CommonCanvas-S-C no longer works

### Custom Node Testing

- [x] I have tried disabling custom nodes and the issue persists (see [how to disable custom nodes](https://docs.comfy.org/troubleshooting/custom-node-issues#step-1%3A-test-with-all-custom-nodes-disabled) if you need help)

### Expected Behavior

It will work as it did previously.

### Actual Behavior

It errors when it reaches the CLIP text encode nodes.

### Steps to Reproduce

Use CommonCanvas-S-C in any sort of workflow. Minimal reproducible example attached.

[minimal.json](https://github.com/user-attachments/files/30862676/minimal.json)

### Debug Logs

```powershell
[INFO] Found comfy_kitchen backend cuda: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope1_', 'apply_rope_', 'apply_rope_split_half', 'apply_rope_split_half1', 'apply_rope_split_half1_', 'apply_rope_split_half_', 'convrot_w4a4_linear', 'dequantize_convrot_w4a4_weight', 'dequantize_int8_convrot_weight', 'dequantize_int8_convrot_weight_dtype', 'dequantize_int8_simple', 'dequantize_int8_simple_dtype', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'dequantize_w4a8_int8_weight', 'gemv_awq_w4a16', 'int8_linear', 'na3d', 'prepare_int4_weight_for_int8_linear', 'quantize_and_rotate_rowwise', 'quantize_convrot_w4a4_weight', 'quantize_int8_convrot_weight', 'quantize_int8_rowwise', 'quantize_int8_tensorwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'quantize_svdquant_w4a4', 'quantize_w4a8_int8_weight', 'rms_adaln', 'rms_rope', 'rms_rope1', 'rms_rope1_', 'rms_rope_', 'rms_rope_split_half', 'rms_rope_split_half1', 'rms_rope_split_half1_', 'rms_rope_split_half_', 'rotate_int8_convrot_weight', 'scaled_mm_nvfp4', 'scaled_mm_svdquant_w4a4', 'stochastic_rounding_fp8', 'w4a8_int8_linear']}
[INFO] Found comfy_kitchen backend triton: {'available': True, 'disabled': True, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope1_', 'apply_rope_', 'apply_rope_split_half', 'apply_rope_split_half1', 'apply_rope_split_half1_', 'apply_rope_split_half_', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'int8_linear', 'na3d', 'quantize_and_rotate_rowwise', 'quantize_int8_rowwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'rms_adaln', 'rms_rope', 'rms_rope1', 'rms_rope1_', 'rms_rope_', 'rms_rope_split_half', 'rms_rope_split_half1', 'rms_rope_split_half1_', 'rms_rope_split_half_', 'w4a8_int8_linear']}
[INFO] Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope1_', 'apply_rope_', 'apply_rope_split_half', 'apply_rope_split_half1', 'apply_rope_split_half1_', 'apply_rope_split_half_', 'convrot_w4a4_linear', 'dequantize_convrot_w4a4_weight', 'dequantize_int8_convrot_weight', 'dequantize_int8_convrot_weight_dtype', 'dequantize_int8_embedding', 'dequantize_int8_simple', 'dequantize_int8_simple_dtype', 'dequantize_mxfp8', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'dequantize_w4a8_int8_weight', 'gemv_awq_w4a16', 'int8_linear', 'na3d', 'prepare_int4_weight_for_int8_linear', 'quantize_and_rotate_rowwise', 'quantize_convrot_w4a4_weight', 'quantize_int8_convrot_weight', 'quantize_int8_rowwise', 'quantize_int8_tensorwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'quantize_svdquant_w4a4', 'quantize_w4a8_int8_weight', 'rms_adaln', 'rms_rope', 'rms_rope1', 'rms_rope1_', 'rms_rope_', 'rms_rope_split_half', 'rms_rope_split_half1', 'rms_rope_split_half1_', 'rms_rope_split_half_', 'rotate_int8_convrot_weight', 'scaled_mm_mxfp8', 'scaled_mm_nvfp4', 'scaled_mm_svdquant_w4a4', 'stochastic_rounding_fp8', 'w4a8_int8_linear']}
[INFO] Found comfy_kitchen backend hip: {'available': False, 'disabled': False, 'unavailable_reason': 'PyTorch ROCm/HIP runtime not available', 'capabilities': []}
[INFO] Checkpoint files will always be loaded safely.
[INFO] Total VRAM 24124 MB, total RAM 64209 MB
[INFO] pytorch version: 2.10.0+cu130
[INFO] Set vram state to: NORMAL_VRAM
[INFO] Device: cuda:0 NVIDIA GeForce RTX 3090 : cudaMallocAsync
[INFO] Using async weight offloading with 2 streams
[INFO] Enabled pinned memory 57788.0
[INFO] Using pytorch attention
[INFO] aimdo: /project/src/control.c:276:INFO:comfy-aimdo inited for GPU: NVIDIA GeForce RTX 3090 (VRAM: 24124 MB)
[INFO] DynamicVRAM support detected and enabled
[INFO] Python version: 3.11.13 (main, Jun 5 2025, 13:12:00) [GCC 11.2.0]
[INFO] ComfyUI version: 0.31.0
[INFO] comfy-aimdo version: 0.4.13
[INFO] comfy-kitchen version: 0.2.28
[INFO] comfyui-frontend-package version: 1.48.7
[INFO] comfyui-workflow-templates version: 0.11.37
[INFO] comfyui-embedded-docs version: 0.5.9
[INFO] comfy-kitchen version: 0.2.28
[INFO] comfy-aimdo version: 0.4.13
[INFO] [Prompt Server] web root: /home/moth/.conda/envs/ldm/lib/python3.11/site-packages/comfyui_frontend_package/static
[INFO] Asset seeder disabled
[INFO] No OpenGL_accelerate module loaded: No module named 'OpenGL_accelerate'
[INFO] Skipping loading of custom nodes
[INFO] Context impl SQLiteImpl.
[INFO] Will assume non-transactional DDL.
[INFO] Using RAM pressure cache.
[INFO] Starting server

[INFO] To see the GUI go to: http://10.0.0.70:8188
[INFO] got prompt
[INFO] model weight dtype torch.float16, manual cast: None
[INFO] model_type EPS
[INFO] Using pytorch attention in VAE
[INFO] Using pytorch attention in VAE
[INFO] VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
[WARNING] clip missing: ['clip_h.logit_scale', 'clip_h.transformer.text_model.encoder.layers.23.layer_norm1.weight', 'clip_h.transformer.text_model.encoder.layers.23.layer_norm1.bias', 'clip_h.transformer.text_model.encoder.layers.23.self_attn.q_proj.weight', 'clip_h.transformer.text_model.encoder.layers.23.self_attn.q_proj.bias', 'clip_h.transformer.text_model.encoder.layers.23.self_attn.k_proj.weight', 'clip_h.transformer.text_model.encoder.layers.23.self_attn.k_proj.bias', 'clip_h.transformer.text_model.encoder.layers.23.self_attn.v_proj.weight', 'clip_h.transformer.text_model.encoder.layers.23.self_attn.v_proj.bias', 'clip_h.transformer.text_model.encoder.layers.23.self_attn.out_proj.weight', 'clip_h.transformer.text_model.encoder.layers.23.self_attn.out_proj.bias', 'clip_h.transformer.text_model.encoder.layers.23.layer_norm2.weight', 'clip_h.transformer.text_model.encoder.layers.23.layer_norm2.bias', 'clip_h.transformer.text_model.encoder.layers.23.mlp.fc1.weight', 'clip_h.transformer.text_model.encoder.layers.23.mlp.fc1.bias', 'clip_h.transformer.text_model.encoder.layers.23.mlp.fc2.weight', 'clip_h.transformer.text_model.encoder.layers.23.mlp.fc2.bias', 'clip_h.transformer.text_projection.weight']
[INFO] CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16
[INFO] Requested to load SD2ClipModel
[INFO] Model SD2ClipModel prepared for dynamic VRAM loading. 675MB Staged. 0 patches attached. Force pre-loaded 98 weights: 196 KB.
[ERROR] !!! Exception during processing !!! mat1 and mat2 shapes cannot be multiplied (77x1024 and 4096x1024)
[ERROR] Traceback (most recent call last):
File "/home/moth/programming/ComfyUI/execution.py", line 545, in execute
output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/moth/programming/ComfyUI/execution.py", line 344, in get_output_data
return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/moth/programming/ComfyUI/execution.py", line 318, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "/home/moth/programming/ComfyUI/execution.py", line 306, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "/home/moth/programming/ComfyUI/nodes.py", line 77, in encode
return (clip.encode_from_tokens_scheduled(tokens), )
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/moth/programming/ComfyUI/comfy/sd.py", line 336, in encode_from_tokens_scheduled
pooled_dict = self.encode_from_tokens(tokens, return_pooled=return_pooled, return_dict=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/moth/programming/ComfyUI/comfy/sd.py", line 405, in encode_from_tokens
o = self.cond_stage_model.encode_token_weights(tokens)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/moth/programming/ComfyUI/comfy/sd1_clip.py", line 743, in encode_token_weights
out = getattr(self, self.clip).encode_token_weights(token_weight_pairs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/moth/programming/ComfyUI/comfy/sd1_clip.py", line 45, in encode_token_weights
o = self.encode(to_encode)
^^^^^^^^^^^^^^^^^^^^^^
File "/home/moth/programming/ComfyUI/comfy/sd1_clip.py", line 306, in encode
return self(tokens)
^^^^^^^^^^^^
File "/home/moth/.conda/envs/ldm/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1776, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/moth/.conda/envs/ldm/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1787, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/moth/programming/ComfyUI/comfy/sd1_clip.py", line 279, in forward
outputs = self.transformer(None, attention_mask_model, embeds=embeds, num_tokens=num_tokens, intermediate_output=intermediate_output, final_layer_norm_intermediate=self.layer_norm_hidden_state, dtype=torch.float32, embeds_info=embeds_info)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/moth/.conda/envs/ldm/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1776, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/moth/.conda/envs/ldm/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1787, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/moth/programming/ComfyUI/comfy/clip_model.py", line 208, in forward
x = self.text_model(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/moth/.conda/envs/ldm/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1776, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/moth/.conda/envs/ldm/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1787, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/moth/programming/ComfyUI/comfy/clip_model.py", line 181, in forward
x, i = self.encoder(x, mask=mask, intermediate_output=intermediate_output)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/moth/.conda/envs/ldm/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1776, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/moth/.conda/envs/ldm/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1787, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/moth/programming/ComfyUI/comfy/clip_model.py", line 127, in forward
x = l(x, mask, optimized_attention)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/moth/.conda/envs/ldm/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1776, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/moth/.conda/envs/ldm/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1787, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/moth/programming/ComfyUI/comfy/clip_model.py", line 105, in forward
x += self.mlp(self.layer_norm2(x))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/moth/.conda/envs/ldm/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1776, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/moth/.conda/envs/ldm/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1787, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/moth/programming/ComfyUI/comfy/clip_model.py", line 90, in forward
x = self.fc1(x)
^^^^^^^^^^^
File "/home/moth/.conda/envs/ldm/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1776, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/moth/.conda/envs/ldm/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1787, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/moth/programming/ComfyUI/comfy/ops.py", line 549, in forward
return self.forward_comfy_cast_weights(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/moth/programming/ComfyUI/comfy/ops.py", line 542, in forward_comfy_cast_weights
x = torch.nn.functional.linear(input, weight, bias)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: mat1 and mat2 shapes cannot be multiplied (77x1024 and 4096x1024)

[INFO] Prompt executed in 1.77 seconds
```

### Other

Not sure what's up with the warning it gives about CLIP missing. But it's always done that and didn't cause any issues previously.

Start by loading the attached minimal.json with custom nodes disabled and reproduce the failure at the CLIP text encode nodes. Read nodes.py, comfy/sd.py, comfy/sd1_clip.py, and comfy/clip_model.py alongside the missing-clip warning and matrix-shape error. Done means the CommonCanvas-S-C workflow reaches and completes CLIP encoding without that exception.

Written by the indexing model from the issue text.