Generate Video problem

[SimpleYj]

Generate Prompt Right
Generate Key Frames Right

Generate Video Error,The error message is as follows：

Unload to CPU: Resampler
Unload to CPU: ImprovedCLIPVisionModelWithProjection
Load to GPU: CLIPTextModel
Unload to CPU: CLIPTextModel
Load to GPU: Resampler
Load to GPU: ImprovedCLIPVisionModelWithProjection
Traceback (most recent call last):
File "/chencai/Paints-UNDO/.venv/lib/python3.12/site-packages/gradio/queueing.py", line 536, in process_events
response = await route_utils.call_process_api(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/chencai/Paints-UNDO/.venv/lib/python3.12/site-packages/gradio/route_utils.py", line 321, in call_process_api
output = await app.get_blocks().process_api(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/chencai/Paints-UNDO/.venv/lib/python3.12/site-packages/gradio/blocks.py", line 1935, in process_api
result = await self.call_function(
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/chencai/Paints-UNDO/.venv/lib/python3.12/site-packages/gradio/blocks.py", line 1520, in call_function
prediction = await anyio.to_thread.run_sync( # type: ignore
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/chencai/Paints-UNDO/.venv/lib/python3.12/site-packages/anyio/to_thread.py", line 56, in run_sync
return await get_async_backend().run_sync_in_worker_thread(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/chencai/Paints-UNDO/.venv/lib/python3.12/site-packages/anyio/_backends/_asyncio.py", line 2461, in run_sync_in_worker_thread
return await future
^^^^^^^^^^^^
File "/chencai/Paints-UNDO/.venv/lib/python3.12/site-packages/anyio/_backends/_asyncio.py", line 962, in run
result = context.run(func, *args)
^^^^^^^^^^^^^^^^^^^^^^^^
File "/chencai/Paints-UNDO/.venv/lib/python3.12/site-packages/gradio/utils.py", line 826, in wrapper
response = f(*args, **kwargs)
^^^^^^^^^^^^^^^^^^
File "/chencai/Paints-UNDO/.venv/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/chencai/Paints-UNDO/gradio_app.py", line 222, in process_video
frames, im1, im2 = process_video_inner(
^^^^^^^^^^^^^^^^^^^^
File "/chencai/Paints-UNDO/.venv/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/chencai/Paints-UNDO/gradio_app.py", line 183, in process_video_inner
positive_image_cond = video_pipe.encode_clip_vision(input_frames)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/chencai/Paints-UNDO/.venv/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/chencai/Paints-UNDO/diffusers_vdm/pipeline.py", line 94, in encode_clip_vision
clipvision_embed = self.image_encoder(frames).last_hidden_state
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/chencai/Paints-UNDO/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/chencai/Paints-UNDO/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/chencai/Paints-UNDO/.venv/lib/python3.12/site-packages/transformers/models/clip/modeling_clip.py", line 1554, in forward
vision_outputs = self.vision_model(
^^^^^^^^^^^^^^^^^^
File "/chencai/Paints-UNDO/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/chencai/Paints-UNDO/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/chencai/Paints-UNDO/.venv/lib/python3.12/site-packages/transformers/models/clip/modeling_clip.py", line 1093, in forward
hidden_states = self.embeddings(pixel_values, interpolate_pos_encoding=interpolate_pos_encoding)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/chencai/Paints-UNDO/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/chencai/Paints-UNDO/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: improved_clipvision_embedding_forward() got an unexpected keyword argument 'interpolate_pos_encoding'

[FurkanGozukara]

i published installers : https://github.com/lllyasviel/Paints-UNDO/issues/100

[borick]

@FurkanGozukara the installer seemed locked, is there any way? I'm near the end, fixed a few package versions, can u tell me how you fixed return forward_call(*args, **kwargs)
TypeError: improved_clipvision_embedding_forward() got an unexpected keyword argument 'interpolate_pos_encoding' please? thanks

[gwa22]

@FurkanGozukara the installer seemed locked, is there any way? I'm near the end, fixed a few package versions, can u tell me how you fixed return forward_call(*args, **kwargs) TypeError: improved_clipvision_embedding_forward() got an unexpected keyword argument 'interpolate_pos_encoding' please? thanks

did you find out how?