Currently, StoryTeller.generate() generates one image at a time. This is for ease of implementation: we generate one image, a subtitle file, and an audio file, then stitch them together to create one frame.
Solution
To speed up generation on GPUs, support batch generation. This is simple with HF's pipeline:
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.
Context
Currently,
StoryTeller.generate()
generates one image at a time. This is for ease of implementation: we generate one image, a subtitle file, and an audio file, then stitch them together to create one frame.Solution
To speed up generation on GPUs, support batch generation. This is simple with HF's pipeline: