From 5db51b76b402ba9064af68618aacf81f74c7ca26 Mon Sep 17 00:00:00 2001 From: John Pollock Date: Mon, 15 Jun 2026 22:23:09 -0500 Subject: [PATCH] Fix odd-height crash and edge bleed in unaligned-width image/video decode (#14491) a1d95f3f padded the decode width to the next multiple of 32 with the pad filter to fix libswscale's float YUV->GBR edge corruption, but kept the pad target height equal to the source height. The pad filter requires the target height to be a multiple of the input's vertical chroma subsampling factor, so a chroma-subsampled input such as yuv420p (the format the gbrpf32le float branch decodes) with an odd height makes the filter round the target below the input height and fail to configure: 'Padded dimensions cannot be smaller than input dimensions' (Errno 22). This is reachable from LoadImage, which routes static images through VideoFromFile, on a lossy WebP whose width is not a multiple of 32 and whose height is odd. The pad filter also fills the added border with black, and chroma upsampling bleeds that black into the cropped edge of every unaligned-width subsampled decode. Pad both axes to the next multiple of 32 (32 is a multiple of every vertical subsampling factor, including yuv410p's 4 that a plain even rounding misses) and run fillborders mode=smear to replicate the real edge into the padding so it never bleeds into the cropped output, then crop both axes back to the source size. Aligned-width and uint8 paths run the identical to_ndarray call as before and are byte-identical to master; only unaligned-width subsampled inputs change, from a crash or edge artifact to a clean, deterministic decode. --- comfy_api/latest/_input_impl/video_types.py | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/comfy_api/latest/_input_impl/video_types.py b/comfy_api/latest/_input_impl/video_types.py index 92a1298c0..6c69256ab 100644 --- a/comfy_api/latest/_input_impl/video_types.py +++ b/comfy_api/latest/_input_impl/video_types.py @@ -325,21 +325,25 @@ class VideoFromFile(VideoInput): checked_alpha = True # Fix non-deterministic video decode when the video width is not a multiple of 32 - # For non-yuvj pixel formats (all H.264/H.265 video) + # For non-yuvj pixel formats: most H.264/H.265 video and static images (e.g. lossy WebP via LoadImage) + # Pad both axes to a multiple of 32 and smear the border so the alignment padding never bleeds into the cropped edges if image_format in ('gbrpf32le', 'gbrapf32le') and frame.width % 32 != 0: if align_graph is None: pad_w = ((frame.width + 31) // 32) * 32 + pad_h = ((frame.height + 31) // 32) * 32 g = av.filter.Graph() g_src = g.add_buffer(width=frame.width, height=frame.height, format=frame.format.name, time_base=video_stream.time_base) - g_pad = g.add('pad', f'{pad_w}:{frame.height}:0:0') + g_pad = g.add('pad', f'{pad_w}:{pad_h}:0:0') + g_fill = g.add('fillborders', f'left=0:right={pad_w - frame.width}:top=0:bottom={pad_h - frame.height}:mode=smear') g_sink = g.add('buffersink') g_src.link_to(g_pad) - g_pad.link_to(g_sink) + g_pad.link_to(g_fill) + g_fill.link_to(g_sink) g.configure() align_graph = (g, g_src, g_sink) align_graph[1].push(frame) - img = np.ascontiguousarray(align_graph[2].pull().to_ndarray(format=image_format)[:, :frame.width]) + img = np.ascontiguousarray(align_graph[2].pull().to_ndarray(format=image_format)[:frame.height, :frame.width]) else: img = frame.to_ndarray(format=image_format) if frame.rotation != 0: