Closed KrakenJet closed 11 months ago
Having same problem for my machine.
What happened? Error occurs when using any form of controlnet
Steps to reproduce the problem Go to SD 1.5 Automatic1111 enabled controlnet, put variety of images in preprocessor runs to generate needed control image, then i press generate, afer 1-8 seconds comes back with error
What should have happened? Not give an error, but give me an posed image, upscaled image, or what i requested.
Commit where the problem happens has happened since install 2 weeks ago.
What browsers do you use to access the UI ? Google Chrome
Command Line Arguments --api --xformers --precision full --upcast-sampling --no-half-vae --medvram --always-batch-cond-uncond --opt-split-attention --opt-channelslast --enable-insecure-extension-access --disable-nan-check --theme dark tried deleting commands one by one and it didn't work
List of enabled extensions OneButtonPrompt a1111-sd-webui-tagcomplete adetailer canvas-zoom deforum-for-automatic1111-webui model-keyword multidiffusion-upscaler-for-automatic1111 openpose-editor sd-dynamic-prompts sd-extension-system-info sd-webui-3d-open-pose-editor sd-webui-aspect-ratio-helper sd-webui-controlnet sd-webui-mov2mov sd-webui-openpose-editor sd-webui-roop stable-diffusion-webui-rembg stable-diffusion-webui-ux ultimate-upscale-for-automatic1111
system arch: AMD64 cpu: Intel64 Family 6 Model 158 Stepping 13, GenuineIntel system: Windows release: Windows-10-10.0.19045-SP0 python: 3.10.6
gpu device: NVIDIA GeForce GTX 1660 Ti (1) (compute_37) (7, 5) cuda: 11.8 cudnn: 8700 driver: 531.41
Console: `2023-11-21 14:50:35,270 - ControlNet - INFO - Loading model: control_v11p_sd15_inpaint [ebff9138]████████████████████████████████████| 20/20 [00:52<00:00, 2.64s/it] 2023-11-21 14:50:37,613 - ControlNet - INFO - Loaded state_dict from [C:\Apache24\htdocs\AI\stable-diffusion-webui\models\ControlNet\control_v11p_sd15_inpaint.pth] 2023-11-21 14:50:37,614 - ControlNet - INFO - controlnet_default_config 2023-11-21 14:50:40,270 - ControlNet - INFO - ControlNet model control_v11p_sd15_inpaint [ebff9138] loaded. 2023-11-21 14:50:40,383 - ControlNet - INFO - using inpaint as input 2023-11-21 14:50:40,426 - ControlNet - INFO - Loading preprocessor: inpaint_only+lama 2023-11-21 14:50:40,464 - ControlNet - INFO - preprocessor resolution = -1 Downloading: "https://huggingface.co/lllyasviel/Annotators/resolve/main/ControlNetLama.pth" to C:\Apache24\htdocs\AI\stable-diffusion-webui\extensions\sd-webui-controlnet\annotator\downloads\lama\ControlNetLama.pth
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 195M/195M [00:18<00:00, 10.8MB/s]
2023-11-21 14:51:11,584 - ControlNet - INFO - ControlNet used torch.float32 VAE to encode torch.Size([1, 4, 64, 192]).
2023-11-21 14:51:11,651 - ControlNet - INFO - ControlNet Hooked - Time = 36.7220938205719
2023-11-21 14:51:13,394 - ControlNet - INFO - [ControlNet] Initial noise hack applied to torch.Size([1, 4, 64, 192]).
0%| | 0/17 [00:03<?, ?it/s]
Error completing request
Arguments: ('task(gcxvsjo7862761e)', 0, "Enchanting forest glade with (sunbeamsfiltering through trees), (natural lighting), \n\n(mossy rocks), (dirt path:1.3),\n(delicate wildflowers), (butterflies), (birds), (mushrooms),\n
[[191, 210, 158], [181, 211, 160], [120, 152, 103], ..., [ 27, 30, 20], [ 24, 32, 18], *** [ 24, 30, 18]],
[[163, 183, 131], [172, 206, 147], [149, 185, 131], ..., [ 27, 31, 19], [ 27, 33, 19], *** [ 25, 30, 19]],
*** ...,
[[ 9, 17, 13], [ 8, 15, 11], [ 8, 15, 10], ..., [ 3, 2, 2], [ 2, 3, 1], *** [ 1, 4, 1]],
[[ 8, 17, 10], [ 6, 15, 7], [ 7, 16, 10], ..., [ 1, 1, 0], [ 1, 3, 2], *** [ 1, 2, 0]],
[[ 5, 14, 10], [ 6, 13, 8], [ 6, 13, 10], ..., [ 2, 0, 1], [ 1, 0, 2], [ 0, 0, 0]]], 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='Resize and Fill', low_vram=True, processor_res=-1, threshold_a=-1, threshold_b=-1, guidance_start=0, guidance_end=1, pixel_perfect=False, control_mode='ControlNet is more important', save_detected_map=True), UiControlNetUnit(enabled=False, module='none', model='None', weight=1, image=None, resize_mode='Crop and Resize', low_vram=False, processor_res=-1, threshold_a=-1, threshold_b=-1, guidance_start=0, guidance_end=1, pixel_perfect=False, control_mode='Balanced', save_detected_map=True), UiControlNetUnit(enabled=False, module='none', model='None', weight=1, image=None, resize_mode='Crop and Resize', low_vram=False, processor_res=-1, threshold_a=-1, threshold_b=-1, guidance_start=0, guidance_end=1, pixel_perfect=False, control_mode='Balanced', save_detected_map=True), None, False, '0', 'C:\Apache24\htdocs\AI\stable-diffusion-webui\models\roop\inswapper_128.onnx', 'CodeFormer', 1, '', 1, 1, False, True, ' Recommended settings: Sampling Steps: 80-100, Sampler: Euler a, Denoising strength: 0.8 Will upscale the image by the selected scale factor; use width and height sliders to set tile size Recommended settings: Sampling Steps: 80-100, Sampler: Euler a, Denoising strength: 0.8 Will upscale the image by the selected scale factor; use width and height sliders to set tile size Will upscale the image depending on the selected target size typeCFG Scale
should be 2 or lower.', True, True, '', '', True, 50, True, 1, 0, False, 4, 0.5, 'Linear', 'None', 'CFG Scale
should be 2 or lower.', True, True, '', '', True, 50, True, 1, 0, False, 4, 0.5, 'Linear', 'None', '
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: v1.6.0-2-g4afaaf8a
Commit hash: 4afaaf8a020c1df457bcf7250cb1c7f609699fa7
Installing sd-webui-controlnet requirement: changing opencv-python version from 4.7.0.72 to 4.8.0
Installing requirements for Mov2mov
Installing requirements for imageio-ffmpeg
Checking roop requirements
Install insightface==0.7.3
Installing sd-webui-roop requirement: insightface==0.7.3
Install onnx==1.14.0
Installing sd-webui-roop requirement: onnx==1.14.0
Install onnxruntime==1.15.0
Installing sd-webui-roop requirement: onnxruntime==1.15.0
Install opencv-python==4.7.0.72
Installing sd-webui-roop requirement: opencv-python==4.7.0.72
Launching Web UI with arguments: --api --xformers --precision full --upcast-sampling --no-half-vae --medvram --always-batch-cond-uncond --opt-split-attention --opt-channelslast --enable-insecure-extension-access --disable-nan-check --theme dark
2023-11-21 14:58:00.325408: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable TF_ENABLE_ONEDNN_OPTS=0
.
WARNING:tensorflow:From C:\Apache24\htdocs\AI\stable-diffusion-webui\venv\lib\site-packages\keras\src\losses.py:2976: The name tf.losses.sparse_softmax_cross_entropy is deprecated. Please use tf.compat.v1.losses.sparse_softmax_cross_entropy instead.
[-] ADetailer initialized. version: 23.11.1, num models: 9 2023-11-21 14:58:13,227 - ControlNet - INFO - ControlNet v1.1.418 ControlNet preprocessor location: C:\Apache24\htdocs\AI\stable-diffusion-webui\extensions\sd-webui-controlnet\annotator\downloads 2023-11-21 14:58:13,423 - ControlNet - INFO - ControlNet v1.1.418 2023-11-21 14:58:14,063 - roop - INFO - roop v0.0.2 2023-11-21 14:58:14,174 - roop - INFO - roop v0.0.2 Loading weights [879db523c3] from C:\Apache24\htdocs\AI\stable-diffusion-webui\models\Stable-diffusion\dreamshaper_8.safetensors Creating model from config: C:\Apache24\htdocs\AI\stable-diffusion-webui\configs\v1-inference.yaml Deforum ControlNet support: enabled Running on local URL: http://127.0.0.1:7860
To create a public link, set share=True
in launch()
.
Startup time: 52.3s (prepare environment: 31.1s, import torch: 11.9s, import gradio: 0.7s, setup paths: 0.9s, initialize shared: 0.2s, other imports: 0.6s, setup codeformer: 0.1s, load scripts: 4.6s, create ui: 1.7s, gradio launch: 0.3s, add APIs: 0.1s).
Applying attention optimization: xformers... done.
No Image data blocks found.
No Image data blocks found.
Model loaded in 11.7s (load weights from disk: 0.8s, create model: 1.6s, apply weights to model: 0.6s, apply channels_last: 0.4s, load textual inversion embeddings: 5.6s, calculate empty prompt: 2.5s).`
I don't think you are having the same issue based on stack trace. Please open a new issue and I will take a further look there.
Is there an existing issue for this?
What happened?
This error keeps popping up when I try to use controlnet's model control_v11p_sd15_canny [d14c016b] for image2image. What should I do? My specs are GTX1650 4GB and cpu is Ryzen 5 3550H 2100-3700 mghz, RAM 16gb. My command list for web.ui Automatic1111 - --xformers --upcast-sampling --precision full --no-half-vae --opt-split-attention
Steps to reproduce the problem
What should have happened?
Should've gotten a generated image with controlnet
Commit where the problem happens
webui: controlnet: here
What browsers do you use to access the UI ?
Google Chrome
Command Line Arguments
List of enabled extensions
Console logs
Additional information
No response