Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

UnboundLocalError: local variable 'out' referenced before assignment #42

Open
blueroutecn opened this issue Jan 11, 2025 · 0 comments
Open

Comments

@blueroutecn
Copy link

Added trellis path to sys.path: /home/llm/linda/lab2/custom_nodes/ComfyUI-IF_Trellis/trellis
[SPARSE] Backend: spconv, Attention: flash_attn
Warp 1.5.0 initialized:
CUDA Toolkit 12.6, Driver 12.0
Devices:
"cpu" : "x86_64"
"cuda:0" : "NVIDIA GeForce RTX 3090" (24 GiB, sm_86, mempool enabled)
Kernel cache:
/root/.cache/warp/1.5.0
[SPARSE][CONV] spconv algo: implicit_gemm
Trellis package imported successfully

Loading: ComfyUI-Manager (V3.6.2)

ComfyUI Version: v0.3.10-47-gee8a7ab6 | Released on '2025-01-11'

Import times for custom nodes:
0.0 seconds: /home/llm/linda/lab2/custom_nodes/websocket_image_save.py
0.0 seconds: /home/llm/linda/lab2/custom_nodes/ComfyUI-Universal-Styler
0.0 seconds: /home/llm/linda/lab2/custom_nodes/ComfyUI-Custom-Scripts
0.0 seconds: /home/llm/linda/lab2/custom_nodes/ComfyUI-VideoHelperSuite
0.0 seconds: /home/llm/linda/lab2/custom_nodes/rgthree-comfy
0.1 seconds: /home/llm/linda/lab2/custom_nodes/ComfyUI-Manager
2.1 seconds: /home/llm/linda/lab2/custom_nodes/ComfyUI-IF_AI_tools
2.6 seconds: /home/llm/linda/lab2/custom_nodes/ComfyUI-IF_Trellis

error info:

Processed image 0, shape: (704, 704, 3), mode: RGB
Sampling: 0%| | 0/12 [00:00<?, ?it/s]
Error in image_to_3d: local variable 'out' referenced before assignment
Traceback (most recent call last):
File "/home/llm/linda/lab2/custom_nodes/ComfyUI-IF_Trellis/IF_Trellis.py", line 319, in image_to_3d
outputs = model.run(pil_imgs[0], **pipeline_params)
File "/home/llm/linda/lab2/venv/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
File "/home/llm/linda/lab2/custom_nodes/ComfyUI-IF_Trellis/trellis/pipelines/trellis_image_to_3d.py", line 408, in run
coords = self.sample_sparse_structure(cond, num_samples, sparse_structure_sampler_params)
File "/home/llm/linda/lab2/venv/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
File "/home/llm/linda/lab2/custom_nodes/ComfyUI-IF_Trellis/trellis/pipelines/trellis_image_to_3d.py", line 285, in sample_sparse_structure
z_s = self.sparse_structure_sampler.sample(
File "/home/llm/linda/lab2/venv/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
File "/home/llm/linda/lab2/custom_nodes/ComfyUI-IF_Trellis/trellis/pipelines/samplers/flow_euler.py", line 199, in sample
return super().sample(model, noise, cond, steps, rescale_t, verbose, neg_cond=neg_cond, cfg_strength=cfg_strength, cfg_interval=cfg_interval, **kwargs)
File "/home/llm/linda/lab2/venv/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
File "/home/llm/linda/lab2/custom_nodes/ComfyUI-IF_Trellis/trellis/pipelines/samplers/flow_euler.py", line 112, in sample
out = self.sample_once(model, sample, t, t_prev, cond, **kwargs)
File "/home/llm/linda/lab2/venv/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
File "/home/llm/linda/lab2/custom_nodes/ComfyUI-IF_Trellis/trellis/pipelines/samplers/flow_euler.py", line 73, in sample_once
pred_x_0, pred_eps, pred_v = self._get_model_prediction(model, x_t, t, cond, **kwargs)
File "/home/llm/linda/lab2/custom_nodes/ComfyUI-IF_Trellis/trellis/pipelines/samplers/flow_euler.py", line 43, in _get_model_prediction
pred_v = self._inference_model(model, x_t, t, cond, **kwargs)
File "/home/llm/linda/lab2/custom_nodes/ComfyUI-IF_Trellis/trellis/pipelines/samplers/guidance_interval_mixin.py", line 11, in _inference_model
pred = super()._inference_model(model, x_t, t, cond, **kwargs)
File "/home/llm/linda/lab2/custom_nodes/ComfyUI-IF_Trellis/trellis/pipelines/samplers/flow_euler.py", line 40, in _inference_model
return model(x_t, t, cond, **kwargs)
File "/home/llm/linda/lab2/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/home/llm/linda/lab2/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
return forward_call(*args, **kwargs)
File "/home/llm/linda/lab2/custom_nodes/ComfyUI-IF_Trellis/trellis/models/sparse_structure_flow.py", line 192, in forward
h = block(h, t_emb, cond)
File "/home/llm/linda/lab2/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/home/llm/linda/lab2/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
return forward_call(*args, **kwargs)
File "/home/llm/linda/lab2/custom_nodes/ComfyUI-IF_Trellis/trellis/modules/transformer/modulated.py", line 156, in forward
return self._forward(x, mod, context)
File "/home/llm/linda/lab2/custom_nodes/ComfyUI-IF_Trellis/trellis/modules/transformer/modulated.py", line 139, in _forward
h = self.self_attn(h)
File "/home/llm/linda/lab2/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/home/llm/linda/lab2/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
return forward_call(*args, **kwargs)
File "/home/llm/linda/lab2/custom_nodes/ComfyUI-IF_Trellis/trellis/modules/attention/modules.py", line 126, in forward
h = scaled_dot_product_attention(q, k, v)
File "/home/llm/linda/lab2/custom_nodes/ComfyUI-IF_Trellis/trellis/modules/attention/full_attn.py", line 120, in scaled_dot_product_attention
out = flash_attn.flash_attn_func(q, k, v)
File "/home/llm/linda/lab2/venv/lib/python3.10/site-packages/flash_attn/flash_attn_interface.py", line 1189, in flash_attn_func
return FlashAttnFunc.apply(
File "/home/llm/linda/lab2/venv/lib/python3.10/site-packages/torch/autograd/function.py", line 575, in apply
return super().apply(*args, **kwargs) # type: ignore[misc]
File "/home/llm/linda/lab2/venv/lib/python3.10/site-packages/flash_attn/flash_attn_interface.py", line 853, in forward
return out if not return_softmax else (out, softmax_lse, S_dmask)
UnboundLocalError: local variable 'out' referenced before assignment

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant