search

AUTOMATIC1111 / stable-diffusion-webui

Stable Diffusion web UI
GNU Affero General Public License v3.0
136.08k stars 25.95k forks source link

[Bug]: RuntimeError: Input type (float) and bias type (c10::Half) should be the same #10362

Open Aniket22156 opened 1 year ago

Aniket22156 commented 1 year ago

Is there an existing issue for this?

What happened?

I am using control net new reference only preprocessor and it gives this error: RuntimeError: Input type (float) and bias type (c10::Half) should be the same

Steps to reproduce the problem

  1. Go to control net and choose reference only in the preprocessor and add your prompt
  2. Press generate

What should have happened?

It should have generated the image same to the image added in the control net

Commit where the problem happens

b08500cec8a791ef20082628b49b17df833f5dda

What platforms do you use to access the UI ?

MacOS

What browsers do you use to access the UI ?

Google Chrome

Command Line Arguments

Np

List of extensions

dreambooth, controlnet,

Console logs

################################################################
Install script for stable-diffusion + Web UI
Tested on Debian 11 (Bullseye)
################################################################

################################################################
Running on aniketsharma user
################################################################

################################################################
Repo already cloned, using it as install directory
################################################################

################################################################
Create and activate python venv
################################################################

################################################################
Launching launch.py...
################################################################
Python 3.10.11 (main, Apr  7 2023, 07:24:53) [Clang 14.0.0 (clang-1400.0.29.202)]
Version: v1.2.0
Commit hash: b08500cec8a791ef20082628b49b17df833f5dda
Installing requirements
Installing sd-webui-controlnet requirement: svglib
Couldn't install sd-webui-controlnet requirement: svglib.
Command: "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/venv/bin/python3.10" -m pip install svglib --prefer-binary
Error code: 1
stdout: Collecting svglib
  Using cached svglib-1.5.1-py3-none-any.whl
Collecting reportlab (from svglib)
  Using cached reportlab-4.0.0-py3-none-any.whl (1.9 MB)
Collecting lxml (from svglib)
  Using cached lxml-4.9.2-cp310-cp310-macosx_13_0_arm64.whl
Collecting tinycss2>=0.6.0 (from svglib)
  Using cached tinycss2-1.2.1-py3-none-any.whl (21 kB)
Collecting cssselect2>=0.2.0 (from svglib)
  Using cached cssselect2-0.7.0-py3-none-any.whl (15 kB)
Collecting webencodings (from cssselect2>=0.2.0->svglib)
  Using cached webencodings-0.5.1-py2.py3-none-any.whl (11 kB)
Requirement already satisfied: pillow>=9.0.0 in ./venv/lib/python3.10/site-packages (from reportlab->svglib) (9.4.0)
Collecting rlPyCairo<1,>=0.2.0 (from reportlab->svglib)
  Using cached rlPyCairo-0.2.0-py3-none-any.whl (10 kB)
Collecting freetype-py<2.4,>=2.3.0 (from reportlab->svglib)
  Using cached freetype_py-2.3.0-py3-none-macosx_10_9_universal2.whl (1.7 MB)
Collecting pycairo>=1.20.0 (from rlPyCairo<1,>=0.2.0->reportlab->svglib)
  Using cached pycairo-1.23.0.tar.gz (344 kB)
  Installing build dependencies: started
  Installing build dependencies: finished with status 'done'
  Getting requirements to build wheel: started
  Getting requirements to build wheel: finished with status 'done'
  Installing backend dependencies: started
  Installing backend dependencies: finished with status 'done'
  Preparing metadata (pyproject.toml): started
  Preparing metadata (pyproject.toml): finished with status 'done'
Building wheels for collected packages: pycairo
  Building wheel for pycairo (pyproject.toml): started
  Building wheel for pycairo (pyproject.toml): finished with status 'error'
Failed to build pycairo

stderr:   error: subprocess-exited-with-error

  × Building wheel for pycairo (pyproject.toml) did not run successfully.
  │ exit code: 1
  ╰─> [15 lines of output]
      running bdist_wheel
      running build
      running build_py
      creating build
      creating build/lib.macosx-13-arm64-cpython-310
      creating build/lib.macosx-13-arm64-cpython-310/cairo
      copying cairo/__init__.py -> build/lib.macosx-13-arm64-cpython-310/cairo
      copying cairo/__init__.pyi -> build/lib.macosx-13-arm64-cpython-310/cairo
      copying cairo/py.typed -> build/lib.macosx-13-arm64-cpython-310/cairo
      running build_ext
      Package cairo was not found in the pkg-config search path.
      Perhaps you should add the directory containing `cairo.pc'
      to the PKG_CONFIG_PATH environment variable
      No package 'cairo' found
      Command '['pkg-config', '--print-errors', '--exists', 'cairo >= 1.15.10']' returned non-zero exit status 1.
      [end of output]

  note: This error originates from a subprocess, and is likely not a problem with pip.
  ERROR: Failed building wheel for pycairo
ERROR: Could not build wheels for pycairo, which is required to install pyproject.toml-based projects

Warning: Failed to install svglib, some preprocessors may not work.

Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
If submitting an issue on github, please provide the full startup log for debugging purposes.

Initializing Dreambooth
Dreambooth revision: 926ae204ef5de17efca2059c334b6098492a0641
Successfully installed fastapi-0.94.1 gitpython-3.1.31 requests-2.30.0 transformers-4.26.1

Does your project take forever to startup?
Repetitive dependency installation may be the reason.
Automatic1111's base project sets strict requirements on outdated dependencies.
If an extension is using a newer version, the dependency is uninstalled and reinstalled twice every startup.

Successfully installed MarkupSafe-2.1.2 filelock-3.12.0 jinja2-3.1.2 mpmath-1.3.0 mypy-extensions-1.0.0 networkx-3.1 numpy-1.24.3 pyre-extensions-0.0.23 sympy-1.12 torch-2.0.1 typing-extensions-4.5.0 typing-inspect-0.8.0 xformers-0.0.16
[!] xformers version 0.0.16 installed.
[+] torch version 2.0.1 installed.
[+] torchvision version 0.14.1 installed.
[+] accelerate version 0.18.0 installed.
[+] diffusers version 0.14.0 installed.
[+] transformers version 4.26.1 installed.
[+] bitsandbytes version 0.35.4 installed.

Launching Web UI with arguments: --skip-torch-cuda-test --upcast-sampling --no-half-vae --use-cpu interrogate
/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/venv/lib/python3.10/site-packages/torchvision/io/image.py:13: UserWarning: Failed to load image Python extension: dlopen(/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/venv/lib/python3.10/site-packages/torchvision/image.so, 0x0006): Symbol not found: __ZN3c106detail19maybe_wrap_dim_slowExxb
  Referenced from: <0B637046-A38B-3A5C-80C6-E847C27DCCD5> /Users/aniketsharma/Documents/fakes/stable-diffusion-webui/venv/lib/python3.10/site-packages/torchvision/image.so
  Expected in:     <3F9923D2-81A5-3EC8-9739-EC0C1C816132> /Users/aniketsharma/Documents/fakes/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch/lib/libc10.dylib
  warn(f"Failed to load image Python extension: {e}")
No module 'xformers'. Proceeding without it.
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
ControlNet v1.1.166
ControlNet v1.1.166
Loading weights [0f49d1caa2] from /Users/aniketsharma/Documents/fakes/stable-diffusion-webui/models/Stable-diffusion/perfectWorld_v3Baked.safetensors
Creating model from config: /Users/aniketsharma/Documents/fakes/stable-diffusion-webui/configs/v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying cross attention optimization (InvokeAI).
Textual inversion embeddings loaded(24): alexandradaddario, AnaD, awaitingtongue, bad-artist-anime, bad-hands-5, bad-picture-chill-75v, bad_prompt, bad_prompt_version2, badhandv4, BiL13L1SH, bukkakAI, By bad artist -neg, corneo_paizuri, corneo_runny_makeup, corneo_side_deepthroat, corneo_side_doggy, easynegative, emb-anada, jenn1f1850, ng_deepnegative_v1_75t, nudes, paradoxical-back-view-bj, thelab-ada, verybadimagenegative_v1.3
Textual inversion embeddings skipped(1): badquality
Model loaded in 8.9s (load weights from disk: 0.2s, create model: 0.5s, apply weights to model: 5.8s, apply half(): 1.7s, move model to device: 0.5s).
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Startup time: 14.5s (import torch: 2.4s, import gradio: 0.4s, import ldm: 0.2s, other imports: 0.7s, load scripts: 10.0s, create ui: 0.7s).
100%|██████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:32<00:00,  1.62s/it]
Total progress: 100%|██████████████████████████████████████████████████████████████████████| 20/20 [00:31<00:00,  1.59s/it]
Loading preprocessor: reference_only███████████████████████████████████████████████████████| 20/20 [00:31<00:00,  1.60s/it]
preprocessor resolution = 512
  0%|                                                                                               | 0/20 [00:00<?, ?it/s]ControlNet used torch.float32 VAE to encode torch.Size([1, 4, 98, 64]).
  0%|                                                                                               | 0/20 [00:02<?, ?it/s]
Error completing request
Arguments: ('task(7bqpn8a7giw8unf)', '((nsfw)), portrait, ultra realistic 8k cg, picture-perfect face, flawless, clean, masterpiece, professional artwork, famous artwork, cinematic lighting, cinematic bloom, perfect face, beautiful face, beautiful eyes, ((perfect female body, narrow waist)), masterpiece,  ', '(blurry image:1.1), (blurry picture:1.1), (worst quality, low quality:1.4), (out of frame), duplication, (folds:1.7), lowres, text, error, cropped, worst quality, low quality, jpeg artifacts, duplicate, morbid, mutilated, out of frame, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, (extra arms), (extra legs), fused fingers, too many fingers, long neck, username, watermark, signature, monochrome, deformed legs, see-through, ng_deepnegative_v1_75t', [], 20, 15, False, False, 1, 1, 7, -1.0, -1.0, 0, 0, 0, False, 784, 512, False, 0.7, 2, 'Latent', 0, 0, 0, [], 0, <controlnet.py.UiControlNetUnit object at 0x2c8f24400>, <controlnet.py.UiControlNetUnit object at 0x2c8f275e0>, <controlnet.py.UiControlNetUnit object at 0x2c8f37880>, False, False, 'positive', 'comma', 0, False, False, '', 1, '', [], 0, '', [], 0, '', [], True, False, False, False, 0, None, False, None, False, None, False, 50) {}
Traceback (most recent call last):
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/modules/call_queue.py", line 57, in f
    res = list(func(*args, **kwargs))
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/modules/call_queue.py", line 37, in f
    res = func(*args, **kwargs)
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/modules/txt2img.py", line 56, in txt2img
    processed = process_images(p)
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/modules/processing.py", line 526, in process_images
    res = process_images_inner(p)
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/extensions/sd-webui-controlnet/scripts/batch_hijack.py", line 42, in processing_process_images_hijack
    return getattr(processing, '__controlnet_original_process_images_inner')(p, *args, **kwargs)
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/modules/processing.py", line 680, in process_images_inner
    samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts)
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/modules/processing.py", line 907, in sample
    samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/modules/sd_samplers_kdiffusion.py", line 377, in sample
    samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/modules/sd_samplers_kdiffusion.py", line 251, in launch_sampling
    return func()
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/modules/sd_samplers_kdiffusion.py", line 377, in <lambda>
    samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/repositories/k-diffusion/k_diffusion/sampling.py", line 594, in sample_dpmpp_2m
    denoised = model(x, sigmas[i] * s_in, **extra_args)
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/modules/sd_samplers_kdiffusion.py", line 154, in forward
    x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond=make_condition_dict(c_crossattn, image_cond_in[a:b]))
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/repositories/k-diffusion/k_diffusion/external.py", line 114, in forward
    eps = self.get_eps(input * c_in, self.sigma_to_t(sigma), **kwargs)
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/repositories/k-diffusion/k_diffusion/external.py", line 140, in get_eps
    return self.inner_model.apply_model(*args, **kwargs)
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/modules/sd_hijack_utils.py", line 17, in <lambda>
    setattr(resolved_obj, func_path[-1], lambda *args, **kwargs: self(*args, **kwargs))
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/modules/sd_hijack_utils.py", line 26, in __call__
    return self.__sub_func(self.__orig_func, *args, **kwargs)
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/modules/sd_hijack_unet.py", line 45, in apply_model
    return orig_func(self, x_noisy.to(devices.dtype_unet), t.to(devices.dtype_unet), cond, **kwargs).float()
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/repositories/stable-diffusion-stability-ai/ldm/models/diffusion/ddpm.py", line 858, in apply_model
    x_recon = self.model(x_noisy, t, **cond)
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/repositories/stable-diffusion-stability-ai/ldm/models/diffusion/ddpm.py", line 1335, in forward
    out = self.diffusion_model(x, t, context=cc)
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/extensions/sd-webui-controlnet/scripts/hook.py", line 402, in forward_webui
    return forward(*args, **kwargs)
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/extensions/sd-webui-controlnet/scripts/hook.py", line 362, in forward
    outer.original_forward(x=ref_xt, timesteps=timesteps, context=context)
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/repositories/stable-diffusion-stability-ai/ldm/modules/diffusionmodules/openaimodel.py", line 807, in forward
    return self.out(h)
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch/nn/modules/container.py", line 217, in forward
    input = module(input)
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/extensions-builtin/Lora/lora.py", line 372, in lora_Conv2d_forward
    return torch.nn.Conv2d_forward_before_lora(self, input)
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/extensions/a1111-sd-webui-lycoris/lycoris.py", line 746, in lyco_Conv2d_forward
    return torch.nn.Conv2d_forward_before_lyco(self, input)
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch/nn/modules/conv.py", line 463, in forward
    return self._conv_forward(input, self.weight, self.bias)
  File "/Users/aniketsharma/Documents/fakes/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch/nn/modules/conv.py", line 459, in _conv_forward
    return F.conv2d(input, weight, bias, self.stride,
RuntimeError: Input type (float) and bias type (c10::Half) should be the same

Additional information

No response

abhinavasr commented 1 year ago

Same issue Using Mac with M1

karim3f commented 1 year ago

the same with me

mynameisbill commented 1 year ago

Same here. M1

Sakura-Luna commented 1 year ago

Use --no-half parameter.

Aniket22156 commented 1 year ago

Use --no-half parameter.

where and how, can you please tell

Sakura-Luna commented 1 year ago

You can directly enable or edit the startup file. Try ./webui.sh --no-half to run webui.

NancyReagan commented 1 year ago

I am still having this problem after starting up with no half. Anyone else? Any other solutions?

karim3f commented 1 year ago

I am still having this problem after starting up with no half. Anyone else? Any other solutions?

Try to update Controlnet, it would solve this issue

search620 commented 10 months ago

This what work for me! I am using 3060ti 8gb set COMMANDLINE_ARGS= --xformers --api --medvram --no-half-vae