optimizations: xformers for prior;sequential CPU offloading for prior;xformers for decoder;sequential CPU offloading for decoder;attention slicing for decoder: slice_size=max
seed generated: 54955802784
0% 0/25 [00:00<?, ?it/s]
Traceback (most recent call last):
File "/usr/local/lib/python3.10/dist-packages/gradio/routes.py", line 439, in run_predict
output = await app.get_blocks().process_api(
File "/usr/local/lib/python3.10/dist-packages/gradio/blocks.py", line 1384, in process_api
result = await self.call_function(
File "/usr/local/lib/python3.10/dist-packages/gradio/blocks.py", line 1089, in call_function
prediction = await anyio.to_thread.run_sync(
File "/usr/local/lib/python3.10/dist-packages/anyio/to_thread.py", line 33, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "/usr/local/lib/python3.10/dist-packages/anyio/_backends/_asyncio.py", line 877, in run_sync_in_worker_thread
return await future
File "/usr/local/lib/python3.10/dist-packages/anyio/_backends/_asyncio.py", line 807, in run
result = context.run(func, *args)
File "/usr/local/lib/python3.10/dist-packages/gradio/utils.py", line 700, in wrapper
response = f(*args, **kwargs)
File "/content/kubin/src/ui_blocks/t2i.py", line 240, in generate
return generate_fn(params)
File "/content/kubin/src/webui.py", line 34, in
generate_fn=lambda params: kubin.model.t2i(params),
File "/content/kubin/src/models/model_diffusers22/model_22.py", line 116, in t2i
return self.t2i_cnet(params)
File "/content/kubin/src/models/model_diffusers22/model_22.py", line 457, in t2i_cnet
image_embeds, zero_embeds = prior(
File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/diffusers/pipelines/kandinsky2_2/pipeline_kandinsky2_2_prior.py", line 494, in call
predicted_image_embedding = self.prior(
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/diffusers/models/prior_transformer.py", line 346, in forward
hidden_states = block(hidden_states, attention_mask=attention_mask)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/diffusers/models/attention.py", line 154, in forward
attn_output = self.attn1(
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/diffusers/models/attention_processor.py", line 321, in forward
return self.processor(
File "/usr/local/lib/python3.10/dist-packages/diffusers/models/attention_processor.py", line 1046, in call
hidden_states = xformers.ops.memory_efficient_attention(
File "/usr/local/lib/python3.10/dist-packages/xformers/ops/fmha/init.py", line 192, in memory_efficient_attention
return _memory_efficient_attention(
File "/usr/local/lib/python3.10/dist-packages/xformers/ops/fmha/init.py", line 290, in _memory_efficient_attention
return _memory_efficient_attention_forward(
File "/usr/local/lib/python3.10/dist-packages/xformers/ops/fmha/init.py", line 308, in _memory_efficient_attention_forward
_ensure_op_supports_or_raise(ValueError, "memory_efficient_attention", op, inp)
File "/usr/local/lib/python3.10/dist-packages/xformers/ops/fmha/dispatch.py", line 45, in _ensure_op_supports_or_raise
raise exc_type(
ValueError: Operator memory_efficient_attention
does not support inputs:
query : shape=(64, 81, 1, 64) (torch.float16)
key : shape=(64, 81, 1, 64) (torch.float16)
value : shape=(64, 81, 1, 64) (torch.float16)
attn_bias : <class 'torch.Tensor'>
p : 0.0
flshattF
is not supported because:
attn_bias type is <class 'torch.Tensor'>