Ethanfel 76dff7e573 Fix FlashVSR quality: two-stage temporal padding, kv_ratio=3, float64 precision ...

Root cause of remaining ghosting: our single-stage temporal padding
(N+4 → floor to 8k+1) TRUNCATED frames when N+4 wasn't already 8k+1.
For 50 frames: 50+4=54 → floor to 49, LOSING the last input frame.
The pipeline then processed misaligned LQ→output frame mapping.

Fix matches naxci1/ComfyUI-FlashVSR_Stable two-stage approach:
1. Pad to next_8n5(N) (next integer >= N of form 8k+5, minimum 21)
2. Add 4 → result is always 8(k+1)+1, a valid 8k+1 — NEVER truncates

Also:
- kv_ratio default 2.0→3.0 (matches naxci1, max quality KV cache)
- local_range default 9→11 (more stable temporal consistency)
- sinusoidal_embedding_1d, precompute_freqs_cis, rope_apply: float32→float64
  (matches naxci1 reference precision for embeddings and RoPE)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-02-13 18:06:46 +01:00

76 KiB

Raw Blame History

View Raw