Gets going and then just stops and sits

Nobody has claimed this yet.

Does a bunch of stuff in the browser, then nothing, it loses the highlight around the video frame sections and sits there with the pic in the image input

Currently enabled native sdp backends: ['flash', 'math', 'mem_efficient', 'cudnn']
Xformers is not installed!
Flash Attn is installed!
Sage Attn is not installed!
Namespace(share=False, server='127.0.0.1', port=None, inbrowser=True)
Free VRAM 4.7021484375 GB
High-VRAM Mode: False
Downloading shards: 100%|██████████████████████████████████████████████████████████████| 4/4 [00:00<00:00, 2016.73it/s]
Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████| 4/4 [00:00<00:00, 4.88it/s]
Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████| 3/3 [00:00<00:00, 5.62it/s]
transformer.high_quality_fp32_output_for_inference = True
* 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: 6 GB
0%| | 0/25 [00:17 @ ]
00007FFA764479FA00007FFA764479A0 c10.dll!c10::detail::torchCheckFail [ @ ]
00007FF95F41351300007FF95F405C20 flash_attn_2_cuda.cp310-win_amd64.pyd!c10::ivalue::Object::operator= [ @ ]
00007FF95F425B8600007FF95F41C460 flash_attn_2_cuda.cp310-win_amd64.pyd!PyInit_flash_attn_2_cuda [ @ ]
00007FF95F425C9400007FF95F41C460 flash_attn_2_cuda.cp310-win_amd64.pyd!PyInit_flash_attn_2_cuda [ @ ]
00007FF95F40E61800007FF95F405C20 flash_attn_2_cuda.cp310-win_amd64.pyd!c10::ivalue::Object::operator= [ @ ]
00007FFA794D49A600007FFA794D491C python310.dll!PyType_IsSubtype [ @ ]
00007FFA794EB29A00007FFA794E71D0 python310.dll!PyEval_EvalFrameDefault [ @ ]
00007FFA794E626700007FFA794E61E0 python310.dll!PyFunction_Vectorcall [ @ ]
00007FFA794A0B3000007FFA794A0AD4 python310.dll!PyVectorcall_Call [ @ ]
00007FFA794A0A0700007FFA794A08B8 python310.dll!PyObject_Call [ @ ]
00007FFA794ED24F00007FFA794E71D0 python310.dll!PyEval_EvalFrameDefault [ @ ]
00007FFA794E626700007FFA794E61E0 python310.dll!PyFunction_Vectorcall [ @ ]
00007FFA794A0B3000007FFA794A0AD4 python310.dll!PyVectorcall_Call [ @ ]
00007FFA794A0A0700007FFA794A08B8 python310.dll!PyObject_Call [ @ ]
00007FFA794ED24F00007FFA794E71D0 python310.dll!PyEval_EvalFrameDefault [ @ ]
00007FFA794E626700007FFA794E61E0 python310.dll!PyFunction_Vectorcall [ @ ]
00007FFA794A0B3000007FFA794A0AD4 python310.dll!PyVectorcall_Call [ @ ]
00007FFA794A0A0700007FFA794A08B8 python310.dll!PyObject_Call [ @ ]
00007FFA794ED24F00007FFA794E71D0 python310.dll!PyEval_EvalFrameDefault [ @ ]
00007FFA794E626700007FFA794E61E0 python310.dll!PyFunction_Vectorcall [ @ ]
00007FFA794A0B3000007FFA794A0AD4 python310.dll!PyVectorcall_Call [ @ ]
00007FFA794A0A0700007FFA794A08B8 python310.dll!PyObject_Call [ @ ]
00007FFA794ED24F00007FFA794E71D0 python310.dll!PyEval_EvalFrameDefault [ @ ]
00007FFA794E626700007FFA794E61E0 python310.dll!PyFunction_Vectorcall [ @ ]
00007FFA794A0B3000007FFA794A0AD4 python310.dll!PyVectorcall_Call [ @ ]
00007FFA794A090700007FFA794A08B8 python310.dll!PyObject_Call [ @ ]
00007FF9913C780200007FF99139F550 torch_python.dll!torch::PythonArgParser::raw_parse [ @ ]
00007FF99770C3AC00007FF99770C240 torch_cpu.dll!c10::Dispatcher::callBoxed [ @ ]
00007FF99119D24000007FF99119D190 torch_python.dll!torch::jit::invokeOperatorFromPython [ @ ]
00007FF99119A2C700007FF99119A180 torch_python.dll!torch::jit::_get_operation_for_overload_or_packet [ @ ]
00007FF991102CA600007FF990FD7400 torch_python.dll!registerPythonTensorClass [ @ ]
00007FF9910AA4E600007FF990FD7400 torch_python.dll!registerPythonTensorClass [ @ ]
00007FF990B1140B00007FF990B0FE90 torch_python.dll!c10::ivalue::Future::devices [ @ ]
00007FFA794D49A600007FFA794D491C python310.dll!PyType_IsSubtype [ @ ]
00007FFA794A094E00007FFA794A08B8 python310.dll!PyObject_Call [ @ ]
00007FFA794A0A4B00007FFA794A08B8 python310.dll!PyObject_Call [ @ ]
00007FFA794ED24F00007FFA794E71D0 python310.dll!PyEval_EvalFrameDefault [ @ ]
00007FFA794E626700007FFA794E61E0 python310.dll!PyFunction_Vectorcall [ @ ]
00007FFA79499FE700007FFA79499F14 python310.dll!PyObject_FastCallDictTstate [ @ ]
00007FFA7949827300007FFA794981F4 python310.dll!PyObject_Call_Prepend [ @ ]
00007FFA794981A000007FFA79497FC0 python310.dll!PyUnicode_Concat [ @ ]
00007FFA794A6C3F00007FFA794A6AD4 python310.dll!PyObject_MakeTpCall [ @ ]
00007FFA794EE02B00007FFA794E71D0 python310.dll!PyEval_EvalFrameDefault [ @ ]
00007FFA794E626700007FFA794E61E0 python310.dll!PyFunction_Vectorcall [ @ ]
00007FFA794A0B3000007FFA794A0AD4 python310.dll!PyVectorcall_Call [ @ ]
00007FFA794A090700007FFA794A08B8 python310.dll!PyObject_Call [ @ ]
00007FF990FADD0100007FF990F99D50 torch_python.dll!THPPointer::THPPointer [ @ ]
00007FFA794D49D500007FFA794D491C python310.dll!PyType_IsSubtype [ @ ]
00007FFA794A094E00007FFA794A08B8 python310.dll!PyObject_Call [ @ ]
00007FFA794A0A4B00007FFA794A08B8 python310.dll!PyObject_Call [ @ ]
00007FFA794ED24F00007FFA794E71D0 python310.dll!PyEval_EvalFrameDefault [ @ ]
00007FFA794E4F1500007FFA794E3ED0 python310.dll!PyObject_GC_Malloc [ @ ]
00007FFA794E8C0B00007FFA794E71D0 python310.dll!PyEval_EvalFrameDefault [ @ ]
00007FFA794E626700007FFA794E61E0 python310.dll!PyFunction_Vectorcall [ @ ]
00007FFA794E77C400007FFA794E71D0 python310.dll!PyEval_EvalFrameDefault [ @ ]
00007FFA794E626700007FFA794E61E0 python310.dll!PyFunction_Vectorcall [ @ ]
00007FFA794E77C400007FFA794E71D0 python310.dll!PyEval_EvalFrameDefault [ @ ]
00007FFA794E626700007FFA794E61E0 python310.dll!PyFunction_Vectorcall [ @ ]
00007FFA79499FE700007FFA79499F14 python310.dll!PyObject_FastCallDictTstate [ @ ]
00007FFA7949827300007FFA794981F4 python310.dll!PyObject_Call_Prepend [ @ ]
00007FFA794981A000007FFA79497FC0 python310.dll!PyUnicode_Concat [ @ ]
00007FFA794A0A8300007FFA794A08B8 python310.dll!PyObject_Call [ @ ]
00007FFA794ED24F00007FFA794E71D0 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.

Start with the worker in webui/demo_gradio.py and follow the traceback through webui/diffusers_helper/k_diffusion/uni_pc_fm.py, wrapper.py, and models/hunyuan_video_packed.py to the FlashAttention call. Reproduce the reported generation failure and determine the expected behavior for GPUs that do not support FlashAttention; done means generation no longer stops with this runtime error on the reported setup.

Written by the indexing model from the issue text.