下载各种版本，都依然出错，

* Running on local URL: http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Unloaded DynamicSwap_LlamaModel as complete.
Unloaded CLIPTextModel as complete.
Unloaded SiglipVisionModel as complete.
Unloaded AutoencoderKLHunyuanVideo as complete.
Unloaded DynamicSwap_HunyuanVideoTransformer3DModelPacked as complete.
Loaded CLIPTextModel to cuda:0 as complete.
Unloaded CLIPTextModel as complete.
Loaded AutoencoderKLHunyuanVideo to cuda:0 as complete.
Unloaded AutoencoderKLHunyuanVideo as complete.
Loaded SiglipVisionModel to cuda:0 as complete.
latent_padding_size = 27, is_last_section = False
Unloaded SiglipVisionModel as complete.
Moving DynamicSwap_HunyuanVideoTransformer3DModelPacked to cuda:0 with preserved memory: 8 GB
0%| | 0/25 [00:00 @ ]
00007FFE2B69169A00007FFE2B691640 c10.dll!c10::detail::torchCheckFail [ @ ]
00007FFC0DF1358300007FFC0DF05CC0 flash_attn_2_cuda.cp310-win_amd64.pyd!c10::ivalue::Object::operator= [ @ ]
00007FFC0DF25C3600007FFC0DF1C4F0 flash_attn_2_cuda.cp310-win_amd64.pyd!PyInit_flash_attn_2_cuda [ @ ]
00007FFC0DF25D4400007FFC0DF1C4F0 flash_attn_2_cuda.cp310-win_amd64.pyd!PyInit_flash_attn_2_cuda [ @ ]
00007FFC0DF0E67800007FFC0DF05CC0 flash_attn_2_cuda.cp310-win_amd64.pyd!c10::ivalue::Object::operator= [ @ ]
00007FFE2E1C9EEA00007FFE2E1C9E18 python310.dll!PyObject_IsTrue [ @ ]
00007FFE2E22989200007FFE2E2258A0 python310.dll!PyEval_EvalFrameDefault [ @ ]
00007FFE2E2249D700007FFE2E224950 python310.dll!PyFunction_Vectorcall [ @ ]
00007FFE2E20BFB000007FFE2E20BF54 python310.dll!PyVectorcall_Call [ @ ]
00007FFE2E20BE8700007FFE2E20BD44 python310.dll!PyObject_Call [ @ ]
00007FFE2E22B5E700007FFE2E2258A0 python310.dll!PyEval_EvalFrameDefault [ @ ]
00007FFE2E2249D700007FFE2E224950 python310.dll!PyFunction_Vectorcall [ @ ]
00007FFE2E20BFB000007FFE2E20BF54 python310.dll!PyVectorcall_Call [ @ ]
00007FFE2E20BE8700007FFE2E20BD44 python310.dll!PyObject_Call [ @ ]
00007FFE2E22B5E700007FFE2E2258A0 python310.dll!PyEval_EvalFrameDefault [ @ ]
00007FFE2E2249D700007FFE2E224950 python310.dll!PyFunction_Vectorcall [ @ ]
00007FFE2E20BFB000007FFE2E20BF54 python310.dll!PyVectorcall_Call [ @ ]
00007FFE2E20BE8700007FFE2E20BD44 python310.dll!PyObject_Call [ @ ]
00007FFE2E22B5E700007FFE2E2258A0 python310.dll!PyEval_EvalFrameDefault [ @ ]
00007FFE2E2249D700007FFE2E224950 python310.dll!PyFunction_Vectorcall [ @ ]
00007FFE2E20BFB000007FFE2E20BF54 python310.dll!PyVectorcall_Call [ @ ]
00007FFE2E20BE8700007FFE2E20BD44 python310.dll!PyObject_Call [ @ ]
00007FFE2E22B5E700007FFE2E2258A0 python310.dll!PyEval_EvalFrameDefault [ @ ]
00007FFE2E2249D700007FFE2E224950 python310.dll!PyFunction_Vectorcall [ @ ]
00007FFE2E20BFB000007FFE2E20BF54 python310.dll!PyVectorcall_Call [ @ ]
00007FFE2E20BD9300007FFE2E20BD44 python310.dll!PyObject_Call [ @ ]
00007FFE2397F89300007FFE239596A0 torch_python.dll!torch::FunctionParameter::type_name [ @ ]
00007FFCB4800B6100007FFCB48009A0 torch_cpu.dll!c10::Dispatcher::callBoxed [ @ ]
00007FFE2375234400007FFE23752280 torch_python.dll!torch::jit::invokeOperatorFromPython [ @ ]
00007FFE2374F45700007FFE2374F320 torch_python.dll!torch::jit::_get_operation_for_overload_or_packet [ @ ]
00007FFE236B834800007FFE236A3D40 torch_python.dll!c10d::PythonOnCompletionHook::PythonOnCompletionHook [ @ ]
00007FFE2365D8F600007FFE235E5360 torch_python.dll!THPPointer::dup [ @ ]
00007FFE230A18D400007FFE230A0A30 torch_python.dll!c10::ivalue::Future::devices [ @ ]
00007FFE2E1C9EEA00007FFE2E1C9E18 python310.dll!PyObject_IsTrue [ @ ]
00007FFE2E20BDCE00007FFE2E20BD44 python310.dll!PyObject_Call [ @ ]
00007FFE2E20BECB00007FFE2E20BD44 python310.dll!PyObject_Call [ @ ]
00007FFE2E22B5E700007FFE2E2258A0 python310.dll!PyEval_EvalFrameDefault [ @ ]
00007FFE2E2249D700007FFE2E224950 python310.dll!PyFunction_Vectorcall [ @ ]
00007FFE2E1DA91700007FFE2E1DA844 python310.dll!PyObject_FastCallDictTstate [ @ ]
00007FFE2E2E81F400007FFE2E2E8178 python310.dll!PyObject_Call_Prepend [ @ ]
00007FFE2E2E815000007FFE2E2E7064 python310.dll!PyBytesWriter_Resize [ @ ]
00007FFE2E20FFBB00007FFE2E20FE58 python310.dll!PyObject_MakeTpCall [ @ ]
00007FFE2E22C39F00007FFE2E2258A0 python310.dll!PyEval_EvalFrameDefault [ @ ]
00007FFE2E2249D700007FFE2E224950 python310.dll!PyFunction_Vectorcall [ @ ]
00007FFE2E20BFB000007FFE2E20BF54 python310.dll!PyVectorcall_Call [ @ ]
00007FFE2E20BD9300007FFE2E20BD44 python310.dll!PyObject_Call [ @ ]
00007FFE23545A5500007FFE23540690 torch_python.dll!torch::autograd::registerFunctionPreHook [ @ ]
00007FFE2E1C9F1900007FFE2E1C9E18 python310.dll!PyObject_IsTrue [ @ ]
00007FFE2E20BDCE00007FFE2E20BD44 python310.dll!PyObject_Call [ @ ]
00007FFE2E20BECB00007FFE2E20BD44 python310.dll!PyObject_Call [ @ ]
00007FFE2E22B5E700007FFE2E2258A0 python310.dll!PyEval_EvalFrameDefault [ @ ]
00007FFE2E22361500007FFE2E2225C0 python310.dll!PyObject_GC_Malloc [ @ ]
00007FFE2E22729300007FFE2E2258A0 python310.dll!PyEval_EvalFrameDefault [ @ ]
00007FFE2E2249D700007FFE2E224950 python310.dll!PyFunction_Vectorcall [ @ ]
00007FFE2E22603300007FFE2E2258A0 python310.dll!PyEval_EvalFrameDefault [ @ ]
00007FFE2E2249D700007FFE2E224950 python310.dll!PyFunction_Vectorcall [ @ ]
00007FFE2E22603300007FFE2E2258A0 python310.dll!PyEval_EvalFrameDefault [ @ ]
00007FFE2E2249D700007FFE2E224950 python310.dll!PyFunction_Vectorcall [ @ ]
00007FFE2E1DA91700007FFE2E1DA844 python310.dll!PyObject_FastCallDictTstate [ @ ]
00007FFE2E2E81F400007FFE2E2E8178 python310.dll!PyObject_Call_Prepend [ @ ]
00007FFE2E2E815000007FFE2E2E7064 python310.dll!PyBytesWriter_Resize [ @ ]
00007FFE2E20BF0300007FFE2E20BD44 python310.dll!PyObject_Call [ @ ]
00007FFE2E22B5E700007FFE2E2258A0 python310.dll!PyEval_EvalFrameDefault [ @ ]

Unloaded DynamicSwap_LlamaModel as complete.
Unloaded CLIPTextModel as complete.
Unloaded SiglipVisionModel as complete.
Unloaded AutoencoderKLHunyuanVideo as complete.
Unloaded DynamicSwap_HunyuanVideoTransformer3DModelPacked as complete.
Traceback (most recent call last):
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\httpx\_transports\default.py", line 101, in map_httpcore_exceptions
yield
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\httpx\_transports\default.py", line 250, in handle_request
resp = self._pool.handle_request(req)
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\httpcore\_sync\connection_pool.py", line 256, in handle_request
raise exc from None
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\httpcore\_sync\connection_pool.py", line 236, in handle_request
response = connection.handle_request(
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\httpcore\_sync\connection.py", line 103, in handle_request
return self._connection.handle_request(request)
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\httpcore\_sync\http11.py", line 136, in handle_request
raise exc
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\httpcore\_sync\http11.py", line 106, in handle_request
) = self._receive_response_headers(**kwargs)
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\httpcore\_sync\http11.py", line 177, in _receive_response_headers
event = self._receive_event(timeout=timeout)
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\httpcore\_sync\http11.py", line 231, in _receive_event
raise RemoteProtocolError(msg)
httpcore.RemoteProtocolError: Server disconnected without sending a response.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\openai\_base_client.py", line 989, in _request
response = self._client.send(
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\httpx\_client.py", line 914, in send
response = self._send_handling_auth(
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\httpx\_client.py", line 942, in _send_handling_auth
response = self._send_handling_redirects(
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\httpx\_client.py", line 979, in _send_handling_redirects
response = self._send_single_request(request)
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\httpx\_client.py", line 1014, in _send_single_request
response = transport.handle_request(request)
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\httpx\_transports\default.py", line 249, in handle_request
with map_httpcore_exceptions():
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\contextlib.py", line 153, in __exit__
self.gen.throw(typ, value, traceback)
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\httpx\_transports\default.py", line 118, in map_httpcore_exceptions
raise mapped_exc(message) from exc
httpx.RemoteProtocolError: Server disconnected without sending a response.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\gradio\queueing.py", line 625, in process_events
response = await route_utils.call_process_api(
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\gradio\route_utils.py", line 322, in call_process_api
output = await app.get_blocks().process_api(
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\gradio\blocks.py", line 2137, in process_api
result = await self.call_function(
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\gradio\blocks.py", line 1663, in call_function
prediction = await anyio.to_thread.run_sync( # type: ignore
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\anyio\to_thread.py", line 56, in run_sync
return await get_async_backend().run_sync_in_worker_thread(
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\anyio\_backends\_asyncio.py", line 2470, in run_sync_in_worker_thread
return await future
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\anyio\_backends\_asyncio.py", line 967, in run
result = context.run(func, *args)
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\gradio\utils.py", line 890, in wrapper
response = f(*args, **kwargs)
File "", line 47, in convert_prompt
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\openai\_utils\_utils.py", line 279, in wrapper
return func(*args, **kwargs)
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\openai\resources\chat\completions\completions.py", line 929, in create
return self._post(
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\openai\_base_client.py", line 1276, in post
return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\openai\_base_client.py", line 949, in request
return self._request(
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\openai\_base_client.py", line 1013, in _request
return self._retry_request(
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\openai\_base_client.py", line 1091, in _retry_request
return self._request(
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\openai\_base_client.py", line 1013, in _request
return self._retry_request(
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\openai\_base_client.py", line 1091, in _retry_request
return self._request(
File "C:\AI\AI-VIDEO\FramePack-250420\FramePack\.glut\lib\site-packages\openai\_base_client.py", line 1023, in _request
raise APIConnectionError(request=request) from err
openai.APIConnectionError: Connection error.

Start with FramePack/demo_gradio.py and trace the call into diffusers_helper/models/hunyuan_video_packed.py, especially attn_varlen_func. Reproduce the failure from the reported Windows environment and inspect how the FlashAttention dependency is selected. Done means the reported GPU compatibility failure is handled or clearly rejected with an appropriate supported path and a verified generation run.

Written by the indexing model from the issue text.