Error
minimax_h3_ref2va_bf16.safetensors
qwen3vl_32b_minimax_h3_bf16.safetensors
minimax_h3_video_vae_fp16.safetensors
minimax_h3_audio_vae_fp32.safetensors
B300x1. --gpu-only
2MP, 11sec, match, 20 steps, res_multistep simple.
[INFO] got prompt
100%|███████████████████████████████████████████| 20/20 [02:59<00:00, 8.98s/it]
[ERROR] !!! Exception during processing !!! Invalid argument: 'avcodec_send_frame()' returned 22; last error log: [aac] Input contains (near) NaN/+-Inf
[ERROR] Traceback (most recent call last):
File "/root/ComfyUI/execution.py", line 545, in execute
output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/ComfyUI/execution.py", line 344, in get_output_data
return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/ComfyUI/execution.py", line 318, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "/root/ComfyUI/execution.py", line 306, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "/root/ComfyUI/comfy_api/internal/init.py", line 149, in wrapped_func
return method(locked_class, **inputs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/ComfyUI/comfy_api/latest/_io.py", line 1990, in EXECUTE_NORMALIZED
to_return = cls.execute(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/ComfyUI/comfy_extras/nodes_video.py", line 141, in execute
video.save_to(
File "/root/ComfyUI/comfy_api/latest/_input_impl/video_types.py", line 895, in save_to
output.mux(audio_stream.encode(frame))
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "av/audio/stream.py", line 26, in av.audio.stream.AudioStream.encode
@cython .ccall
^^^^^^^^^^^
File "av/audio/stream.py", line 36, in av.audio.stream.AudioStream.encode
packets = self.codec_context.encode(frame)
^^^^^^^^^^^
File "av/codec/context.py", line 686, in av.codec.context.CodecContext.encode
for packet in self._send_frame_and_recv(frame):
^^^^^^^^^^^
File "av/codec/context.py", line 545, in _send_frame_and_recv
err_check(res, "avcodec_send_frame()")
^^^^^^^^^^^
File "av/error.py", line 354, in av.error.err_check
raise cls(code, message, filename, log)
^^^^^^^^^^^
av.error.ArgumentError: Invalid argument: 'avcodec_send_frame()' returned 22; last error log: [aac] Input contains (near) NaN/+-Inf
"2MP, 11sec, match, 20 steps, res_multistep" is pretty intense. Assuming that it isn't a workflow error, either the API is struggling to keep up or the AAC encoder is choking on it's input (which it typically does if it's getting weird floats or the numbers are simply too big).
You might try testing it with a lower sampling overhead, something like "6 sec, 20 steps, euler", to help identify the issue. The B300 can easily handle 11 seconds of 2MP video with 20x2 steps but it's pipeline might be struggling, especially if an API is involved.