Files
hao-ai-lab-FastVideo/docs/design
Davids048andClaude Opus 5.5 4d05e9c020 [bugfix]: apply per-request embedded_cfg_scale in the worker
A request's embedded_cfg_scale (request extension or legacy generate_video
keyword) was applied to a deep copy of FastVideoArgs.pipeline_config in
VideoGenerator. The worker runs the pipeline with its own FastVideoArgs
(GpuWorker.execute_forward passes self.fastvideo_args), so the copy never
reached the denoising stages and the request value was ignored.

embedded_cfg_scale is now a per-request sampling value:

- the request field request.sampling.embedded_cfg_scale (the extension key
  still works);
- SamplingParam.embedded_cfg_scale and ForwardBatch.embedded_cfg_scale;
- embedded_cfg_scale_for_batch(batch, fastvideo_args), which the denoising,
  SR denoising, Wan DMD, and Flux2 text-encoding stages read. It returns the
  batch value, else pipeline_config.embedded_cfg_scale, so training and
  requests without the field are unchanged.

VideoGenerator no longer copies or changes FastVideoArgs per request, and
request_to_pipeline_overrides is removed. The golden snapshots record the new
SamplingParam field, and the request with extensions.embedded_cfg_scale now
carries 3.0 on SamplingParam instead of on a pipeline override.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_012M91wnVFmPEvJ9h39r5BH7
2026-10-02 20:17:03 +00:00
..