hnmr293 / stable-diffusion-webui-dumpunet Goto Github PK

Using the command --medvram will result in the following error

Input type (torch.cuda.HalfTensor) and weight type (torch.HalfTensor) should be the same

使用layer prompt的时候显示的两张图一样，其实生成的是两张不同的图，但是都显示了同一张
正确生成了两张图

显示都是同一张，好几次都以为自己用错了，后来翻看存档才知道显示错误


另外想问一下 unet features和attention layers' features 这两个可以用具体讲解用法吗？出来的差异图看不懂啊。

[DumpUnet] U-Net: hooking M00...
0%| | 0/20 [00:00<?, ?it/s][DumpUnet] 1 M00 torch.Size([2, 1280, 12, 8]) torch.Size([2, 1280, 12, 8])
5%|████▏ | 1/20 [00:00<00:18, 1.04it/s][DumpUnet] 2 M00 torch.Size([2, 1280, 12, 8]) torch.Size([2, 1280, 12, 8])
10%|████████▎ | 2/20 [00:01<00:15, 1.14it/s][DumpUnet] 3 M00 torch.Size([2, 1280, 12, 8]) torch.Size([2, 1280, 12, 8])
15%|████████████▍ | 3/20 [00:02<00:14, 1.19it/s][DumpUnet] 4 M00 torch.Size([2, 1280, 12, 8]) torch.Size([2, 1280, 12, 8])
20%|████████████████▌ | 4/20 [00:03<00:13, 1.22it/s][DumpUnet] 5 M00 torch.Size([2, 1280, 12, 8]) torch.Size([2, 1280, 12, 8])
25%|████████████████████▊ | 5/20 [00:04<00:12, 1.23it/s][DumpUnet] 6 M00 torch.Size([2, 1280, 12, 8]) torch.Size([2, 1280, 12, 8])
30%|████████████████████████▉ | 6/20 [00:04<00:11, 1.23it/s][DumpUnet] 7 M00 torch.Size([2, 1280, 12, 8]) torch.Size([2, 1280, 12, 8])
35%|█████████████████████████████ | 7/20 [00:05<00:10, 1.23it/s][DumpUnet] 8 M00 torch.Size([2, 1280, 12, 8]) torch.Size([2, 1280, 12, 8])
40%|█████████████████████████████████▏ | 8/20 [00:06<00:09, 1.24it/s][DumpUnet] 9 M00 torch.Size([2, 1280, 12, 8]) torch.Size([2, 1280, 12, 8])
45%|█████████████████████████████████████▎ | 9/20 [00:07<00:08, 1.25it/s][DumpUnet] 10 M00 torch.Size([2, 1280, 12, 8]) torch.Size([2, 1280, 12, 8])
50%|█████████████████████████████████████████ | 10/20 [00:08<00:08, 1.25it/s][DumpUnet] 11 M00 torch.Size([2, 1280, 12, 8]) torch.Size([2, 1280, 12, 8])
55%|█████████████████████████████████████████████ | 11/20 [00:08<00:07, 1.25it/s][DumpUnet] 12 M00 torch.Size([2, 1280, 12, 8]) torch.Size([2, 1280, 12, 8])
60%|█████████████████████████████████████████████████▏ | 12/20 [00:09<00:06, 1.25it/s][DumpUnet] 13 M00 torch.Size([2, 1280, 12, 8]) torch.Size([2, 1280, 12, 8])
65%|█████████████████████████████████████████████████████▎ | 13/20 [00:10<00:05, 1.25it/s][DumpUnet] 14 M00 torch.Size([2, 1280, 12, 8]) torch.Size([2, 1280, 12, 8])
70%|█████████████████████████████████████████████████████████▍ | 14/20 [00:11<00:04, 1.25it/s][DumpUnet] 15 M00 torch.Size([2, 1280, 12, 8]) torch.Size([2, 1280, 12, 8])
75%|█████████████████████████████████████████████████████████████▌ | 15/20 [00:12<00:03, 1.25it/s][DumpUnet] 16 M00 torch.Size([2, 1280, 12, 8]) torch.Size([2, 1280, 12, 8])
80%|█████████████████████████████████████████████████████████████████▌ | 16/20 [00:12<00:03, 1.25it/s][DumpUnet] 17 M00 torch.Size([2, 1280, 12, 8]) torch.Size([2, 1280, 12, 8])
85%|█████████████████████████████████████████████████████████████████████▋ | 17/20 [00:13<00:02, 1.25it/s][DumpUnet] 18 M00 torch.Size([2, 1280, 12, 8]) torch.Size([2, 1280, 12, 8])
90%|█████████████████████████████████████████████████████████████████████████▊ | 18/20 [00:14<00:01, 1.23it/s][DumpUnet] 19 M00 torch.Size([2, 1280, 12, 8]) torch.Size([2, 1280, 12, 8])
95%|█████████████████████████████████████████████████████████████████████████████▉ | 19/20 [00:15<00:00, 1.23it/s][DumpUnet] 20 M00 torch.Size([2, 1280, 12, 8]) torch.Size([2, 1280, 12, 8])
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:16<00:00, 1.23it/s]
*** Error completing request
*** Arguments: ('task(tx0re419mz2a84e)', <gradio.routes.Request object at 0x000001C970B885B0>, 'a cute girl\n', '(low quality, worst quality:1.4)', [], 20, 'Euler a', 1, 1, 7, 768, 512, False, 0.7, 2, 'Latent', 0, 0, 0, 'Use same checkpoint', 'Use same sampler', '', '', [], 5, False, '', 0.8, 2899652489, False, -1, 0, 0, 0, False, False, {'ad_model': 'face_yolov8n.pt', 'ad_model_classes': '', 'ad_prompt': '', 'ad_negative_prompt': '', 'ad_confidence': 0.3, 'ad_mask_k_largest': 1, 'ad_mask_min_ratio': 0, 'ad_mask_max_ratio': 1, 'ad_x_offset': 0, 'ad_y_offset': 0, 'ad_dilate_erode': 32, 'ad_mask_merge_invert': 'None', 'ad_mask_blur': 4, 'ad_denoising_strength': 0.4, 'ad_inpaint_only_masked': True, 'ad_inpaint_only_masked_padding': 32, 'ad_use_inpaint_width_height': False, 'ad_inpaint_width': 512, 'ad_inpaint_height': 512, 'ad_use_steps': False, 'ad_steps': 28, 'ad_use_cfg_scale': False, 'ad_cfg_scale': 7, 'ad_use_checkpoint': False, 'ad_checkpoint': 'Use same checkpoint', 'ad_use_vae': False, 'ad_vae': 'Use same VAE', 'ad_use_sampler': False, 'ad_sampler': 'Euler a', 'ad_use_noise_multiplier': False, 'ad_noise_multiplier': 1, 'ad_use_clip_skip': False, 'ad_clip_skip': 1, 'ad_restore_face': False, 'ad_controlnet_model': 'None', 'ad_controlnet_module': 'None', 'ad_controlnet_weight': 1, 'ad_controlnet_guidance_start': 0, 'ad_controlnet_guidance_end': 1, 'is_api': ()}, {'ad_model': 'None', 'ad_model_classes': '', 'ad_prompt': '', 'ad_negative_prompt': '', 'ad_confidence': 0.3, 'ad_mask_k_largest': 0, 'ad_mask_min_ratio': 0, 'ad_mask_max_ratio': 1, 'ad_x_offset': 0, 'ad_y_offset': 0, 'ad_dilate_erode': 32, 'ad_mask_merge_invert': 'None', 'ad_mask_blur': 4, 'ad_denoising_strength': 0.4, 'ad_inpaint_only_masked': True, 'ad_inpaint_only_masked_padding': 32, 'ad_use_inpaint_width_height': False, 'ad_inpaint_width': 512, 'ad_inpaint_height': 512, 'ad_use_steps': False, 'ad_steps': 28, 'ad_use_cfg_scale': False, 'ad_cfg_scale': 7, 'ad_use_checkpoint': False, 'ad_checkpoint': 'Use same checkpoint', 'ad_use_vae': False, 'ad_vae': 'Use same VAE', 'ad_use_sampler': False, 'ad_sampler': 'Euler a', 'ad_use_noise_multiplier': False, 'ad_noise_multiplier': 1, 'ad_use_clip_skip': False, 'ad_clip_skip': 1, 'ad_restore_face': False, 'ad_controlnet_model': 'None', 'ad_controlnet_module': 'None', 'ad_controlnet_weight': 1, 'ad_controlnet_guidance_start': 0, 'ad_controlnet_guidance_end': 1, 'is_api': ()}, {'ad_model': 'None', 'ad_model_classes': '', 'ad_prompt': '', 'ad_negative_prompt': '', 'ad_confidence': 0.3, 'ad_mask_k_largest': 0, 'ad_mask_min_ratio': 0, 'ad_mask_max_ratio': 1, 'ad_x_offset': 0, 'ad_y_offset': 0, 'ad_dilate_erode': 4, 'ad_mask_merge_invert': 'None', 'ad_mask_blur': 4, 'ad_denoising_strength': 0.4, 'ad_inpaint_only_masked': True, 'ad_inpaint_only_masked_padding': 32, 'ad_use_inpaint_width_height': False, 'ad_inpaint_width': 512, 'ad_inpaint_height': 512, 'ad_use_steps': False, 'ad_steps': 28, 'ad_use_cfg_scale': False, 'ad_cfg_scale': 7, 'ad_use_checkpoint': False, 'ad_checkpoint': 'Use same checkpoint', 'ad_use_vae': False, 'ad_vae': 'Use same VAE', 'ad_use_sampler': False, 'ad_sampler': 'Euler a', 'ad_use_noise_multiplier': False, 'ad_noise_multiplier': 1, 'ad_use_clip_skip': False, 'ad_clip_skip': 1, 'ad_restore_face': False, 'ad_controlnet_model': 'None', 'ad_controlnet_module': 'None', 'ad_controlnet_weight': 1, 'ad_controlnet_guidance_start': 0, 'ad_controlnet_guidance_end': 1, 'is_api': ()}, UiControlNetUnit(enabled=False, module='none', model='None', weight=1, image=None, resize_mode='Crop and Resize', low_vram=False, processor_res=512, threshold_a=64, threshold_b=64, guidance_start=0, guidance_end=1, pixel_perfect=False, control_mode='Balanced', inpaint_crop_input_image=False, hr_option='Both', save_detected_map=True, advanced_weighting=None), UiControlNetUnit(enabled=False, module='none', model='None', weight=1, image=None, resize_mode='Crop and Resize', low_vram=False, processor_res=512, threshold_a=64, threshold_b=64, guidance_start=0, guidance_end=1, pixel_perfect=False, control_mode='Balanced', inpaint_crop_input_image=False, hr_option='Both', save_detected_map=True, advanced_weighting=None), UiControlNetUnit(enabled=False, module='none', model='None', weight=1, image=None, resize_mode='Crop and Resize', low_vram=False, processor_res=512, threshold_a=64, threshold_b=64, guidance_start=0, guidance_end=1, pixel_perfect=False, control_mode='Balanced', inpaint_crop_input_image=False, hr_option='Both', save_detected_map=True, advanced_weighting=None), 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0, '', False, '', False, False, False, False, 'Auto', 0.5, 1, False, False, False, False, 'positive', 'comma', 0, False, False, 'start', '', 1, '', [], 0, '', [], 0, '', [], True, False, False, False, False, False, False, 0, False, None, None, False, None, None, False, None, None, False, 50, True, 'M00', '', 'disable', 'Custom', 'HSL', 'abs(v)', 'abs(v)', 'abs(v)', '(2+v)/3', '1.0', '0.5', 'Auto [0,1]', -1, 1, 1, 0, False, '', False, 'M00', '1-20(+5)', 'sum', ['K'], 'Custom', 'HSL', 'abs(v)', 'abs(v)', 'abs(v)', '(2+v)/3', '1.0', '0.5', 'Auto [0,1]', -1, 1, 1, 0, False, '', False, True, 'M00', '1-20(+5)', 'sum', 'Custom', 'HSL', 'abs(v)', 'abs(v)', 'abs(v)', '(2+v)/3', '1.0', '0.5', 'Auto [0,1]', -1, 1, 1, 0, False, '', True, '', True) {}
Traceback (most recent call last):
File "F:\stable-diffusion-webui\modules\call_queue.py", line 57, in f
res = list(func(*args, **kwargs))
File "F:\stable-diffusion-webui\modules\call_queue.py", line 36, in f
res = func(*args, **kwargs)
File "F:\stable-diffusion-webui\modules\txt2img.py", line 107, in txt2img
processed = modules.scripts.scripts_txt2img.run(p, *p.script_args)
File "F:\stable-diffusion-webui\modules\scripts.py", line 766, in run
processed = script.run(p, *script_args)
File "F:\stable-diffusion-webui\extensions\stable-diffusion-webui-dumpunet\scripts\dumpunet.py", line 114, in run
return self.run_impl(p, *args, **kwargs)
File "F:\stable-diffusion-webui\extensions\stable-diffusion-webui-dumpunet\scripts\dumpunet.py", line 268, in run_impl
ex.add_images(p, builder, features1, favg, color)
File "F:\stable-diffusion-webui\extensions\stable-diffusion-webui-dumpunet\scripts\dumpunetlib\features\extractor.py", line 82, in add_images
super().add_images(*args, **kwargs)
File "F:\stable-diffusion-webui\extensions\stable-diffusion-webui-dumpunet\scripts\dumpunetlib\feature_extractor.py", line 135, in add_images
shared.total_tqdm._tqdm.set_postfix_str(layer.ljust(5)) # type: ignore
AttributeError: 'NoneType' object has no attribute 'set_postfix_str'

both this and Stable-Diffusion-Webui-Civitai-Helper

import modules.scripts as scripts
from scripts.lib import XXX

Civitai-Helper Pre-reading, Dumpunet unable to load.

Error loading script: dumpunet.py Traceback (most recent call last): File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/modules/scripts.py", line 229, in load_scripts script_module = script_loading.load_module(scriptfile.path) File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/modules/script_loading.py", line 11, in load_module module_spec.loader.exec_module(module) File "<frozen importlib._bootstrap_external>", line 848, in exec_module File "<frozen importlib._bootstrap>", line 219, in _call_with_frames_removed File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/extensions/stable-diffusion-webui-dumpunet/scripts/dumpunet.py", line 10, in <module> from scripts.lib.build_ui import UI File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/extensions/stable-diffusion-webui-dumpunet/scripts/lib/build_ui.py", line 9, in <module> from scripts.lib import layerinfo File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/extensions/stable-diffusion-webui-dumpunet/scripts/lib/layerinfo.py", line 5, in <module> Names_IN : tuple[str, ...] = ( TypeError: 'type' object is not subscriptable

I want to save the feature maps, but after checking "Dump feature tensors to files", I get a pair of binary files in .bin format, so if I want to save the feature maps of the web page, I can only save each feature map by right clicking on it, which is too slow. How to automatically save to local like txt2img? Is it possible to allow users to save grid images locally?