fix(Video): don't crash on videos with undecodable audio streams

Signed-off-by: bigcat88 <bigcat88@icloud.com>

.coderabbit.yaml

@@ -4,12 +4,12 @@ early_access: false
 tone_instructions: "Only comment on issues introduced by this PR's changes. Do not flag pre-existing problems in moved, re-indented, or reformatted code."
 
 reviews:
-  profile: "assertive"
-  request_changes_workflow: true
+  profile: "chill"
+  request_changes_workflow: false
   high_level_summary: false
   poem: false
   review_status: false
-  review_details: true
+  review_details: false
   commit_status: true
   collapse_walkthrough: true
   changed_files_summary: false
@@ -39,14 +39,6 @@ reviews:
     - path: "**"
       instructions: |
         IMPORTANT: Only comment on issues directly introduced by this PR's code changes.
-        Treat AGENTS.md as mandatory repository policy, not optional style guidance.
-        Flag PR changes that violate AGENTS.md even when the code is otherwise functional.
-        In particular, enforce architecture boundaries, dtype/device/memory rules,
-        interface contracts, import style, no unnecessary try/except blocks, no inline
-        imports, no outbound internet paths in core ComfyUI, and narrow scoped fixes.
-        Prefer direct findings over suggestions when a rule is violated. Only ignore
-        AGENTS.md when it clearly conflicts with a newer explicit maintainer instruction
-        in the PR.
         Do NOT flag pre-existing issues in code that was merely moved, re-indented,
         de-indented, or reformatted without logic changes. If code appears in the diff
         only due to whitespace or structural reformatting (e.g., removing a `with:` block),
@@ -131,10 +123,5 @@ chat:
 
 knowledge_base:
   opt_out: false
-  code_guidelines:
-    enabled: true
-    filePatterns:
-      - files: "AGENTS.md"
-        applyTo: "**"
   learnings:
     scope: "auto"

AGENTS.md

@@ -171,9 +171,6 @@
 - Reuse existing model classes, blocks, ops, and helper modules when appropriate.
   Before implementing a new version of a model component, search the existing
   model code for a class or helper that already provides the behavior.
-- Model detection code that inspects linear weight shapes should only use the
-  first dimension. The second dimension may be half the original size for
-  NVFP4 or other 4-bit quantized models.
 - Avoid adding `einops` usage in core inference code. Use native torch tensor
   ops such as `reshape`, `view`, `permute`, `transpose`, `flatten`, `unflatten`,
   `unsqueeze`, and `squeeze` instead.

CLAUDE.md

@@ -1 +0,0 @@
-AGENTS.md

comfy/sd1_clip.py

@@ -543,24 +543,18 @@ class SDTokenizer:
     def _try_get_embedding(self, embedding_name:str):
         '''
         Takes a potential embedding name and tries to retrieve it.
-        Returns a Tuple consisting of the embedding, the cleaned embedding name, and any leftover string, embedding can be None.
+        Returns a Tuple consisting of the embedding and any leftover string, embedding can be None.
         '''
         split_embed = embedding_name.split()
         embedding_name = split_embed[0]
         leftover = ' '.join(split_embed[1:])
-
-        match = re.search(r'[<\[]', embedding_name)
-        if match is not None:
-            leftover = embedding_name[match.start():] + (" " + leftover if leftover else "")
-            embedding_name = embedding_name[:match.start()]
-
         embed = load_embed(embedding_name, self.embedding_directory, self.embedding_size, self.embedding_key)
         if embed is None:
             stripped = embedding_name.strip(',')
             if len(stripped) < len(embedding_name):
                 embed = load_embed(stripped, self.embedding_directory, self.embedding_size, self.embedding_key)
-                return (embed, embedding_name, "{} {}".format(embedding_name[len(stripped):], leftover))
-        return (embed, embedding_name, leftover)
+                return (embed, "{} {}".format(embedding_name[len(stripped):], leftover))
+        return (embed, leftover)
 
     def pad_tokens(self, tokens, amount):
         if self.pad_left:
@@ -591,7 +585,7 @@ class SDTokenizer:
         tokens = []
         for weighted_segment, weight in parsed_weights:
             to_tokenize = unescape_important(weighted_segment)
-            split = re.split(r'(?<=\s){}'.format(re.escape(self.embedding_identifier)), to_tokenize)
+            split = re.split(' {0}|\n{0}'.format(self.embedding_identifier), to_tokenize)
             to_tokenize = [split[0]]
             for i in range(1, len(split)):
                 to_tokenize.append("{}{}".format(self.embedding_identifier, split[i]))
@@ -601,7 +595,7 @@ class SDTokenizer:
                 # if we find an embedding, deal with the embedding
                 if word.startswith(self.embedding_identifier) and self.embedding_directory is not None:
                     embedding_name = word[len(self.embedding_identifier):].strip('\n')
-                    embed, embedding_name, leftover = self._try_get_embedding(embedding_name)
+                    embed, leftover = self._try_get_embedding(embedding_name)
                     if embed is None:
                         logging.warning(f"warning, embedding:{embedding_name} does not exist, ignoring")
                     else:

comfy/text_encoders/llama.py

@@ -937,41 +937,22 @@ class BaseGenerate:
             return torch.argmax(logits, dim=-1, keepdim=True)
 
         # Sampling mode
-        if len(token_history) > 0 and (repetition_penalty != 1.0 or (presence_penalty is not None and presence_penalty != 0.0)):
-            token_ids = torch.tensor(list(set(token_history)), device=logits.device)
-            token_logits = logits[:, token_ids]
-            if repetition_penalty != 1.0:
-                token_logits = torch.where(token_logits < 0, token_logits * repetition_penalty, token_logits / repetition_penalty)
-            if presence_penalty is not None and presence_penalty != 0.0:
-                token_logits = token_logits - presence_penalty
-            logits[:, token_ids] = token_logits
+        if repetition_penalty != 1.0:
+            for i in range(logits.shape[0]):
+                for token_id in set(token_history):
+                    logits[i, token_id] *= repetition_penalty if logits[i, token_id] < 0 else 1/repetition_penalty
+
+        if presence_penalty is not None and presence_penalty != 0.0:
+            for i in range(logits.shape[0]):
+                for token_id in set(token_history):
+                    logits[i, token_id] -= presence_penalty
 
         if temperature != 1.0:
             logits = logits / temperature
 
         if top_k > 0:
-            top_k = min(top_k, logits.shape[-1])
-            logits, top_indices = torch.topk(logits, top_k)
-
-            if min_p > 0.0:
-                probs_before_filter = torch.nn.functional.softmax(logits, dim=-1)
-                top_probs, _ = probs_before_filter.max(dim=-1, keepdim=True)
-                min_threshold = min_p * top_probs
-                indices_to_remove = probs_before_filter < min_threshold
-                logits[indices_to_remove] = torch.finfo(logits.dtype).min
-
-            if top_p < 1.0:
-                sorted_logits, sorted_indices = torch.sort(logits, descending=True)
-                cumulative_probs = torch.cumsum(torch.nn.functional.softmax(sorted_logits, dim=-1), dim=-1)
-                sorted_indices_to_remove = cumulative_probs > top_p
-                sorted_indices_to_remove[..., 0] = False
-                indices_to_remove = torch.zeros_like(logits, dtype=torch.bool)
-                indices_to_remove.scatter_(1, sorted_indices, sorted_indices_to_remove)
-                logits[indices_to_remove] = torch.finfo(logits.dtype).min
-
-            probs = torch.nn.functional.softmax(logits, dim=-1)
-            next_token = torch.multinomial(probs, num_samples=1, generator=generator)
-            return top_indices.gather(1, next_token)
+            indices_to_remove = logits < torch.topk(logits, top_k)[0][..., -1, None]
+            logits[indices_to_remove] = torch.finfo(logits.dtype).min
 
         if min_p > 0.0:
             probs_before_filter = torch.nn.functional.softmax(logits, dim=-1)

comfy_api/latest/_input_impl/video_types.py

@@ -281,11 +281,18 @@ class VideoFromFile(VideoInput):
         video_done = False
         audio_done = True
 
-        if len(container.streams.audio):
-            audio_stream = container.streams.audio[-1]
+        # Use the last decodable audio stream. Streams FFmpeg has no decoder for have no codec context,
+        # and decoding their packets crashes the process. (e.g. APAC spatial-audio track in iPhone)
+        audio_stream = next(
+            (s for s in reversed(container.streams.audio) if s.codec_context is not None),
+            None,
+        )
+        if audio_stream is not None:
             streams += [audio_stream]
             resampler = av.audio.resampler.AudioResampler(format='fltp')
             audio_done = False
+        elif len(container.streams.audio):
+            logging.warning("No decodable audio stream found in video; ignoring audio.")
 
         for packet in container.demux(*streams):
             if video_done and audio_done:
@@ -457,10 +464,13 @@ class VideoFromFile(VideoInput):
                         else:
                             output_container.metadata[key] = json.dumps(value)
 
-                # Add streams to the new container
+                # Add streams to the new container. Streams with no codec context cannot be used as an output template.
                 stream_map = {}
                 for stream in streams:
                     if isinstance(stream, (av.VideoStream, av.AudioStream, SubtitleStream)):
+                        if stream.codec_context is None:
+                            logging.warning("Skipping %s stream %d with unsupported codec", stream.type, stream.index)
+                            continue
                         out_stream = output_container.add_stream_from_template(template=stream, opaque=True)
                         stream_map[stream] = out_stream
 

comfy_api_nodes/nodes_bytedance.py

@@ -2611,7 +2611,7 @@ class ByteDanceSeedAudioNode(IO.ComfyNode):
         return IO.Schema(
             node_id="ByteDanceSeedAudio",
             display_name="ByteDance Seed Audio 1.0",
-            category="partner/audio/ByteDance",
+            category="api node/audio/ByteDance",
             description=(
                 "Generate speech, music, sound effects and multi-speaker dialogue from a single prompt "
                 "with ByteDance Seed Audio 1.0. Describe the voice(s), emotion, ambience, background music "

comfy_api_nodes/util/upload_helpers.py

@@ -158,7 +158,14 @@ async def upload_video_to_comfyapi(
 
     # Convert VideoInput to BytesIO using specified container/codec
     video_bytes_io = BytesIO()
-    video.save_to(video_bytes_io, format=container, codec=codec)
+    try:
+        video.save_to(video_bytes_io, format=container, codec=codec)
+    except Exception as e:
+        raise ValueError(
+            f"Could not convert the input video to {container.value.upper()} for upload; "
+            f"the file may be corrupt or use an unsupported codec. "
+            f"Try re-exporting it as MP4 (H.264). Original error: {e}"
+        ) from e
     video_bytes_io.seek(0)
 
     return await upload_file_to_comfyapi(cls, video_bytes_io, filename, upload_mime_type, wait_label)

comfy_extras/nodes_color.py

@@ -16,30 +16,23 @@ class ColorToRGBInt(io.ComfyNode):
             ],
             outputs=[
                 io.Int.Output(display_name="rgb_int"),
-                io.Color.Output(display_name="hex"),
-                io.Float.Output(display_name="alpha"),
+                io.Color.Output(display_name="hex")
             ],
         )
 
     @classmethod
     def execute(cls, color: str) -> io.NodeOutput:
-        # expect format #RRGGBB or #RRGGBBAA
-        if len(color) not in (7, 9) or color[0] != "#":
-            raise ValueError("Color must be in format #RRGGBB or #RRGGBBAA")
+        # expect format #RRGGBB
+        if len(color) != 7 or color[0] != "#":
+            raise ValueError("Color must be in format #RRGGBB")
         try:
             int(color[1:], 16)
         except ValueError:
-            raise ValueError("Color must be in format #RRGGBB or #RRGGBBAA") from None
-
-        alpha = 1.0
-        if len(color) == 9:
-            alpha = int(color[7:9], 16) / 255.0
-            color = color[:7]
-
+            raise ValueError("Color must be in format #RRGGBB") from None
         r, g, b = hex_to_rgb(color)
 
         rgb_int = r * 256 * 256 + g * 256 + b
-        return io.NodeOutput(rgb_int, color, alpha)
+        return io.NodeOutput(rgb_int, color)
 
 
 class ColorExtension(ComfyExtension):