biegert / ComfyUI-CLIPSeg

ComfyUI CLIPSeg
Apache License 2.0
210 stars 34 forks source link

CLIPSeg Input image size (352*352) doesn't match model (224*224). #29

Open deepakpf opened 2 weeks ago

deepakpf commented 2 weeks ago

ComfyUI Error Report

Error Details

## System Information
- **ComfyUI Version:** v0.2.4-16-g30c0c81
- **Arguments:** C:\StabilityMatrix\Data\Packages\ComfyUI\main.py --normalvram --preview-method auto
- **OS:** nt
- **Python Version:** 3.10.11 (tags/v3.10.11:7d4cc5a, Apr  5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)]
- **Embedded Python:** false
- **PyTorch Version:** 2.5.1+cu124
## Devices

- **Name:** cuda:0 NVIDIA GeForce RTX 3050 Laptop GPU : cudaMallocAsync
  - **Type:** cuda
  - **VRAM Total:** 4294443008
  - **VRAM Free:** 2020587673
  - **Torch VRAM Total:** 2214592512
  - **Torch VRAM Free:** 844714546

## Logs

2024-10-29 11:21:52,277 - root - INFO - Total VRAM 4096 MB, total RAM 7919 MB 2024-10-29 11:21:52,277 - root - INFO - pytorch version: 2.5.1+cu124 2024-10-29 11:21:52,279 - root - INFO - Set vram state to: NORMAL_VRAM 2024-10-29 11:21:52,279 - root - INFO - Device: cuda:0 NVIDIA GeForce RTX 3050 Laptop GPU : cudaMallocAsync 2024-10-29 11:21:54,167 - root - INFO - Using pytorch cross attention 2024-10-29 11:21:55,934 - root - INFO - [Prompt Server] web root: C:\StabilityMatrix\Data\Packages\ComfyUI\web 2024-10-29 11:21:55,939 - root - INFO - Adding extra search path checkpoints C:\StabilityMatrix\Data\Models\StableDiffusion 2024-10-29 11:21:55,940 - root - INFO - Adding extra search path vae C:\StabilityMatrix\Data\Models\VAE 2024-10-29 11:21:55,940 - root - INFO - Adding extra search path loras C:\StabilityMatrix\Data\Models\Lora 2024-10-29 11:21:55,940 - root - INFO - Adding extra search path loras C:\StabilityMatrix\Data\Models\LyCORIS 2024-10-29 11:21:55,940 - root - INFO - Adding extra search path upscale_models C:\StabilityMatrix\Data\Models\ESRGAN 2024-10-29 11:21:55,940 - root - INFO - Adding extra search path upscale_models C:\StabilityMatrix\Data\Models\RealESRGAN 2024-10-29 11:21:55,940 - root - INFO - Adding extra search path upscale_models C:\StabilityMatrix\Data\Models\SwinIR 2024-10-29 11:21:55,940 - root - INFO - Adding extra search path embeddings C:\StabilityMatrix\Data\Models\TextualInversion 2024-10-29 11:21:55,940 - root - INFO - Adding extra search path hypernetworks C:\StabilityMatrix\Data\Models\Hypernetwork 2024-10-29 11:21:55,940 - root - INFO - Adding extra search path controlnet C:\StabilityMatrix\Data\Models\ControlNet 2024-10-29 11:21:55,940 - root - INFO - Adding extra search path controlnet C:\StabilityMatrix\Data\Models\T2IAdapter 2024-10-29 11:21:55,940 - root - INFO - Adding extra search path clip C:\StabilityMatrix\Data\Models\CLIP 2024-10-29 11:21:55,940 - root - INFO - Adding extra search path clip_vision C:\StabilityMatrix\Data\Models\InvokeClipVision 2024-10-29 11:21:55,941 - root - INFO - Adding extra search path diffusers C:\StabilityMatrix\Data\Models\Diffusers 2024-10-29 11:21:55,941 - root - INFO - Adding extra search path gligen C:\StabilityMatrix\Data\Models\GLIGEN 2024-10-29 11:21:55,941 - root - INFO - Adding extra search path vae_approx C:\StabilityMatrix\Data\Models\ApproxVAE 2024-10-29 11:21:55,941 - root - INFO - Adding extra search path ipadapter C:\StabilityMatrix\Data\Models\IpAdapter 2024-10-29 11:21:55,941 - root - INFO - Adding extra search path ipadapter C:\StabilityMatrix\Data\Models\InvokeIpAdapters15 2024-10-29 11:21:55,941 - root - INFO - Adding extra search path ipadapter C:\StabilityMatrix\Data\Models\InvokeIpAdaptersXl 2024-10-29 11:21:55,941 - root - INFO - Adding extra search path prompt_expansion C:\StabilityMatrix\Data\Models\PromptExpansion 2024-10-29 11:21:55,941 - root - INFO - Adding extra search path ultralytics C:\StabilityMatrix\Data\Models\Ultralytics 2024-10-29 11:21:55,941 - root - INFO - Adding extra search path ultralytics_bbox C:\StabilityMatrix\Data\Models\Ultralytics\bbox 2024-10-29 11:21:55,941 - root - INFO - Adding extra search path ultralytics_segm C:\StabilityMatrix\Data\Models\Ultralytics\segm 2024-10-29 11:21:55,941 - root - INFO - Adding extra search path sams C:\StabilityMatrix\Data\Models\Sams 2024-10-29 11:21:55,941 - root - INFO - Adding extra search path diffusion_models C:\StabilityMatrix\Data\Models\unet 2024-10-29 11:22:01,781 - root - INFO - Total VRAM 4096 MB, total RAM 7919 MB 2024-10-29 11:22:01,781 - root - INFO - pytorch version: 2.5.1+cu124 2024-10-29 11:22:01,782 - root - INFO - Set vram state to: NORMAL_VRAM 2024-10-29 11:22:01,783 - root - INFO - Device: cuda:0 NVIDIA GeForce RTX 3050 Laptop GPU : cudaMallocAsync 2024-10-29 11:22:03,461 - root - INFO - -------------- 2024-10-29 11:22:03,461 - root - INFO -  ### Mixlab Nodes: Loaded 2024-10-29 11:22:03,464 - root - INFO - ChatGPT.available False 2024-10-29 11:22:03,465 - root - INFO - editmask.available True 2024-10-29 11:22:04,501 - root - INFO - ClipInterrogator.available True 2024-10-29 11:22:04,752 - root - INFO - PromptGenerate.available True 2024-10-29 11:22:04,752 - root - INFO - ChinesePrompt.available True 2024-10-29 11:22:04,752 - root - INFO - RembgNode.available True 2024-10-29 11:22:05,363 - root - INFO - TripoSR.available 2024-10-29 11:22:05,364 - root - INFO - MiniCPMNode.available 2024-10-29 11:22:05,367 - root - INFO - Scenedetect.available False 2024-10-29 11:22:05,510 - root - INFO - FishSpeech.available False 2024-10-29 11:22:05,514 - root - INFO - SenseVoice.available False 2024-10-29 11:22:05,518 - root - INFO - Whisper.available False 2024-10-29 11:22:05,538 - root - INFO - FalVideo.available 2024-10-29 11:22:05,538 - root - INFO -  --------------  2024-10-29 11:22:11,311 - root - INFO - Import times for custom nodes: 2024-10-29 11:22:11,312 - root - INFO - 0.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\websocket_image_save.py 2024-10-29 11:22:11,312 - root - INFO - 0.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\ComfyUI_IPAdapter_plus 2024-10-29 11:22:11,312 - root - INFO - 0.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\sdxl_prompt_styler 2024-10-29 11:22:11,312 - root - INFO - 0.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\stability-ComfyUI-nodes 2024-10-29 11:22:11,312 - root - INFO - 0.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\efficiency-nodes-comfyui 2024-10-29 11:22:11,312 - root - INFO - 0.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\cg-use-everywhere 2024-10-29 11:22:11,312 - root - INFO - 0.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\ComfyUI-Universal-Styler 2024-10-29 11:22:11,312 - root - INFO - 0.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\ComfyUI_Gemini_Flash 2024-10-29 11:22:11,313 - root - INFO - 0.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\masquerade-nodes-comfyui 2024-10-29 11:22:11,313 - root - INFO - 0.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\ComfyUi_PromptStylers 2024-10-29 11:22:11,313 - root - INFO - 0.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\ComfyUI-YOLO 2024-10-29 11:22:11,313 - root - INFO - 0.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\ComfyUI_IPAdapter_plus.old 2024-10-29 11:22:11,313 - root - INFO - 0.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\ComfyUI-WD14-Tagger 2024-10-29 11:22:11,313 - root - INFO - 0.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\comfyui-photoshop 2024-10-29 11:22:11,313 - root - INFO - 0.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\ComfyLiterals 2024-10-29 11:22:11,313 - root - INFO - 0.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\comfyui_controlnet_aux 2024-10-29 11:22:11,313 - root - INFO - 0.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\comfyui-copilot 2024-10-29 11:22:11,313 - root - INFO - 0.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\ComfyUI_JPS-Nodes 2024-10-29 11:22:11,313 - root - INFO - 0.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\comfyui-stablesr 2024-10-29 11:22:11,313 - root - INFO - 0.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\ComfyUI-Impact-Pack 2024-10-29 11:22:11,314 - root - INFO - 0.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\ComfyUI-Custom-Scripts 2024-10-29 11:22:11,314 - root - INFO - 0.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\ComfyMath 2024-10-29 11:22:11,314 - root - INFO - 0.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\Derfuu_ComfyUI_ModdedNodes 2024-10-29 11:22:11,314 - root - INFO - 0.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\comfyui-various 2024-10-29 11:22:11,314 - root - INFO - 0.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\ComfyUI_essentials 2024-10-29 11:22:11,314 - root - INFO - 0.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\ComfyUI_UltimateSDUpscale 2024-10-29 11:22:11,314 - root - INFO - 0.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\rgthree-comfy 2024-10-29 11:22:11,314 - root - INFO - 0.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\ComfyUI-KJNodes-main 2024-10-29 11:22:11,314 - root - INFO - 0.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\ComfyUI-GGUF 2024-10-29 11:22:11,314 - root - INFO - 0.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\ComfyUI-Advanced-ControlNet 2024-10-29 11:22:11,314 - root - INFO - 0.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\ComfyUI_Comfyroll_CustomNodes 2024-10-29 11:22:11,314 - root - INFO - 0.1 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\ComfyUI-KJNodes 2024-10-29 11:22:11,314 - root - INFO - 0.1 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\comfy_mtb 2024-10-29 11:22:11,314 - root - INFO - 0.1 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\Comfyui-ergouzi-Nodes 2024-10-29 11:22:11,315 - root - INFO - 0.1 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\ComfyUI_LayerStyle 2024-10-29 11:22:11,315 - root - INFO - 0.2 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\eden_comfy_pipelines 2024-10-29 11:22:11,315 - root - INFO - 0.4 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\ComfyUI-Gemini 2024-10-29 11:22:11,315 - root - INFO - 0.5 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\ComfyUI-Crystools 2024-10-29 11:22:11,315 - root - INFO - 0.8 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\ComfyUI-Manager 2024-10-29 11:22:11,315 - root - INFO - 0.8 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\clipseg.py 2024-10-29 11:22:11,315 - root - INFO - 0.8 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\ComfyUI-Easy-Use 2024-10-29 11:22:11,315 - root - INFO - 1.0 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\ComfyUI-SUPIR 2024-10-29 11:22:11,315 - root - INFO - 1.1 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\comfyui-art-venture 2024-10-29 11:22:11,315 - root - INFO - 1.1 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\ComfyUI-Allor 2024-10-29 11:22:11,315 - root - INFO - 2.1 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\ComfyUI-YoloWorld-EfficientSAM 2024-10-29 11:22:11,315 - root - INFO - 2.2 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\was-node-suite-comfyui 2024-10-29 11:22:11,315 - root - INFO - 2.9 seconds: C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\comfyui-mixlab-nodes 2024-10-29 11:22:11,315 - root - INFO - 2024-10-29 11:22:11,348 - root - INFO - Starting server

2024-10-29 11:22:11,349 - root - INFO - To see the GUI go to: http://127.0.0.1:8188 2024-10-29 11:23:20,514 - root - INFO - got prompt 2024-10-29 11:23:36,196 - root - INFO - model weight dtype torch.float16, manual cast: None 2024-10-29 11:23:36,263 - root - INFO - model_type EPS 2024-10-29 11:23:40,782 - root - INFO - Using pytorch attention in VAE 2024-10-29 11:23:40,814 - root - INFO - Using pytorch attention in VAE 2024-10-29 11:23:42,538 - root - INFO - loaded straight to GPU 2024-10-29 11:23:42,538 - root - INFO - Requested to load BaseModel 2024-10-29 11:23:42,538 - root - INFO - Loading 1 new model 2024-10-29 11:23:42,594 - root - INFO - loaded completely 0.0 1639.406135559082 True 2024-10-29 11:23:42,804 - root - INFO - Requested to load SD1ClipModel 2024-10-29 11:23:42,804 - root - INFO - Loading 1 new model 2024-10-29 11:23:43,179 - root - INFO - loaded completely 0.0 235.84423828125 True 2024-10-29 11:23:44,218 - root - INFO - Using pytorch attention in VAE 2024-10-29 11:23:44,222 - root - INFO - Using pytorch attention in VAE 2024-10-29 11:23:49,892 - root - INFO - Requested to load CLIPVisionModelProjection 2024-10-29 11:23:49,893 - root - INFO - Loading 1 new model 2024-10-29 11:24:06,321 - root - INFO - loaded completely 0.0 1208.09814453125 True 2024-10-29 11:24:19,982 - root - INFO - Requested to load AutoencoderKL 2024-10-29 11:24:19,999 - root - INFO - Loading 1 new model 2024-10-29 11:24:23,251 - root - INFO - loaded completely 0.0 159.55708122253418 True 2024-10-29 11:24:28,836 - root - ERROR - !!! Exception during processing !!! Input image size (352352) doesn't match model (224224). 2024-10-29 11:24:28,878 - root - ERROR - Traceback (most recent call last): File "C:\StabilityMatrix\Data\Packages\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 "C:\StabilityMatrix\Data\Packages\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 "C:\StabilityMatrix\Data\Packages\ComfyUI\execution.py", line 169, in _map_node_over_list process_inputs(input_dict, i) File "C:\StabilityMatrix\Data\Packages\ComfyUI\execution.py", line 158, in process_inputs results.append(getattr(obj, func)(inputs)) File "C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\clipseg.py", line 127, in segment_image outputs = model(input_prc) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl return self._call_impl(*args, kwargs) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl return forward_call(*args, *kwargs) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\transformers\models\clipseg\modeling_clipseg.py", line 1436, in forward vision_outputs = self.clip.vision_model( File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl return self._call_impl(args, kwargs) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl return forward_call(*args, kwargs) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\transformers\models\clipseg\modeling_clipseg.py", line 870, in forward hidden_states = self.embeddings(pixel_values, interpolate_pos_encoding=interpolate_pos_encoding) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl return self._call_impl(*args, *kwargs) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl return forward_call(args, kwargs) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\transformers\models\clipseg\modeling_clipseg.py", line 211, in forward raise ValueError( ValueError: Input image size (352352) doesn't match model (224224).

2024-10-29 11:24:28,899 - root - INFO - Prompt executed in 68.34 seconds 2024-10-29 11:25:42,810 - root - INFO - got prompt 2024-10-29 11:25:53,158 - root - INFO - Requested to load SD1ClipModel 2024-10-29 11:25:53,161 - root - INFO - Loading 1 new model 2024-10-29 11:25:54,069 - root - INFO - loaded completely 0.0 235.84423828125 True 2024-10-29 11:25:55,048 - root - INFO - loaded completely 1386.798677253723 1208.09814453125 True 2024-10-29 11:25:59,724 - root - ERROR - !!! Exception during processing !!! Input image size (352352) doesn't match model (224224). 2024-10-29 11:25:59,724 - root - ERROR - Traceback (most recent call last): File "C:\StabilityMatrix\Data\Packages\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 "C:\StabilityMatrix\Data\Packages\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 "C:\StabilityMatrix\Data\Packages\ComfyUI\execution.py", line 169, in _map_node_over_list process_inputs(input_dict, i) File "C:\StabilityMatrix\Data\Packages\ComfyUI\execution.py", line 158, in process_inputs results.append(getattr(obj, func)(inputs)) File "C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\clipseg.py", line 127, in segment_image outputs = model(input_prc) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl return self._call_impl(*args, kwargs) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl return forward_call(*args, *kwargs) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\transformers\models\clipseg\modeling_clipseg.py", line 1436, in forward vision_outputs = self.clip.vision_model( File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl return self._call_impl(args, kwargs) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl return forward_call(*args, kwargs) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\transformers\models\clipseg\modeling_clipseg.py", line 870, in forward hidden_states = self.embeddings(pixel_values, interpolate_pos_encoding=interpolate_pos_encoding) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl return self._call_impl(*args, *kwargs) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl return forward_call(args, kwargs) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\transformers\models\clipseg\modeling_clipseg.py", line 211, in forward raise ValueError( ValueError: Input image size (352352) doesn't match model (224224).

2024-10-29 11:25:59,732 - root - INFO - Prompt executed in 16.87 seconds 2024-10-29 11:26:39,031 - root - INFO - got prompt 2024-10-29 11:26:39,434 - root - INFO - got prompt 2024-10-29 11:27:00,370 - root - INFO - Requested to load SD1ClipModel 2024-10-29 11:27:00,379 - root - INFO - Loading 1 new model 2024-10-29 11:27:02,082 - root - INFO - loaded completely 0.0 235.84423828125 True 2024-10-29 11:27:02,420 - root - INFO - Requested to load CLIPVisionModelProjection 2024-10-29 11:27:02,420 - root - INFO - Loading 1 new model 2024-10-29 11:27:04,563 - root - INFO - loaded completely 0.0 1208.09814453125 True 2024-10-29 11:27:09,787 - root - ERROR - !!! Exception during processing !!! Input image size (352352) doesn't match model (224224). 2024-10-29 11:27:09,803 - root - ERROR - Traceback (most recent call last): File "C:\StabilityMatrix\Data\Packages\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 "C:\StabilityMatrix\Data\Packages\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 "C:\StabilityMatrix\Data\Packages\ComfyUI\execution.py", line 169, in _map_node_over_list process_inputs(input_dict, i) File "C:\StabilityMatrix\Data\Packages\ComfyUI\execution.py", line 158, in process_inputs results.append(getattr(obj, func)(inputs)) File "C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\clipseg.py", line 127, in segment_image outputs = model(input_prc) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl return self._call_impl(*args, kwargs) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl return forward_call(*args, *kwargs) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\transformers\models\clipseg\modeling_clipseg.py", line 1436, in forward vision_outputs = self.clip.vision_model( File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl return self._call_impl(args, kwargs) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl return forward_call(*args, kwargs) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\transformers\models\clipseg\modeling_clipseg.py", line 870, in forward hidden_states = self.embeddings(pixel_values, interpolate_pos_encoding=interpolate_pos_encoding) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl return self._call_impl(*args, *kwargs) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl return forward_call(args, kwargs) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\transformers\models\clipseg\modeling_clipseg.py", line 211, in forward raise ValueError( ValueError: Input image size (352352) doesn't match model (224224).

2024-10-29 11:27:09,819 - root - INFO - Prompt executed in 30.75 seconds 2024-10-29 11:27:16,011 - root - ERROR - !!! Exception during processing !!! Input image size (352352) doesn't match model (224224). 2024-10-29 11:27:16,011 - root - ERROR - Traceback (most recent call last): File "C:\StabilityMatrix\Data\Packages\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 "C:\StabilityMatrix\Data\Packages\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 "C:\StabilityMatrix\Data\Packages\ComfyUI\execution.py", line 169, in _map_node_over_list process_inputs(input_dict, i) File "C:\StabilityMatrix\Data\Packages\ComfyUI\execution.py", line 158, in process_inputs results.append(getattr(obj, func)(inputs)) File "C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\clipseg.py", line 127, in segment_image outputs = model(input_prc) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl return self._call_impl(*args, kwargs) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl return forward_call(*args, *kwargs) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\transformers\models\clipseg\modeling_clipseg.py", line 1436, in forward vision_outputs = self.clip.vision_model( File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl return self._call_impl(args, kwargs) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl return forward_call(*args, kwargs) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\transformers\models\clipseg\modeling_clipseg.py", line 870, in forward hidden_states = self.embeddings(pixel_values, interpolate_pos_encoding=interpolate_pos_encoding) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl return self._call_impl(*args, *kwargs) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl return forward_call(args, kwargs) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\transformers\models\clipseg\modeling_clipseg.py", line 211, in forward raise ValueError( ValueError: Input image size (352352) doesn't match model (224224).

2024-10-29 11:27:16,011 - root - INFO - Prompt executed in 2.62 seconds 2024-10-29 11:28:06,490 - root - INFO - got prompt 2024-10-29 11:28:13,565 - root - INFO - Requested to load SD1ClipModel 2024-10-29 11:28:13,568 - root - INFO - Loading 1 new model 2024-10-29 11:28:14,369 - root - INFO - loaded completely 0.0 235.84423828125 True 2024-10-29 11:28:14,894 - root - INFO - loaded completely 1386.798677253723 1208.09814453125 True 2024-10-29 11:28:19,253 - root - ERROR - !!! Exception during processing !!! Input image size (352352) doesn't match model (224224). 2024-10-29 11:28:19,257 - root - ERROR - Traceback (most recent call last): File "C:\StabilityMatrix\Data\Packages\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 "C:\StabilityMatrix\Data\Packages\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 "C:\StabilityMatrix\Data\Packages\ComfyUI\execution.py", line 169, in _map_node_over_list process_inputs(input_dict, i) File "C:\StabilityMatrix\Data\Packages\ComfyUI\execution.py", line 158, in process_inputs results.append(getattr(obj, func)(inputs)) File "C:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\clipseg.py", line 127, in segment_image outputs = model(input_prc) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl return self._call_impl(*args, kwargs) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl return forward_call(*args, *kwargs) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\transformers\models\clipseg\modeling_clipseg.py", line 1436, in forward vision_outputs = self.clip.vision_model( File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl return self._call_impl(args, kwargs) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl return forward_call(*args, kwargs) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\transformers\models\clipseg\modeling_clipseg.py", line 870, in forward hidden_states = self.embeddings(pixel_values, interpolate_pos_encoding=interpolate_pos_encoding) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl return self._call_impl(*args, *kwargs) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl return forward_call(args, kwargs) File "C:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\transformers\models\clipseg\modeling_clipseg.py", line 211, in forward raise ValueError( ValueError: Input image size (352352) doesn't match model (224224).

2024-10-29 11:28:19,259 - root - INFO - Prompt executed in 12.73 seconds

## Attached Workflow
Please make sure that workflow does not contain any sensitive information such as API keys or passwords.

Workflow too large. Please manually upload the workflow from local file system.



## Additional Context
(Please add any additional context or steps to reproduce the error here)
marid2607 commented 5 days ago

Same problem since last update...

vfxturjo commented 3 days ago

:( same problem...