search

CY-CHENYUE / ComfyUI-Molmo

Generate detailed image descriptions and analysis using Molmo models in ComfyUI.
Apache License 2.0
96 stars 5 forks source link

TypeError: _stack_dispatcher() got an unexpected keyword argument 'dtype' #14

Open ShmuelRonen opened 1 month ago

ShmuelRonen commented 1 month ago

got prompt Loading model from /home/sam/ComfyUI/models/Molmo/molmo-7B-D-bnb-4bit Unused kwargs: ['_load_in_4bit', '_load_in_8bit', 'quant_method']. These kwargs are not used in <class 'transformers.utils.quantization_config.BitsAndBytesConfig'>. We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set max_memory in to a higher value to use more memory (at your own risk). Loading checkpoint shards: 100%|██████████████████████████████████████████████████████████| 2/2 [00:02<00:00, 1.39s/it] Model and processor have been unloaded, and CUDA cache has been cleared. !!! Exception during processing !!! _stack_dispatcher() got an unexpected keyword argument 'dtype' Traceback (most recent call last): File "/home/sam/ComfyUI/execution.py", line 323, in execute output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) File "/home/sam/ComfyUI/execution.py", line 198, in get_output_data return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) File "/home/sam/ComfyUI/execution.py", line 169, in _map_node_over_list process_inputs(input_dict, i) File "/home/sam/ComfyUI/execution.py", line 158, in process_inputs results.append(getattr(obj, func)(**inputs)) File "/home/sam/ComfyUI/custom_nodes/ComfyUI-Molmo/Molmo7BDbnb.py", line 170, in generate_caption inputs = self.processor.process( File "/home/sam/.cache/huggingface/modules/transformers_modules/molmo-7B-D-bnb-4bit/preprocessing_molmo.py", line 145, in process out = self.image_processor.multimodal_preprocess( File "/home/sam/.cache/huggingface/modules/transformers_modules/molmo-7B-D-bnb-4bit/image_preprocessing_molmo.py", line 525, in multimodal_preprocess crops, image_tokens, patch_idx, img_mask = self.preprocess( File "/home/sam/.cache/huggingface/modules/transformers_modules/molmo-7B-D-bnb-4bit/image_preprocessing_molmo.py", line 450, in preprocess crops, image_tokens, patch_ordering, img_mask = self.image_to_patches_and_tokens( File "/home/sam/.cache/huggingface/modules/transformers_modules/molmo-7B-D-bnb-4bit/image_preprocessing_molmo.py", line 235, in image_to_patches_and_tokens tiling = select_tiling( File "/home/sam/.cache/huggingface/modules/transformers_modules/molmo-7B-D-bnb-4bit/image_preprocessing_molmo.py", line 138, in select_tiling original_size = np.stack([h, w], dtype=np.float32) # [1, 2] File "<__array_function__ internals>", line 179, in stack TypeError: _stack_dispatcher() got an unexpected keyword argument 'dtype'

My ComfyUI :

Platform: Linux Python version: 3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0] Python executable: /home/sam/ComfyUI/venv/bin/python ComfyUI Path: /home/sam/ComfyUI ** Log path: /home/sam/ComfyUI/comfyui.log

Total VRAM 24576 MB, total RAM 31689 MB pytorch version: 2.4.1+cu121 xformers version: 0.0.28.post1 Set vram state to: NORMAL_VRAM Device: cuda:0 NVIDIA GeForce RTX 3090 : cudaMallocAsync Using xformers cross attention

ShmuelRonen commented 1 month ago

Find a solution 👍 pip install numpy==1.24.4