Public/automatic
1
0
Fork 0
mirror of https://github.com/vladmandic/automatic synced 2026-09-10 14:58:44 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix(video): count generated frames on the first output axis

Browse Source 
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.
This commit is contained in:
CalamitousFelicitousness
2026-08-17 03:41:46 +01:00
parent 6b499b7d17
commit 7792b1ab62
1 changed files with 1 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/processing_diffusers.py
+1 -4
View File
@@ -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)