support seedance 1.5 pro and sleep with max_wait_seconds feat: support seedance 1.5 pro and sleep with max_wait_seconds Dec 26, 2025
Copy link
Collaborator

@warm-wm warm-wm left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

lgtm

if model_name.startswith("doubao-seedance-1-0") and generate_audio:
logger.warning(
"The `doubao-seedance-1-0` series models do not support enabling the audio field. "
"Please upgrade to the `doubao-seedance-1-5` series."
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

"Please upgrade to the doubao-seedance-1-5 series of you want to generate video with audio."

@zakahan zakahan merged commit 5bd0ea6 into volcengine:main Dec 26, 2025
5 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants