When Batch count is set above 1 NansException: A tensor with all NaNs was produced in Unet. This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try setting the "Upcast cross attention layer to float32" option in Settings > Stable Diffusion or using the --no-half commandline argument to fix this. Use --disable-nan-check commandline argument to disable this check. #2887
[X] I have searched the existing issues and checked the recent builds/commits of both this extension and the webui
What happened?
when control net is enabled i cant generate more then one generation at a time if the number is above 1 it attempts to generate 1 image and then comes up with this error NansException: A tensor with all NaNs was produced in Unet. This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try setting the "Upcast cross attention layer to float32" option in Settings > Stable Diffusion or using the --no-half commandline argument to fix this. Use --disable-nan-check commandline argument to disable this check.
Steps to reproduce the problem
Go to control net, enable, select settings then increase batch count and click generate
What should have happened?
stable diffusion should generate the number of images i selected usually 6
Commit where the problem happens
webui:
controlnet:
What browsers do you use to access the UI ?
Mozilla Firefox
Command Line Arguments
none
List of enabled extensions
Console logs
venv "F:\sd.webui\webui\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: v1.9.3
Commit hash: 1c0a0c4c26f78c32095ebc7f8af82f5c04fca8c0
Collecting protobuf<=3.9999,>=3.20
Using cached protobuf-3.20.3-cp310-cp310-win_amd64.whl.metadata (698 bytes)
Using cached protobuf-3.20.3-cp310-cp310-win_amd64.whl (904 kB)
Installing collected packages: protobuf
Attempting uninstall: protobuf
Found existing installation: protobuf 4.25.3
Uninstalling protobuf-4.25.3:
Successfully uninstalled protobuf-4.25.3
Successfully installed protobuf-3.20.3
Launching Web UI with arguments:
no module 'xformers'. Processing without...
no module 'xformers'. Processing without...
No module 'xformers'. Proceeding without it.
[-] ADetailer initialized. version: 24.4.2, num models: 10
*** Error loading script: main.py
Traceback (most recent call last):
File "F:\sd.webui\webui\modules\scripts.py", line 508, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
File "F:\sd.webui\webui\modules\script_loading.py", line 13, in load_module
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 883, in exec_module
File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed
File "F:\sd.webui\webui\extensions\openpose-editor\scripts\main.py", line 14, in <module>
from basicsr.utils.download_util import load_file_from_url
ModuleNotFoundError: No module named 'basicsr'
---
CivitAI Browser+: Aria2 RPC started
ControlNet preprocessor location: F:\sd.webui\webui\extensions\sd-webui-controlnet\annotator\downloads
2024-05-13 16:08:24,978 - ControlNet - INFO - ControlNet v1.1.448
Loading weights [fb79f124fb] from F:\sd.webui\webui\models\Stable-diffusion\galenaMixLegacy_reduxV30.safetensors
Creating model from config: F:\sd.webui\webui\configs\v1-inference.yaml
2024-05-13 16:08:25,500 - ControlNet - INFO - ControlNet UI callback registered.
F:\sd.webui\webui\venv\lib\site-packages\huggingface_hub\file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
warnings.warn(
Running on local URL: http://127.0.0.1:7860
To create a public link, set `share=True` in `launch()`.
Startup time: 27.1s (prepare environment: 4.3s, import torch: 3.4s, import gradio: 0.6s, setup paths: 0.8s, initialize shared: 0.2s, other imports: 0.4s, load scripts: 16.3s, create ui: 0.6s, gradio launch: 0.4s).
Applying attention optimization: Doggettx... done.
Model loaded in 3.4s (load weights from disk: 0.1s, create model: 0.8s, apply weights to model: 2.2s, calculate empty prompt: 0.1s).
Loading VAE weights specified in settings: F:\sd.webui\webui\models\VAE\vae-ft-mse-840000-ema-pruned.ckpt
Applying attention optimization: Doggettx... done.
VAE weights loaded.
100%|██████████████████████████████████████████████████████████████████████████████████| 40/40 [00:03<00:00, 10.53it/s]
tiled upscale: 100%|███████████████████████████████████████████████████████████████████| 15/15 [00:00<00:00, 31.89it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 15/15 [00:08<00:00, 1.67it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 55/55 [00:16<00:00, 1.72it/s]
0: 640x448 1 face, 64.8ms
Speed: 2.2ms preprocess, 64.8ms inference, 22.2ms postprocess per image at shape (1, 3, 640, 448)
100%|██████████████████████████████████████████████████████████████████████████████████| 17/17 [00:02<00:00, 7.67it/s]
Restoring base VAE
Applying attention optimization: Doggettx... done.
VAE weights loaded.
Total progress: 100%|██████████████████████████████████████████████████████████████████| 55/55 [00:21<00:00, 2.52it/s]
Loading VAE weights specified in settings: F:\sd.webui\webui\models\VAE\vae-ft-mse-840000-ema-pruned.ckpt00, 1.72it/s]
Applying attention optimization: Doggettx... done.
VAE weights loaded.
2024-05-13 16:11:01,735 - ControlNet - INFO - unit_separate = False, style_align = False
2024-05-13 16:11:01,928 - ControlNet - INFO - Loading model: control_v11f1p_sd15_depth [cfd03158]
2024-05-13 16:11:02,479 - ControlNet - INFO - Loaded state_dict from [F:\sd.webui\webui\extensions\sd-webui-controlnet\models\control_v11f1p_sd15_depth.pth]
2024-05-13 16:11:02,479 - ControlNet - INFO - controlnet_default_config
2024-05-13 16:11:03,782 - ControlNet - INFO - ControlNet model control_v11f1p_sd15_depth [cfd03158](ControlModelType.ControlNet) loaded.
2024-05-13 16:11:03,787 - ControlNet - INFO - Using preprocessor: none
2024-05-13 16:11:03,788 - ControlNet - INFO - preprocessor resolution = 512
2024-05-13 16:11:03,867 - ControlNet - INFO - ControlNet Hooked - Time = 2.1345717906951904
100%|██████████████████████████████████████████████████████████████████████████████████| 40/40 [00:04<00:00, 9.01it/s]
tiled upscale: 100%|███████████████████████████████████████████████████████████████████| 15/15 [00:00<00:00, 37.60it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 15/15 [00:12<00:00, 1.20it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 55/55 [00:18<00:00, 1.23it/s]
0: 640x448 1 face, 62.2ms
Speed: 1.5ms preprocess, 62.2ms inference, 1.1ms postprocess per image at shape (1, 3, 640, 448)
100%|██████████████████████████████████████████████████████████████████████████████████| 17/17 [00:02<00:00, 7.71it/s]
Restoring base VAE
Applying attention optimization: Doggettx... done.
VAE weights loaded.
Total progress: 100%|██████████████████████████████████████████████████████████████████| 55/55 [00:23<00:00, 2.31it/s]
Loading VAE weights specified in settings: F:\sd.webui\webui\models\VAE\vae-ft-mse-840000-ema-pruned.ckpt00, 1.23it/s]
Applying attention optimization: Doggettx... done.
VAE weights loaded.
INFO:sd_dynamic_prompts.dynamic_prompting:Prompt matrix will create 2 images in a total of 2 batches.
2024-05-13 16:11:41,363 - ControlNet - INFO - unit_separate = False, style_align = False
2024-05-13 16:11:41,363 - ControlNet - INFO - Loading model from cache: control_v11f1p_sd15_depth [cfd03158]
2024-05-13 16:11:41,368 - ControlNet - INFO - Using preprocessor: none
2024-05-13 16:11:41,368 - ControlNet - INFO - preprocessor resolution = 512
2024-05-13 16:11:41,401 - ControlNet - INFO - ControlNet Hooked - Time = 0.03971266746520996
100%|██████████████████████████████████████████████████████████████████████████████████| 40/40 [00:04<00:00, 9.17it/s]
tiled upscale: 100%|███████████████████████████████████████████████████████████████████| 15/15 [00:00<00:00, 41.53it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 15/15 [00:12<00:00, 1.20it/s]
Total progress: 50%|████████████████████████████████▌ | 55/110 [00:18<00:44, 1.23it/s]
0: 640x448 1 face, 66.4ms
Speed: 1.5ms preprocess, 66.4ms inference, 1.1ms postprocess per image at shape (1, 3, 640, 448)
100%|██████████████████████████████████████████████████████████████████████████████████| 17/17 [00:02<00:00, 7.75it/s]
INFO:sd_dynamic_prompts.dynamic_prompting:Prompt matrix will create 2 images in a total of 2 batches.
0%| | 0/40 [00:00<?, ?it/s]
Restoring base VAE
Applying attention optimization: Doggettx... done.
VAE weights loaded.
*** Error completing request
*** Arguments: ('task(56bqjpl3s3l7gl3)', <gradio.routes.Request object at 0x0000022B1E3B3C40>, '(masterpiece, best quality, perfect hourglass figure, wide waist,(masterpiece, best quality,), busty, portrait, perfect face, flawless eyes, beautiful lips, full lips, sultry look, head tilt, seductive grin, <lora:add_detail:-0.2>, perfect waist, cowboy shot, perfect hips, <lora:sanpaku-eyes-v2:0.8> , sanpaku, round pupils, wide smile, huge breasts, saggy breasts, <lora:Sagging Breasts v1:1.2> (sagging breasts:1.2), ((ombre orange hair)), two-tone hair, multicolored hair, <lora:Ombre Hair:0.7>, wild hair, long hair, <lora:concave:0.8> , concave bangs, (collarbone), solo, (open shirt), puffy nipples, white nurse oufit, nurse cap, looking at viewer, (blush:1.2), smiling, nsfw, on back, pussy, solo, on bed, legs up, arms up', '(worst quality:1.6, low quality:1.6), fat, ugly, lowres, blurry, FastNegativeV2, easynegative, cat ears, wrinkles, (earrings), (hands), watermark, signature, moles, nonsensical hair, (((coat))), holding,', [], 2, 1, 8, 768, 512, True, 0.4, 2, 'R-ESRGAN 4x+ Anime6B', 15, 0, 0, 'Use same checkpoint', 'Use same sampler', 'Use same scheduler', '', '', ['Clip skip: 2', 'VAE: vae-ft-mse-840000-ema-pruned.ckpt'], 0, 40, 'Euler a', 'Automatic', False, '', 0.8, 964617240, False, -1, 0, 0, 0, 'Automatic', 1, True, False, {'ad_model': 'face_yolov8n.pt', 'ad_model_classes': '', 'ad_prompt': '(masterpiece, best quality), blush, perfect face, flawless eyes, pink eyes, beautiful lips, full lips, <lora:add_detail:-0.2>, <lora:sanpaku-eyes-v2:0.8> , sanpaku, round pupils, wide smile,<lora:concave:0.8> , concave bangs, sultry look, head tilt, seductive grin', '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': 'DPM++ 2M', 'ad_scheduler': 'Use same scheduler', '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': 'DPM++ 2M', 'ad_scheduler': 'Use same scheduler', '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': ()}, True, False, 1, False, False, False, 1.1, 1.5, 100, 0.7, False, False, True, False, False, 0, 'Gustavosta/MagicPrompt-Stable-Diffusion', '', False, 7, 100, 'Constant', 0, 'Constant', 0, 4, True, 'MEAN', 'AD', 1, ControlNetUnit(is_ui=True, input_mode=<InputMode.SIMPLE: 'simple'>, batch_images='', output_dir='', loopback=False, enabled=False, module='none', model='control_v11f1p_sd15_depth [cfd03158]', weight=1.0, image={'image': array([[[ 29, 29, 29],
*** [ 28, 28, 28],
*** [ 28, 28, 28],
*** ...,
*** [ 19, 19, 19],
*** [ 18, 18, 18],
*** [ 12, 12, 12]],
***
*** [[ 27, 27, 27],
*** [ 28, 28, 28],
*** [ 28, 28, 28],
*** ...,
*** [ 19, 19, 19],
*** [ 18, 18, 18],
*** [ 18, 18, 18]],
***
*** [[ 28, 28, 28],
*** [ 28, 28, 28],
*** [ 27, 27, 27],
*** ...,
*** [ 19, 19, 19],
*** [ 18, 18, 18],
*** [ 19, 19, 19]],
***
*** ...,
***
*** [[161, 161, 161],
*** [162, 162, 162],
*** [161, 161, 161],
*** ...,
*** [ 77, 77, 77],
*** [ 77, 77, 77],
*** [ 77, 77, 77]],
***
*** [[162, 162, 162],
*** [162, 162, 162],
*** [162, 162, 162],
*** ...,
*** [ 78, 78, 78],
*** [ 78, 78, 78],
*** [ 79, 79, 79]],
***
*** [[161, 161, 161],
*** [162, 162, 162],
*** [162, 162, 162],
*** ...,
*** [ 80, 80, 80],
*** [ 80, 80, 80],
*** [ 80, 80, 80]]], dtype=uint8), 'mask': array([[[0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0],
*** ...,
*** [0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0]],
***
*** [[0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0],
*** ...,
*** [0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0]],
***
*** [[0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0],
*** ...,
*** [0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0]],
***
*** ...,
***
*** [[0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0],
*** ...,
*** [0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0]],
***
*** [[0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0],
*** ...,
*** [0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0]],
***
*** [[0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0],
*** ...,
*** [0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0]]], dtype=uint8)}, resize_mode=<ResizeMode.INNER_FIT: 'Crop and Resize'>, low_vram=False, processor_res=512, threshold_a=0.5, threshold_b=0.5, guidance_start=0.0, guidance_end=1.0, pixel_perfect=True, control_mode=<ControlMode.BALANCED: 'Balanced'>, inpaint_crop_input_image=False, hr_option=<HiResFixOption.BOTH: 'Both'>, save_detected_map=True, advanced_weighting=None, effective_region_mask=None, pulid_mode=<PuLIDMode.FIDELITY: 'Fidelity'>, ipadapter_input=None, mask=None, batch_mask_dir=None, animatediff_batch=False, batch_modifiers=[], batch_image_files=[]), ControlNetUnit(is_ui=True, input_mode=<InputMode.SIMPLE: 'simple'>, batch_images='', output_dir='', loopback=False, enabled=False, module='none', model='None', weight=1.0, image=None, resize_mode=<ResizeMode.INNER_FIT: 'Crop and Resize'>, low_vram=False, processor_res=-1, threshold_a=-1.0, threshold_b=-1.0, guidance_start=0.0, guidance_end=1.0, pixel_perfect=False, control_mode=<ControlMode.BALANCED: 'Balanced'>, inpaint_crop_input_image=False, hr_option=<HiResFixOption.BOTH: 'Both'>, save_detected_map=True, advanced_weighting=None, effective_region_mask=None, pulid_mode=<PuLIDMode.FIDELITY: 'Fidelity'>, ipadapter_input=None, mask=None, batch_mask_dir=None, animatediff_batch=False, batch_modifiers=[], batch_image_files=[]), ControlNetUnit(is_ui=True, input_mode=<InputMode.SIMPLE: 'simple'>, batch_images='', output_dir='', loopback=False, enabled=False, module='none', model='None', weight=1.0, image=None, resize_mode=<ResizeMode.INNER_FIT: 'Crop and Resize'>, low_vram=False, processor_res=-1, threshold_a=-1.0, threshold_b=-1.0, guidance_start=0.0, guidance_end=1.0, pixel_perfect=False, control_mode=<ControlMode.BALANCED: 'Balanced'>, inpaint_crop_input_image=False, hr_option=<HiResFixOption.BOTH: 'Both'>, save_detected_map=True, advanced_weighting=None, effective_region_mask=None, pulid_mode=<PuLIDMode.FIDELITY: 'Fidelity'>, ipadapter_input=None, mask=None, batch_mask_dir=None, animatediff_batch=False, batch_modifiers=[], batch_image_files=[]), False, False, 'Matrix', 'Columns', 'Mask', 'Prompt', '1,1', '0.2', False, False, False, 'Attention', [False], '0', '0', '0.4', None, '0', '0', 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, [], 30, '', 4, [], 1, '', '', '', '') {}
Traceback (most recent call last):
File "F:\sd.webui\webui\modules\call_queue.py", line 57, in f
res = list(func(*args, **kwargs))
File "F:\sd.webui\webui\modules\call_queue.py", line 36, in f
res = func(*args, **kwargs)
File "F:\sd.webui\webui\modules\txt2img.py", line 109, in txt2img
processed = processing.process_images(p)
File "F:\sd.webui\webui\extensions\sd-webui-prompt-history\lib_history\image_process_hijacker.py", line 21, in process_images
res = original_function(p)
File "F:\sd.webui\webui\modules\processing.py", line 845, in process_images
res = process_images_inner(p)
File "F:\sd.webui\webui\extensions\sd-webui-controlnet\scripts\batch_hijack.py", line 59, in processing_process_images_hijack
return getattr(processing, '__controlnet_original_process_images_inner')(p, *args, **kwargs)
File "F:\sd.webui\webui\modules\processing.py", line 981, in process_images_inner
samples_ddim = p.sample(conditioning=p.c, unconditional_conditioning=p.uc, seeds=p.seeds, subseeds=p.subseeds, subseed_strength=p.subseed_strength, prompts=p.prompts)
File "F:\sd.webui\webui\extensions\sd-webui-controlnet\scripts\hook.py", line 463, in process_sample
return process.sample_before_CN_hack(*args, **kwargs)
File "F:\sd.webui\webui\modules\processing.py", line 1328, in sample
samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
File "F:\sd.webui\webui\modules\sd_samplers_kdiffusion.py", line 218, in sample
samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
File "F:\sd.webui\webui\modules\sd_samplers_common.py", line 272, in launch_sampling
return func()
File "F:\sd.webui\webui\modules\sd_samplers_kdiffusion.py", line 218, in <lambda>
samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
File "F:\sd.webui\webui\venv\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "F:\sd.webui\webui\repositories\k-diffusion\k_diffusion\sampling.py", line 145, in sample_euler_ancestral
denoised = model(x, sigmas[i] * s_in, **extra_args)
File "F:\sd.webui\webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "F:\sd.webui\webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "F:\sd.webui\webui\modules\sd_samplers_cfg_denoiser.py", line 269, in forward
devices.test_for_nans(x_out, "unet")
File "F:\sd.webui\webui\modules\devices.py", line 255, in test_for_nans
raise NansException(message)
modules.devices.NansException: A tensor with all NaNs was produced in Unet. This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try setting the "Upcast cross attention layer to float32" option in Settings > Stable Diffusion or using the --no-half commandline argument to fix this. Use --disable-nan-check commandline argument to disable this check.
---
Loading VAE weights specified in settings: F:\sd.webui\webui\models\VAE\vae-ft-mse-840000-ema-pruned.ckpt
Applying attention optimization: Doggettx... done.
VAE weights loaded.
INFO:sd_dynamic_prompts.dynamic_prompting:Prompt matrix will create 6 images in a total of 1 batches.
2024-05-13 16:12:22,613 - ControlNet - INFO - unit_separate = False, style_align = False
2024-05-13 16:12:22,613 - ControlNet - INFO - Loading model from cache: control_v11f1p_sd15_depth [cfd03158]
2024-05-13 16:12:22,618 - ControlNet - INFO - Using preprocessor: none
2024-05-13 16:12:22,618 - ControlNet - INFO - preprocessor resolution = 512
2024-05-13 16:12:22,655 - ControlNet - INFO - ControlNet Hooked - Time = 0.04339790344238281
100%|██████████████████████████████████████████████████████████████████████████████████| 40/40 [00:19<00:00, 2.04it/s]
tiled upscale: 100%|███████████████████████████████████████████████████████████████████| 15/15 [00:00<00:00, 43.76it/s]
tiled upscale: 100%|███████████████████████████████████████████████████████████████████| 15/15 [00:00<00:00, 45.33it/s]
tiled upscale: 100%|███████████████████████████████████████████████████████████████████| 15/15 [00:00<00:00, 43.28it/s]
tiled upscale: 100%|███████████████████████████████████████████████████████████████████| 15/15 [00:00<00:00, 42.52it/s]
tiled upscale: 100%|███████████████████████████████████████████████████████████████████| 15/15 [00:00<00:00, 46.20it/s]
tiled upscale: 100%|███████████████████████████████████████████████████████████████████| 15/15 [00:00<00:00, 41.99it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 15/15 [01:14<00:00, 4.97s/it]
Total progress: 110it [02:21, 4.95s/it]
0: 640x448 1 face, 67.6ms
Speed: 1.5ms preprocess, 67.6ms inference, 1.0ms postprocess per image at shape (1, 3, 640, 448)
100%|██████████████████████████████████████████████████████████████████████████████████| 17/17 [00:02<00:00, 8.02it/s]
0: 640x448 1 face, 7.1ms
Speed: 1.0ms preprocess, 7.1ms inference, 1.1ms postprocess per image at shape (1, 3, 640, 448)
100%|██████████████████████████████████████████████████████████████████████████████████| 17/17 [00:01<00:00, 9.38it/s]
0: 640x448 1 face, 4.4ms
Speed: 1.0ms preprocess, 4.4ms inference, 1.1ms postprocess per image at shape (1, 3, 640, 448)
100%|██████████████████████████████████████████████████████████████████████████████████| 17/17 [00:01<00:00, 9.07it/s]
0: 640x448 1 face, 4.5ms
Speed: 1.6ms preprocess, 4.5ms inference, 0.6ms postprocess per image at shape (1, 3, 640, 448)
100%|██████████████████████████████████████████████████████████████████████████████████| 17/17 [00:01<00:00, 9.32it/s]
0: 640x448 1 face, 6.3ms
Speed: 1.6ms preprocess, 6.3ms inference, 1.0ms postprocess per image at shape (1, 3, 640, 448)
100%|██████████████████████████████████████████████████████████████████████████████████| 17/17 [00:01<00:00, 9.69it/s]
0: 640x448 1 face, 5.0ms
Speed: 1.1ms preprocess, 5.0ms inference, 0.5ms postprocess per image at shape (1, 3, 640, 448)
100%|██████████████████████████████████████████████████████████████████████████████████| 17/17 [00:01<00:00, 9.20it/s]
INFO:sd_dynamic_prompts.dynamic_prompting:Prompt matrix will create 6 images in a total of 1 batches.
Restoring base VAE
Applying attention optimization: Doggettx... done.
VAE weights loaded.
Total progress: 110it [02:42, 1.48s/it]
X/Y/Z plot will create 0 images on 0 0x0 grid; 6 images per cell. (Total steps to process: 0)
Unexpected error: Processing could not begin, you may need to refresh the tab or restart the service. 0it [00:00, ?it/s]
Total progress: 0it [00:00, ?it/s]
X/Y/Z plot will create 6 images on 1 1x1 grid; 6 images per cell. (Total steps to process: 55)
Loading VAE weights specified in settings: F:\sd.webui\webui\models\VAE\vae-ft-mse-840000-ema-pruned.ckpt [00:00, ?it/s]
Applying attention optimization: Doggettx... done.
VAE weights loaded.
INFO:sd_dynamic_prompts.dynamic_prompting:Prompt matrix will create 6 images in a total of 1 batches.
2024-05-13 16:15:09,578 - ControlNet - INFO - unit_separate = False, style_align = False
2024-05-13 16:15:09,578 - ControlNet - INFO - Loading model from cache: control_v11f1p_sd15_depth [cfd03158]
2024-05-13 16:15:09,583 - ControlNet - INFO - Using preprocessor: none
2024-05-13 16:15:09,583 - ControlNet - INFO - preprocessor resolution = 512
2024-05-13 16:15:09,634 - ControlNet - INFO - ControlNet Hooked - Time = 0.05808281898498535
82%|███████████████████████████████████████████████████████████████████▋ | 33/40 [00:16<00:03, 1.99it/s]
INFO:sd_dynamic_prompts.dynamic_prompting:Prompt matrix will create 6 images in a total of 1 batches.<00:10, 2.06it/s]
2024-05-13 16:15:28,398 - ControlNet - INFO - unit_separate = False, style_align = False
2024-05-13 16:15:28,398 - ControlNet - INFO - Loading model from cache: control_v11f1p_sd15_depth [cfd03158]
2024-05-13 16:15:28,402 - ControlNet - INFO - Using preprocessor: none
2024-05-13 16:15:28,402 - ControlNet - INFO - preprocessor resolution = 512
2024-05-13 16:15:28,445 - ControlNet - INFO - ControlNet Hooked - Time = 0.04992389678955078
Restoring base VAE
Applying attention optimization: Doggettx... done.
VAE weights loaded.
Total progress: 60%|███████████████████████████████████████▌ | 33/55 [00:22<00:14, 1.50it/s]
X/Y/Z plot will create 1 images on 1 1x1 grid. (Total steps to process: 55) | 33/55 [00:22<00:10, 2.06it/s]
Loading VAE weights specified in settings: F:\sd.webui\webui\models\VAE\vae-ft-mse-840000-ema-pruned.ckpt [00:00, ?it/s]
Applying attention optimization: Doggettx... done.
VAE weights loaded.
2024-05-13 16:15:39,050 - ControlNet - INFO - unit_separate = False, style_align = False
2024-05-13 16:15:39,050 - ControlNet - INFO - Loading model from cache: control_v11f1p_sd15_depth [cfd03158]
2024-05-13 16:15:39,055 - ControlNet - INFO - Using preprocessor: none
2024-05-13 16:15:39,055 - ControlNet - INFO - preprocessor resolution = 512
2024-05-13 16:15:39,096 - ControlNet - INFO - ControlNet Hooked - Time = 0.047617435455322266
100%|██████████████████████████████████████████████████████████████████████████████████| 40/40 [00:03<00:00, 10.13it/s]
tiled upscale: 100%|███████████████████████████████████████████████████████████████████| 15/15 [00:00<00:00, 37.49it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 15/15 [00:12<00:00, 1.20it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 55/55 [00:19<00:00, 1.23it/s]
0: 640x448 1 face, 69.1ms
Speed: 1.0ms preprocess, 69.1ms inference, 0.0ms postprocess per image at shape (1, 3, 640, 448)
100%|██████████████████████████████████████████████████████████████████████████████████| 17/17 [00:02<00:00, 7.90it/s]
Restoring base VAE
Applying attention optimization: Doggettx... done.
VAE weights loaded.
Total progress: 100%|██████████████████████████████████████████████████████████████████| 55/55 [00:24<00:00, 2.25it/s]
X/Y/Z plot will create 1 images on 1 1x1 grid. (Total steps to process: 55)████████████| 55/55 [00:24<00:00, 1.23it/s]
Loading VAE weights specified in settings: F:\sd.webui\webui\models\VAE\vae-ft-mse-840000-ema-pruned.ckpt [00:00, ?it/s]
Applying attention optimization: Doggettx... done.
VAE weights loaded.
2024-05-13 16:16:22,046 - ControlNet - INFO - unit_separate = False, style_align = False
2024-05-13 16:16:22,047 - ControlNet - INFO - Loading model from cache: control_v11f1p_sd15_depth [cfd03158]
2024-05-13 16:16:22,051 - ControlNet - INFO - Using preprocessor: none
2024-05-13 16:16:22,051 - ControlNet - INFO - preprocessor resolution = 512
2024-05-13 16:16:22,094 - ControlNet - INFO - ControlNet Hooked - Time = 0.049373626708984375
100%|██████████████████████████████████████████████████████████████████████████████████| 40/40 [00:04<00:00, 8.95it/s]
tiled upscale: 100%|███████████████████████████████████████████████████████████████████| 15/15 [00:00<00:00, 34.04it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 15/15 [00:12<00:00, 1.19it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 55/55 [00:20<00:00, 1.22it/s]
0: 640x448 1 face, 63.6ms
Speed: 1.1ms preprocess, 63.6ms inference, 1.2ms postprocess per image at shape (1, 3, 640, 448)
100%|██████████████████████████████████████████████████████████████████████████████████| 17/17 [00:02<00:00, 7.25it/s]
Restoring base VAE
Applying attention optimization: Doggettx... done.
VAE weights loaded.
Total progress: 100%|██████████████████████████████████████████████████████████████████| 55/55 [00:25<00:00, 2.14it/s]
X/Y/Z plot will create 3 images on 1 1x1 grid; 3 images per cell. (Total steps to process: 55) [00:25<00:00, 1.22it/s]
Loading VAE weights specified in settings: F:\sd.webui\webui\models\VAE\vae-ft-mse-840000-ema-pruned.ckpt [00:00, ?it/s]
Applying attention optimization: Doggettx... done.
VAE weights loaded.
INFO:sd_dynamic_prompts.dynamic_prompting:Prompt matrix will create 3 images in a total of 1 batches.
2024-05-13 16:17:56,374 - ControlNet - INFO - unit_separate = False, style_align = False
2024-05-13 16:17:56,374 - ControlNet - INFO - Loading model from cache: control_v11f1p_sd15_depth [cfd03158]
2024-05-13 16:17:56,379 - ControlNet - INFO - Using preprocessor: none
2024-05-13 16:17:56,379 - ControlNet - INFO - preprocessor resolution = 512
2024-05-13 16:17:56,422 - ControlNet - INFO - ControlNet Hooked - Time = 0.04943537712097168
100%|██████████████████████████████████████████████████████████████████████████████████| 40/40 [00:10<00:00, 3.82it/s]
tiled upscale: 100%|███████████████████████████████████████████████████████████████████| 15/15 [00:00<00:00, 41.85it/s]
tiled upscale: 100%|███████████████████████████████████████████████████████████████████| 15/15 [00:00<00:00, 45.72it/s]
tiled upscale: 100%|███████████████████████████████████████████████████████████████████| 15/15 [00:00<00:00, 46.37it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 15/15 [00:37<00:00, 2.47s/it]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 55/55 [00:52<00:00, 2.45s/it]
0: 640x448 1 face, 67.0ms
Speed: 1.5ms preprocess, 67.0ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 448)
100%|██████████████████████████████████████████████████████████████████████████████████| 17/17 [00:02<00:00, 7.72it/s]
0: 640x448 1 face, 5.7ms
Speed: 0.6ms preprocess, 5.7ms inference, 1.0ms postprocess per image at shape (1, 3, 640, 448)
100%|██████████████████████████████████████████████████████████████████████████████████| 17/17 [00:01<00:00, 9.54it/s]
0: 640x448 1 face, 5.7ms
Speed: 1.2ms preprocess, 5.7ms inference, 1.1ms postprocess per image at shape (1, 3, 640, 448)
100%|██████████████████████████████████████████████████████████████████████████████████| 17/17 [00:01<00:00, 9.50it/s]
INFO:sd_dynamic_prompts.dynamic_prompting:Prompt matrix will create 3 images in a total of 1 batches.
Restoring base VAE
Applying attention optimization: Doggettx... done.
VAE weights loaded.
Total progress: 100%|██████████████████████████████████████████████████████████████████| 55/55 [01:04<00:00, 1.18s/it]
Loading VAE weights specified in settings: F:\sd.webui\webui\models\VAE\vae-ft-mse-840000-ema-pruned.ckpt00, 2.45s/it]
Applying attention optimization: Doggettx... done.
VAE weights loaded.
INFO:sd_dynamic_prompts.dynamic_prompting:Prompt matrix will create 6 images in a total of 6 batches.
2024-05-13 16:20:25,910 - ControlNet - INFO - unit_separate = False, style_align = False
2024-05-13 16:20:25,910 - ControlNet - INFO - Loading model from cache: control_v11f1p_sd15_depth [cfd03158]
2024-05-13 16:20:25,915 - ControlNet - INFO - Using preprocessor: none
2024-05-13 16:20:25,915 - ControlNet - INFO - preprocessor resolution = 512
2024-05-13 16:20:25,954 - ControlNet - INFO - ControlNet Hooked - Time = 0.045037269592285156
100%|██████████████████████████████████████████████████████████████████████████████████| 40/40 [00:04<00:00, 9.09it/s]
tiled upscale: 100%|███████████████████████████████████████████████████████████████████| 15/15 [00:00<00:00, 40.11it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 15/15 [00:12<00:00, 1.20it/s]
Total progress: 17%|██████████▊ | 55/330 [00:19<03:44, 1.23it/s]
0: 640x448 1 face, 64.9ms
Speed: 1.0ms preprocess, 64.9ms inference, 0.5ms postprocess per image at shape (1, 3, 640, 448)
100%|██████████████████████████████████████████████████████████████████████████████████| 17/17 [00:02<00:00, 8.01it/s]
INFO:sd_dynamic_prompts.dynamic_prompting:Prompt matrix will create 6 images in a total of 6 batches.
0%| | 0/40 [00:00<?, ?it/s]
Restoring base VAE
Applying attention optimization: Doggettx... done.
VAE weights loaded.
*** Error completing request
*** Arguments: ('task(q0iku3mnk7zrz80)', <gradio.routes.Request object at 0x0000022BB7F36860>, '(masterpiece, best quality, perfect hourglass figure, wide waist,(masterpiece, best quality,), busty, portrait, perfect face, flawless eyes, beautiful lips, full lips, sultry look, head tilt, seductive grin, <lora:add_detail:-0.2>, perfect waist, cowboy shot, perfect hips, <lora:sanpaku-eyes-v2:0.8> , sanpaku, round pupils, wide smile, huge breasts, saggy breasts, <lora:Sagging Breasts v1:1.2> (sagging breasts:1.2), ((ombre orange hair)), two-tone hair, multicolored hair, <lora:Ombre Hair:0.7>, wild hair, long hair, <lora:concave:0.8> , concave bangs, (collarbone), solo, (open shirt), puffy nipples, (white nurse oufit:1.4), nurse cap, looking at viewer, (blush:1.2), smiling, nsfw, on back, pussy, solo, on bed, legs up, arms up', '(worst quality:1.6, low quality:1.6), fat, ugly, lowres, blurry, FastNegativeV2, easynegative, cat ears, wrinkles, (earrings), (hands), watermark, signature, moles, nonsensical hair, (((coat))), holding,', [], 6, 1, 8, 768, 512, True, 0.4, 2, 'R-ESRGAN 4x+ Anime6B', 15, 0, 0, 'Use same checkpoint', 'Use same sampler', 'Use same scheduler', '', '', ['Clip skip: 2', 'VAE: vae-ft-mse-840000-ema-pruned.ckpt'], 0, 40, 'Euler a', 'Automatic', False, '', 0.8, 964617240, False, -1, 0, 0, 0, 'Automatic', 1, True, False, {'ad_model': 'face_yolov8n.pt', 'ad_model_classes': '', 'ad_prompt': '(masterpiece, best quality), blush, perfect face, flawless eyes, pink eyes, beautiful lips, full lips, <lora:add_detail:-0.2>, <lora:sanpaku-eyes-v2:0.8> , sanpaku, round pupils, wide smile,<lora:concave:0.8> , concave bangs, sultry look, head tilt, seductive grin', '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': 'DPM++ 2M', 'ad_scheduler': 'Use same scheduler', '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': 'DPM++ 2M', 'ad_scheduler': 'Use same scheduler', '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': ()}, True, False, 1, False, False, False, 1.1, 1.5, 100, 0.7, False, False, True, False, False, 0, 'Gustavosta/MagicPrompt-Stable-Diffusion', '', False, 7, 100, 'Constant', 0, 'Constant', 0, 4, True, 'MEAN', 'AD', 1, ControlNetUnit(is_ui=True, input_mode=<InputMode.SIMPLE: 'simple'>, batch_images='', output_dir='', loopback=False, enabled=False, module='none', model='control_v11f1p_sd15_depth [cfd03158]', weight=1.0, image={'image': array([[[ 29, 29, 29],
*** [ 28, 28, 28],
*** [ 28, 28, 28],
*** ...,
*** [ 19, 19, 19],
*** [ 18, 18, 18],
*** [ 12, 12, 12]],
***
*** [[ 27, 27, 27],
*** [ 28, 28, 28],
*** [ 28, 28, 28],
*** ...,
*** [ 19, 19, 19],
*** [ 18, 18, 18],
*** [ 18, 18, 18]],
***
*** [[ 28, 28, 28],
*** [ 28, 28, 28],
*** [ 27, 27, 27],
*** ...,
*** [ 19, 19, 19],
*** [ 18, 18, 18],
*** [ 19, 19, 19]],
***
*** ...,
***
*** [[161, 161, 161],
*** [162, 162, 162],
*** [161, 161, 161],
*** ...,
*** [ 77, 77, 77],
*** [ 77, 77, 77],
*** [ 77, 77, 77]],
***
*** [[162, 162, 162],
*** [162, 162, 162],
*** [162, 162, 162],
*** ...,
*** [ 78, 78, 78],
*** [ 78, 78, 78],
*** [ 79, 79, 79]],
***
*** [[161, 161, 161],
*** [162, 162, 162],
*** [162, 162, 162],
*** ...,
*** [ 80, 80, 80],
*** [ 80, 80, 80],
*** [ 80, 80, 80]]], dtype=uint8), 'mask': array([[[0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0],
*** ...,
*** [0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0]],
***
*** [[0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0],
*** ...,
*** [0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0]],
***
*** [[0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0],
*** ...,
*** [0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0]],
***
*** ...,
***
*** [[0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0],
*** ...,
*** [0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0]],
***
*** [[0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0],
*** ...,
*** [0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0]],
***
*** [[0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0],
*** ...,
*** [0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0]]], dtype=uint8)}, resize_mode=<ResizeMode.INNER_FIT: 'Crop and Resize'>, low_vram=False, processor_res=512, threshold_a=0.5, threshold_b=0.5, guidance_start=0.0, guidance_end=1.0, pixel_perfect=True, control_mode=<ControlMode.BALANCED: 'Balanced'>, inpaint_crop_input_image=False, hr_option=<HiResFixOption.BOTH: 'Both'>, save_detected_map=True, advanced_weighting=None, effective_region_mask=None, pulid_mode=<PuLIDMode.FIDELITY: 'Fidelity'>, ipadapter_input=None, mask=None, batch_mask_dir=None, animatediff_batch=False, batch_modifiers=[], batch_image_files=[]), ControlNetUnit(is_ui=True, input_mode=<InputMode.SIMPLE: 'simple'>, batch_images='', output_dir='', loopback=False, enabled=False, module='none', model='None', weight=1.0, image=None, resize_mode=<ResizeMode.INNER_FIT: 'Crop and Resize'>, low_vram=False, processor_res=-1, threshold_a=-1.0, threshold_b=-1.0, guidance_start=0.0, guidance_end=1.0, pixel_perfect=False, control_mode=<ControlMode.BALANCED: 'Balanced'>, inpaint_crop_input_image=False, hr_option=<HiResFixOption.BOTH: 'Both'>, save_detected_map=True, advanced_weighting=None, effective_region_mask=None, pulid_mode=<PuLIDMode.FIDELITY: 'Fidelity'>, ipadapter_input=None, mask=None, batch_mask_dir=None, animatediff_batch=False, batch_modifiers=[], batch_image_files=[]), ControlNetUnit(is_ui=True, input_mode=<InputMode.SIMPLE: 'simple'>, batch_images='', output_dir='', loopback=False, enabled=False, module='none', model='None', weight=1.0, image=None, resize_mode=<ResizeMode.INNER_FIT: 'Crop and Resize'>, low_vram=False, processor_res=-1, threshold_a=-1.0, threshold_b=-1.0, guidance_start=0.0, guidance_end=1.0, pixel_perfect=False, control_mode=<ControlMode.BALANCED: 'Balanced'>, inpaint_crop_input_image=False, hr_option=<HiResFixOption.BOTH: 'Both'>, save_detected_map=True, advanced_weighting=None, effective_region_mask=None, pulid_mode=<PuLIDMode.FIDELITY: 'Fidelity'>, ipadapter_input=None, mask=None, batch_mask_dir=None, animatediff_batch=False, batch_modifiers=[], batch_image_files=[]), False, False, 'Matrix', 'Columns', 'Mask', 'Prompt', '1,1', '0.2', False, False, False, 'Attention', [False], '0', '0', '0.4', None, '0', '0', False, False, False, 'positive', 'comma', 0, False, False, 'start', '', 1, '4747468459', [], 1, '0785858959', [], 1, '7847474864', [], True, False, False, False, False, False, False, 0, False, None, None, False, None, None, False, None, None, False, 50, [], 30, '', 4, [], 1, '', '', '', '') {}
Traceback (most recent call last):
File "F:\sd.webui\webui\modules\call_queue.py", line 57, in f
res = list(func(*args, **kwargs))
File "F:\sd.webui\webui\modules\call_queue.py", line 36, in f
res = func(*args, **kwargs)
File "F:\sd.webui\webui\modules\txt2img.py", line 109, in txt2img
processed = processing.process_images(p)
File "F:\sd.webui\webui\extensions\sd-webui-prompt-history\lib_history\image_process_hijacker.py", line 21, in process_images
res = original_function(p)
File "F:\sd.webui\webui\modules\processing.py", line 845, in process_images
res = process_images_inner(p)
File "F:\sd.webui\webui\extensions\sd-webui-controlnet\scripts\batch_hijack.py", line 59, in processing_process_images_hijack
return getattr(processing, '__controlnet_original_process_images_inner')(p, *args, **kwargs)
File "F:\sd.webui\webui\modules\processing.py", line 981, in process_images_inner
samples_ddim = p.sample(conditioning=p.c, unconditional_conditioning=p.uc, seeds=p.seeds, subseeds=p.subseeds, subseed_strength=p.subseed_strength, prompts=p.prompts)
File "F:\sd.webui\webui\extensions\sd-webui-controlnet\scripts\hook.py", line 463, in process_sample
return process.sample_before_CN_hack(*args, **kwargs)
File "F:\sd.webui\webui\modules\processing.py", line 1328, in sample
samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
File "F:\sd.webui\webui\modules\sd_samplers_kdiffusion.py", line 218, in sample
samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
File "F:\sd.webui\webui\modules\sd_samplers_common.py", line 272, in launch_sampling
return func()
File "F:\sd.webui\webui\modules\sd_samplers_kdiffusion.py", line 218, in <lambda>
samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
File "F:\sd.webui\webui\venv\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "F:\sd.webui\webui\repositories\k-diffusion\k_diffusion\sampling.py", line 145, in sample_euler_ancestral
denoised = model(x, sigmas[i] * s_in, **extra_args)
File "F:\sd.webui\webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "F:\sd.webui\webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "F:\sd.webui\webui\modules\sd_samplers_cfg_denoiser.py", line 269, in forward
devices.test_for_nans(x_out, "unet")
File "F:\sd.webui\webui\modules\devices.py", line 255, in test_for_nans
raise NansException(message)
modules.devices.NansException: A tensor with all NaNs was produced in Unet. This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try setting the "Upcast cross attention layer to float32" option in Settings > Stable Diffusion or using the --no-half commandline argument to fix this. Use --disable-nan-check commandline argument to disable this check.
---
Loading VAE weights specified in settings: F:\sd.webui\webui\models\VAE\vae-ft-mse-840000-ema-pruned.ckpt
Applying attention optimization: Doggettx... done.
VAE weights loaded.
INFO:sd_dynamic_prompts.dynamic_prompting:Prompt matrix will create 6 images in a total of 6 batches.
2024-05-13 16:21:20,095 - ControlNet - INFO - unit_separate = True, style_align = False
2024-05-13 16:21:20,096 - ControlNet - INFO - Loading model from cache: control_v11f1p_sd15_depth [cfd03158]
2024-05-13 16:21:20,100 - ControlNet - INFO - Using preprocessor: none
2024-05-13 16:21:20,100 - ControlNet - INFO - preprocessor resolution = 512
2024-05-13 16:21:20,135 - ControlNet - INFO - ControlNet Hooked - Time = 0.04179501533508301
100%|██████████████████████████████████████████████████████████████████████████████████| 40/40 [00:03<00:00, 10.02it/s]
tiled upscale: 100%|███████████████████████████████████████████████████████████████████| 15/15 [00:00<00:00, 41.29it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 15/15 [00:12<00:00, 1.20it/s]
Total progress: 33%|█████████████████████▎ | 110/330 [01:12<02:59, 1.23it/s]
0: 640x448 1 face, 64.2ms
Speed: 2.0ms preprocess, 64.2ms inference, 1.0ms postprocess per image at shape (1, 3, 640, 448)
100%|██████████████████████████████████████████████████████████████████████████████████| 17/17 [00:02<00:00, 7.13it/s]
INFO:sd_dynamic_prompts.dynamic_prompting:Prompt matrix will create 6 images in a total of 6 batches.
0%| | 0/40 [00:00<?, ?it/s]
Restoring base VAE
Applying attention optimization: Doggettx... done.
VAE weights loaded.
*** Error completing request
*** Arguments: ('task(rtyth4ybonq7si4)', <gradio.routes.Request object at 0x0000022BA115C430>, '(masterpiece, best quality, perfect hourglass figure, wide waist,(masterpiece, best quality,), busty, portrait, perfect face, flawless eyes, beautiful lips, full lips, sultry look, head tilt, seductive grin, <lora:add_detail:-0.2>, perfect waist, cowboy shot, perfect hips, <lora:sanpaku-eyes-v2:0.8> , sanpaku, round pupils, wide smile, huge breasts, saggy breasts, <lora:Sagging Breasts v1:1.2> (sagging breasts:1.2), ((ombre orange hair)), two-tone hair, multicolored hair, <lora:Ombre Hair:0.7>, wild hair, long hair, <lora:concave:0.8> , concave bangs, (collarbone), solo, (open shirt), puffy nipples, (white nurse oufit:1.4), nurse cap, looking at viewer, (blush:1.2), smiling, nsfw, on back, pussy, solo, on bed, legs up, arms up', '(worst quality:1.6, low quality:1.6), fat, ugly, lowres, blurry, FastNegativeV2, easynegative, cat ears, wrinkles, (earrings), (hands), watermark, signature, moles, nonsensical hair, (((coat))), holding,', [], 6, 1, 8, 768, 512, True, 0.4, 2, 'R-ESRGAN 4x+ Anime6B', 15, 0, 0, 'Use same checkpoint', 'Use same sampler', 'Use same scheduler', '', '', ['Clip skip: 2', 'VAE: vae-ft-mse-840000-ema-pruned.ckpt'], 0, 40, 'Euler a', 'Automatic', False, '', 0.8, 964617240, False, -1, 0, 0, 0, 'Automatic', 1, True, False, {'ad_model': 'face_yolov8n.pt', 'ad_model_classes': '', 'ad_prompt': '(masterpiece, best quality), blush, perfect face, flawless eyes, pink eyes, beautiful lips, full lips, <lora:add_detail:-0.2>, <lora:sanpaku-eyes-v2:0.8> , sanpaku, round pupils, wide smile,<lora:concave:0.8> , concave bangs, sultry look, head tilt, seductive grin', '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': 'DPM++ 2M', 'ad_scheduler': 'Use same scheduler', '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': 'DPM++ 2M', 'ad_scheduler': 'Use same scheduler', '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': ()}, True, False, 1, False, False, False, 1.1, 1.5, 100, 0.7, False, False, True, False, False, 0, 'Gustavosta/MagicPrompt-Stable-Diffusion', '', False, 7, 100, 'Constant', 0, 'Constant', 0, 4, True, 'MEAN', 'AD', 1, ControlNetUnit(is_ui=True, input_mode=<InputMode.SIMPLE: 'simple'>, batch_images='', output_dir='', loopback=False, enabled=False, module='none', model='control_v11f1p_sd15_depth [cfd03158]', weight=1.0, image={'image': array([[[ 29, 29, 29],
*** [ 28, 28, 28],
*** [ 28, 28, 28],
*** ...,
*** [ 19, 19, 19],
*** [ 18, 18, 18],
*** [ 12, 12, 12]],
***
*** [[ 27, 27, 27],
*** [ 28, 28, 28],
*** [ 28, 28, 28],
*** ...,
*** [ 19, 19, 19],
*** [ 18, 18, 18],
*** [ 18, 18, 18]],
***
*** [[ 28, 28, 28],
*** [ 28, 28, 28],
*** [ 27, 27, 27],
*** ...,
*** [ 19, 19, 19],
*** [ 18, 18, 18],
*** [ 19, 19, 19]],
***
*** ...,
***
*** [[161, 161, 161],
*** [162, 162, 162],
*** [161, 161, 161],
*** ...,
*** [ 77, 77, 77],
*** [ 77, 77, 77],
*** [ 77, 77, 77]],
***
*** [[162, 162, 162],
*** [162, 162, 162],
*** [162, 162, 162],
*** ...,
*** [ 78, 78, 78],
*** [ 78, 78, 78],
*** [ 79, 79, 79]],
***
*** [[161, 161, 161],
*** [162, 162, 162],
*** [162, 162, 162],
*** ...,
*** [ 80, 80, 80],
*** [ 80, 80, 80],
*** [ 80, 80, 80]]], dtype=uint8), 'mask': array([[[0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0],
*** ...,
*** [0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0]],
***
*** [[0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0],
*** ...,
*** [0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0]],
***
*** [[0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0],
*** ...,
*** [0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0]],
***
*** ...,
***
*** [[0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0],
*** ...,
*** [0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0]],
***
*** [[0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0],
*** ...,
*** [0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0]],
***
*** [[0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0],
*** ...,
*** [0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0]]], dtype=uint8)}, resize_mode=<ResizeMode.INNER_FIT: 'Crop and Resize'>, low_vram=False, processor_res=512, threshold_a=0.5, threshold_b=0.5, guidance_start=0.0, guidance_end=1.0, pixel_perfect=True, control_mode=<ControlMode.BALANCED: 'Balanced'>, inpaint_crop_input_image=False, hr_option=<HiResFixOption.BOTH: 'Both'>, save_detected_map=True, advanced_weighting=None, effective_region_mask=None, pulid_mode=<PuLIDMode.FIDELITY: 'Fidelity'>, ipadapter_input=None, mask=None, batch_mask_dir=None, animatediff_batch=False, batch_modifiers=[], batch_image_files=[]), ControlNetUnit(is_ui=True, input_mode=<InputMode.SIMPLE: 'simple'>, batch_images='', output_dir='', loopback=False, enabled=False, module='none', model='None', weight=1.0, image=None, resize_mode=<ResizeMode.INNER_FIT: 'Crop and Resize'>, low_vram=False, processor_res=-1, threshold_a=-1.0, threshold_b=-1.0, guidance_start=0.0, guidance_end=1.0, pixel_perfect=False, control_mode=<ControlMode.BALANCED: 'Balanced'>, inpaint_crop_input_image=False, hr_option=<HiResFixOption.BOTH: 'Both'>, save_detected_map=True, advanced_weighting=None, effective_region_mask=None, pulid_mode=<PuLIDMode.FIDELITY: 'Fidelity'>, ipadapter_input=None, mask=None, batch_mask_dir=None, animatediff_batch=False, batch_modifiers=[], batch_image_files=[]), ControlNetUnit(is_ui=True, input_mode=<InputMode.SIMPLE: 'simple'>, batch_images='', output_dir='', loopback=False, enabled=False, module='none', model='None', weight=1.0, image=None, resize_mode=<ResizeMode.INNER_FIT: 'Crop and Resize'>, low_vram=False, processor_res=-1, threshold_a=-1.0, threshold_b=-1.0, guidance_start=0.0, guidance_end=1.0, pixel_perfect=False, control_mode=<ControlMode.BALANCED: 'Balanced'>, inpaint_crop_input_image=False, hr_option=<HiResFixOption.BOTH: 'Both'>, save_detected_map=True, advanced_weighting=None, effective_region_mask=None, pulid_mode=<PuLIDMode.FIDELITY: 'Fidelity'>, ipadapter_input=None, mask=None, batch_mask_dir=None, animatediff_batch=False, batch_modifiers=[], batch_image_files=[]), False, False, 'Matrix', 'Columns', 'Mask', 'Prompt', '1,1', '0.2', False, False, False, 'Attention', [False], '0', '0', '0.4', None, '0', '0', False, False, False, 'positive', 'comma', 0, False, False, 'start', '', 1, '4747468459', [], 1, '0785858959', [], 1, '7847474864', [], True, False, False, False, False, False, False, 0, False, None, None, False, None, None, False, None, None, False, 50, [], 30, '', 4, [], 1, '', '', '', '') {}
Traceback (most recent call last):
File "F:\sd.webui\webui\modules\call_queue.py", line 57, in f
res = list(func(*args, **kwargs))
File "F:\sd.webui\webui\modules\call_queue.py", line 36, in f
res = func(*args, **kwargs)
File "F:\sd.webui\webui\modules\txt2img.py", line 109, in txt2img
processed = processing.process_images(p)
File "F:\sd.webui\webui\extensions\sd-webui-prompt-history\lib_history\image_process_hijacker.py", line 21, in process_images
res = original_function(p)
File "F:\sd.webui\webui\modules\processing.py", line 845, in process_images
res = process_images_inner(p)
File "F:\sd.webui\webui\extensions\sd-webui-controlnet\scripts\batch_hijack.py", line 59, in processing_process_images_hijack
return getattr(processing, '__controlnet_original_process_images_inner')(p, *args, **kwargs)
File "F:\sd.webui\webui\modules\processing.py", line 981, in process_images_inner
samples_ddim = p.sample(conditioning=p.c, unconditional_conditioning=p.uc, seeds=p.seeds, subseeds=p.subseeds, subseed_strength=p.subseed_strength, prompts=p.prompts)
File "F:\sd.webui\webui\extensions\sd-webui-controlnet\scripts\hook.py", line 463, in process_sample
return process.sample_before_CN_hack(*args, **kwargs)
File "F:\sd.webui\webui\modules\processing.py", line 1328, in sample
samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
File "F:\sd.webui\webui\modules\sd_samplers_kdiffusion.py", line 218, in sample
samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
File "F:\sd.webui\webui\modules\sd_samplers_common.py", line 272, in launch_sampling
return func()
File "F:\sd.webui\webui\modules\sd_samplers_kdiffusion.py", line 218, in <lambda>
samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
File "F:\sd.webui\webui\venv\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "F:\sd.webui\webui\repositories\k-diffusion\k_diffusion\sampling.py", line 145, in sample_euler_ancestral
denoised = model(x, sigmas[i] * s_in, **extra_args)
File "F:\sd.webui\webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "F:\sd.webui\webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "F:\sd.webui\webui\modules\sd_samplers_cfg_denoiser.py", line 269, in forward
devices.test_for_nans(x_out, "unet")
File "F:\sd.webui\webui\modules\devices.py", line 255, in test_for_nans
raise NansException(message)
modules.devices.NansException: A tensor with all NaNs was produced in Unet. This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try setting the "Upcast cross attention layer to float32" option in Settings > Stable Diffusion or using the --no-half commandline argument to fix this. Use --disable-nan-check commandline argument to disable this check.
---
Loading VAE weights specified in settings: F:\sd.webui\webui\models\VAE\vae-ft-mse-840000-ema-pruned.ckpt
Applying attention optimization: Doggettx... done.
VAE weights loaded.
2024-05-13 16:26:49,023 - ControlNet - INFO - unit_separate = True, style_align = False
2024-05-13 16:26:49,023 - ControlNet - INFO - Loading model from cache: control_v11f1p_sd15_depth [cfd03158]
2024-05-13 16:26:49,027 - ControlNet - INFO - Using preprocessor: none
2024-05-13 16:26:49,027 - ControlNet - INFO - preprocessor resolution = 512
2024-05-13 16:26:49,065 - ControlNet - INFO - ControlNet Hooked - Time = 0.04369616508483887
100%|██████████████████████████████████████████████████████████████████████████████████| 40/40 [00:03<00:00, 10.08it/s]
tiled upscale: 100%|███████████████████████████████████████████████████████████████████| 15/15 [00:00<00:00, 42.39it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 15/15 [00:12<00:00, 1.20it/s]
Total progress: 165it [06:41, 1.23it/s]
0: 640x448 1 face, 65.2ms
Speed: 1.0ms preprocess, 65.2ms inference, 1.0ms postprocess per image at shape (1, 3, 640, 448)
100%|██████████████████████████████████████████████████████████████████████████████████| 17/17 [00:02<00:00, 7.46it/s]
Restoring base VAE
Applying attention optimization: Doggettx... done.
VAE weights loaded.
Total progress: 165it [06:46, 2.47s/it]
Total progress: 165it [06:46, 1.23it/s]
Andy91xx
commented
4 months ago
Is there an existing issue for this?
What happened?
when control net is enabled i cant generate more then one generation at a time if the number is above 1 it attempts to generate 1 image and then comes up with this error NansException: A tensor with all NaNs was produced in Unet. This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try setting the "Upcast cross attention layer to float32" option in Settings > Stable Diffusion or using the --no-half commandline argument to fix this. Use --disable-nan-check commandline argument to disable this check.
Steps to reproduce the problem
What should have happened?
stable diffusion should generate the number of images i selected usually 6
Commit where the problem happens
webui: controlnet:
What browsers do you use to access the UI ?
Mozilla Firefox
Command Line Arguments
List of enabled extensions
Console logs
Additional information
No response