From 7792b1ab62102014466361d190e9eebeac86b523 Mon Sep 17 00:00:00 2001 From: CalamitousFelicitousness Date: Mon, 17 Aug 2026 03:41:46 +0100 Subject: [PATCH] fix(video): count generated frames on the first output axis The shape branch read axis 1, which held the frame count back when animatediff returned (batch, channels, frames, height, width). Diffusers now returns (batch, frames, channels, height, width) and the modular video path puts channels last, so axis 1 reads channels or height and the line printed a plausible wrong number: a 124 frame 1024x576 generation logged frames=576. len() is the frame count under both layouts and is what the sibling call site in process_decode already uses. --- modules/processing_diffusers.py | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/modules/processing_diffusers.py b/modules/processing_diffusers.py index ddd4e0171..0efbc4904 100644 --- a/modules/processing_diffusers.py +++ b/modules/processing_diffusers.py @@ -204,10 +204,7 @@ def process_base(p: processing.StableDiffusionProcessing): t1 = time.time() log.debug(f'Profile: pipeline call: {t1-t0:.2f}') if not hasattr(output, 'images') and hasattr(output, 'frames'): - if hasattr(output.frames[0], 'shape'): - log.debug(f'Generated: frames={output.frames[0].shape[1]}') - else: - log.debug(f'Generated: frames={len(output.frames[0])}') + log.debug(f'Generated: frames={len(output.frames[0])}') output.images = output.frames[0] if hasattr(output, 'images') and isinstance(output.images, np.ndarray): output.images = torch.from_numpy(output.images)