cxn007 发表于 2026-9-5 19:55
为啥启动后参考图参考音频视频点击都没反应
下方对应模式手动切换
cxn007 发表于 2026-9-5 19:55
为啥启动后参考图参考音频视频点击都没反应
选参考模式才是图生视频，才能上传图片。
无言以对 发表于 2026-9-5 21:14
下方对应模式手动切换
卧槽，我长这么大眼睛，纯出气用的
老哥，4080S 16G显卡，32G运存，装了运行库和CUDA，参考图模式，两张图，生成5秒视频，显示Attempting to release mmap（170），一段时间后Windows fatal exception: access violation，最后一大段提示后，显示gradio.exceptions.Error: "发生错误: HTTPConnectionPool(host='127.0.0.1', port=8188): Read timed out. (read timeout=10)"，麻烦帮忙看看。
liglass 发表于 2026-9-7 13:33
老哥，4080S 16G显卡，32G运存，装了运行库和CUDA，参考图模式，两张图，生成5秒视频，显示Attempting to r ...
复制粘贴完整的报错信息
Attempting to release mmap (170)
gguf qtypes: F32 (269), F16 (16), Q4_K (250)
model weight dtype torch.bfloat16, manual cast: None
model_type FLOW_AV
Applying MiniMax H3 Memory Efficient Sage Attention Patch to all transformer blocks
Requested to load MiniMaxH3
Windows fatal exception: access violation
Stack (most recent call first):
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\deepface\Lib\site-packages\torch\_tensor.py", line 1668 in __torch_function__
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\ComfyUI\custom_nodes\ComfyUI-GGUF\ops.py", line 58 in to
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\deepface\Lib\site-packages\torch\nn\modules\module.py", line 1341 in convert
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\deepface\Lib\site-packages\torch\nn\modules\module.py", line 942 in _apply
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\deepface\Lib\site-packages\torch\nn\modules\module.py", line 1355 in to
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\ComfyUI\custom_nodes\ComfyUI-GGUF\nodes.py", line 85 in pin_weight_to_device
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\ComfyUI\comfy\model_patcher.py", line 1089 in load
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\ComfyUI\custom_nodes\ComfyUI-GGUF\nodes.py", line 97 in load
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\ComfyUI\comfy\model_patcher.py", line 1277 in partially_load
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\ComfyUI\comfy\model_management.py", line 818 in model_use_more_vram
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\ComfyUI\comfy\model_management.py", line 790 in model_load
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\ComfyUI\comfy\model_management.py", line 1004 in load_models_gpu
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\ComfyUI\comfy\sampler_helpers.py", line 201 in _prepare_sampling
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\ComfyUI\comfy\patcher_extension.py", line 113 in execute
File "asyncio\events.py", line 88 in _run
File "asyncio\base_events.py", line 1999 in _run_once
File "asyncio\base_events.py", line 645 in run_forever
File "asyncio\windows_events.py", line 322 in run_forever
File "asyncio\base_events.py", line 678 in run_until_complete
File "asyncio\runners.py", line 118 in run
File "asyncio\runners.py", line 195 in run
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\ComfyUI\execution.py", line 728 in execute
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\ComfyUI\main.py", line 382 in prompt_worker
File "threading.py", line 1012 in run
File "threading.py", line 1075 in _bootstrap_inner
File "threading.py", line 1032 in _bootstrap
Traceback (most recent call last):
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\deepface\Lib\site-packages\urllib3\connectionpool.py", line 534, in _make_request
response = conn.getresponse()
^^^^^^^^^^^^^^^^^^
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\deepface\Lib\site-packages\urllib3\connection.py", line 565, in getresponse
httplib_response = super().getresponse()
^^^^^^^^^^^^^^^^^^^^^
File "http\client.py", line 1430, in getresponse
File "http\client.py", line 331, in begin
File "http\client.py", line 292, in _read_status
File "socket.py", line 720, in readinto
TimeoutError: timed out
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\deepface\Lib\site-packages\requests\adapters.py", line 667, in send
resp = conn.urlopen(
^^^^^^^^^^^^^
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\deepface\Lib\site-packages\urllib3\connectionpool.py", line 841, in urlopen
retries = retries.increment(
^^^^^^^^^^^^^^^^^^
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\deepface\Lib\site-packages\urllib3\util\retry.py", line 474, in increment
raise reraise(type(error), error, _stacktrace)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\deepface\Lib\site-packages\urllib3\util\util.py", line 39, in reraise
raise value
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\deepface\Lib\site-packages\urllib3\connectionpool.py", line 787, in urlopen
response = self._make_request(
^^^^^^^^^^^^^^^^^^^
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\deepface\Lib\site-packages\urllib3\connectionpool.py", line 536, in _make_request
self._raise_timeout(err=e, url=url, timeout_value=read_timeout)
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\deepface\Lib\site-packages\urllib3\connectionpool.py", line 367, in _raise_timeout
raise ReadTimeoutError(
urllib3.exceptions.ReadTimeoutError: HTTPConnectionPool(host='127.0.0.1', port=8188): Read timed out. (read timeout=10)
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "<frozen app>", line 571, in generate_video
File "<frozen app>", line 170, in get_history
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\deepface\Lib\site-packages\requests\api.py", line 73, in get
return request("get", url, params=params, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\deepface\Lib\site-packages\requests\api.py", line 59, in request
return session.request(method=method, url=url, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\deepface\Lib\site-packages\requests\sessions.py", line 589, in request
resp = self.send(prep, **send_kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\deepface\Lib\site-packages\requests\sessions.py", line 703, in send
r = adapter.send(request, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\deepface\Lib\site-packages\requests\adapters.py", line 713, in send
raise ReadTimeout(e, request=request)
requests.exceptions.ReadTimeout: HTTPConnectionPool(host='127.0.0.1', port=8188): Read timed out. (read timeout=10)
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\deepface\Lib\site-packages\gradio\queueing.py", line 759, in process_events
response = await route_utils.call_process_api(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\deepface\Lib\site-packages\gradio\route_utils.py", line 354, in call_process_api
output = await app.get_blocks().process_api(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\deepface\Lib\site-packages\gradio\blocks.py", line 2116, in process_api
result = await self.call_function(
^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\deepface\Lib\site-packages\gradio\blocks.py", line 1623, in call_function
prediction = await anyio.to_thread.run_sync(# type: ignore
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\deepface\Lib\site-packages\anyio\to_thread.py", line 65, in run_sync
return await get_async_backend().run_sync_in_worker_thread(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\Worksofts\ComfyUI_MiniMax-H3-V5\deepface\Lib\site-packages\gradio\utils.py", line 915, in wrapper
response = f(*args, **kwargs)
^^^^^^^^^^^^^^^^^^
File "<frozen app>", line 607, in generate_video
gradio.exceptions.Error: "发生错误: HTTPConnectionPool(host='127.0.0.1', port=8188): Read timed out. (read timeout=10)"
检测到服务退出，正在关闭所有进程...
liglass 发表于 2026-9-7 15:10
Attempting to release mmap (170)
gguf qtypes ...
参数都是默认的吗？
还是自定义，一采，二采都设置多少
还有，你虚拟内存设置了没？你这有可能是显存和内存不足导致的
显卡驱动是最新的吗？
参数都是默认的，一采是0.2，二采是0.8，时长5秒，虚拟内存系统自动分配的12G，运存32G，显存4080S 16G，studio驱动616.56。我手动设置下虚拟内存大小，再更新下显卡驱动试试吧。
liglass 发表于 2026-9-7 16:58
参数都是默认的，一采是0.2，二采是0.8，时长5秒，虚拟内存系统自动分配的12G，运存32G，显存4080S 16G，st ...
手动设置虚拟内存，最少64G起
参考这个帖子
After Max GPU memory allocated: 2.92 GB
0%| | 0/8
0%| | 0/8
!!! Exception during processing !!! The size of tensor a (32) must match the size of tensor b (1024) at non-singleton dimension 1
Traceback (most recent call last):
File "E:\BaiduNetdiskDownload\ComfyUI_MiniMax-H3-V5\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 "E:\BaiduNetdiskDownload\ComfyUI_MiniMax-H3-V5\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 "E:\BaiduNetdiskDownload\ComfyUI_MiniMax-H3-V5\ComfyUI\execution.py", line 318, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "E:\BaiduNetdiskDownload\ComfyUI_MiniMax-H3-V5\ComfyUI\execution.py", line 306, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "E:\BaiduNetdiskDownload\ComfyUI_MiniMax-H3-V5\ComfyUI\comfy_api\internal\__init__.py", line 149, in wrapped_func
return method(locked_class, **inputs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\BaiduNetdiskDownload\ComfyUI_MiniMax-H3-V5\ComfyUI\comfy_api\latest\_io.py", line 1990, in EXECUTE_NORMALIZED
to_return = cls.execute(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\BaiduNetdiskDownload\ComfyUI_MiniMax-H3-V5\ComfyUI\comfy_extras\nodes_custom_sampler.py", line 1055, in execute
samples = guider.sample(noise.generate_noise(latent), latent_image, sampler, sigmas, denoise_mask=noise_mask, callback=callback, disable_pbar=disable_pbar, seed=noise.seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
^^^^^^^^^^^^^^^^^^
File "<frozen app>", line 585, in generate_video
gradio.exceptions.Error: '生成失败: 节点 SamplerCustomAdvanced: The size of tensor a (32) must match the size of tensor b (1024) at non-singleton dimension 1\n'