fkunn1326
Detect from image not work
Describe the bug Detect from image not work To Reproduce click Detect from image，select a picture，and then error
remove stable-diffusion-webui\models\body_pose_model.pth and relaunch will work for you
same here, I reinstall openpose and deleted the file body_pose_model. I restarted and it downloaded the model. Then error. 100%|███████████████████████████████████████████████████████████████████████████████| 200M/200M [00:16<00:00, 12.7MB/s] Traceback (most recent call last): File "E:\Documents\A1111 Web UI Autoinstaller\stable-diffusion-webui\venv\lib\site-packages\gradio\routes.py", line 39 4, in run_predict output = await app.get_blocks().process_api( File "E:\Documents\A1111 Web UI Autoinstaller\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 10 75, in process_api result = await self.call_function( File "E:\Documents\A1111 Web UI Autoinstaller\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 88 4, in call_function prediction = await anyio.to_thread.run_sync( File "E:\Documents\A1111 Web UI Autoinstaller\stable-diffusion-webui\venv\lib\site-packages\anyio\to_thread.py", line 31, in run_sync return await get_asynclib().run_sync_in_worker_thread( File "E:\Documents\A1111 Web UI Autoinstaller\stable-diffusion-webui\venv\lib\site-packages\anyio_backends_asyncio.p y", line 937, in run_sync_in_worker_thread return await future File "E:\Documents\A1111 Web UI Autoinstaller\stable-diffusion-webui\venv\lib\site-packages\anyio_backends_asyncio.p y", line 867, in run result = context.run(func, *args) File "E:\Documents\A1111 Web UI Autoinstaller\stable-diffusion-webui\extensions\openpose-editor\scripts\main.py", line 106, in estimate candidate, subset = body_estimation(pil2cv(img)) File "E:\Documents\A1111 Web UI Autoinstaller\stable-diffusion-webui\extensions\openpose-editor\scripts\openpose\body. py", line 49, in call Mconv7_stage6_L1, Mconv7_stage6_L2 = self.model(data) File "E:\Documents\A1111 Web UI Autoinstaller\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py ", line 1194, in _call_impl return forward_call(*input, **kwargs) File "E:\Documents\A1111 Web UI Autoinstaller\stable-diffusion-webui\extensions\openpose-editor\scripts\openpose\model .py", line 118, in forward out1 = self.model0(x) File "E:\Documents\A1111 Web UI Autoinstaller\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py ", line 1194, in _call_impl return forward_call(*input, **kwargs) File "E:\Documents\A1111 Web UI Autoinstaller\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\container .py", line 204, in forward input = module(input) File "E:\Documents\A1111 Web UI Autoinstaller\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py ", line 1194, in _call_impl return forward_call(*input, **kwargs) File "E:\Documents\A1111 Web UI Autoinstaller\stable-diffusion-webui\extensions-builtin\Lora\lora.py", line 319, in lo ra_Conv2d_forward return torch.nn.Conv2d_forward_before_lora(self, input) File "E:\Documents\A1111 Web UI Autoinstaller\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\conv.py", line 463, in forward return self._conv_forward(input, self.weight, self.bias) File "E:\Documents\A1111 Web UI Autoinstaller\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\conv.py", line 459, in _conv_forward return F.conv2d(input, weight, bias, self.stride, RuntimeError: Given groups=1, weight of size [64, 3, 3, 3], expected input[1, 4, 184, 248] to have 3 channels, but got 4 channels instead
I think the 4th channel is the alphachannel.
Workaround: I converted my image to JPEG (which does not support alphachannel), then it worked.
I pushed small fix for this issue in https://github.com/fkunn1326/openpose-editor/tree/fkunn1326-patch-3, so please git switch fkunn1326-patch-3 in this extension's directory.
nothing worked for me, I get no error, but my output is nothing or blank
