-
Notifications
You must be signed in to change notification settings - Fork 25.6k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
error: Input types are not broadcast compatible #1890
Comments
I'm having a similar problem. I'm using
I modified the following files to be able to use this project, stable-diffusion-webui. // launch.py
torch_command = os.environ.get('TORCH_COMMAND', "pip install torch==1.12.1 torchvision==0.13.1 --extra-index-url https://download.pytorch.org/whl/cu113")
commandline_args = os.environ.get('COMMANDLINE_ARGS', "--skip-torch-cuda-test") // requirements.txt
diffusers==0.4.1
// instead of functorch==0.2.1
git+https://github.com/pytorch/functorch@release/0.2 // webui-user.sh
# Commandline arguments for webui.py, for example: export COMMANDLINE_ARGS="--medvram --opt-split-attention"
export COMMANDLINE_ARGS="--skip-torch-cuda-test"
|
Were you able to resolve this issue? |
@amitsangani Unfortunately, no. |
I've got the same issue. I'm using M1 Mac. Trying to train hypernetwork. Run-time error.
{
"datetime": "2023-01-29 02:31:36",
"model_name": "v1-5-pruned-emaonly",
"model_hash": "cc6cb27103",
"num_of_dataset_images": 21,
"layer_structure": [
1.0,
2.0,
1.0
],
"activation_func": "linear",
"weight_init": "Normal",
"add_layer_norm": false,
"use_dropout": false,
"hypernetwork_name": "alg",
"learn_rate": "0.00005",
"batch_size": 1,
"gradient_step": 1,
"data_root": "/Users/alg/Downloads/sl-model/preprocessed",
"log_directory": "textual_inversion/2023-01-29/sl",
"training_width": 512,
"training_height": 512,
"steps": 2000,
"clip_grad_mode": "disabled",
"clip_grad_value": "0.1",
"latent_sampling_method": "once",
"create_image_every": 100,
"save_hypernetwork_every": 100,
"template_file": "/Users/alg/Sites/stable-diffusion-webui/textual_inversion_templates/style_filewords.txt",
"initial_step": 0
} |
Same error here |
Same issue. Mac M1 |
same here - happens when trying to use a prepared hypernetwork |
I'm on M1 Pro and I have error too when I try to train an embedding:
|
Same here, but only when using a hypernetwork. I can run a standard model and generate images just fine, but when I try and add a hypernetwork I get the error.
The above is with the default
|
Hey @brkirch you seem to know a thing or two about MPS, any thoughts on this? |
Ok, so adding Anyway, I suppose I can live with the performance penalty that |
Confirm that adding |
In diffusers' stable diffusion, a recent upgrade started giving me this error. I had to remove torch calls that requested fp16 |
same error. |
@JumpIntoCoding After add --no-half, it works
It shows the similar error previously
|
@pjq wow, I guess its working now after I add --no-half. |
./webui.sh --no-half, it works |
Thanks a lot !! @fork4jm |
It works for me too. Thank you! |
thanks a lot. question for re launch 1111 do I have to proceed all the steps in the command every time I relaunch 1111? |
A1111 is a again crashing on MacOS M2.. relating to memory/RAM. 😞 |
adding |
@alex-the-programmer See https://github.com/abetlen/llama-cpp-python/blob/main/docs/install/macos.md. That is the setup I use for Python GPU/NPU work - a conda version for MacOS that supports Metal GPU + the latest nightly Pytorch build. By default, A1111 manages the Python environment itself using venv... though I have a bash script that I periodically run to get the latest nightly Pytorch. The A1111 venv setup DOES enable MacOS GPUs. Though the A1111 way of updating with MacOS Pytorch nightly would be to edit You can see the GPUs being used when you run A1111 - I use https://github.com/tlkh/asitop |
That said - the new A1111 version v1.4.0 is completely crashing out Python 😞 |
Closing as stale. |
sorry for silly question but how I do invoke the command? ./webui.sh --share --skip-torch-cuda-test --no-half |
You can put those in |
1111 ver.1.6 has an automatic Web UI launch function. |
* Port DW Pose preprocessor (#1856) * ➕ Add dependencies * 🚧 wip * 🚧 wip * 🚧 download models * 🚧 Minor fixes * 🔧 update gitignore * 🐛 Fix normalization issue * 🚧 load DW model only when DW preprocessor is selected * ✅ Change test config * 🎨 nits * 🐛 Fix A1111 safe torch issue 📝 v1.1.235 (AUTOMATIC1111#1859) Revert "Port DW Pose preprocessor (#1856)" (AUTOMATIC1111#1860) This reverts commit 0d3310f. Reland "Port DW Pose preprocessor" (AUTOMATIC1111#1861) * Revert "Revert "Port DW Pose preprocessor (#1856)" (AUTOMATIC1111#1860)" This reverts commit 17e100e. * 🐛 Fix install.py 📝 v1.1.236 (AUTOMATIC1111#1862) :bug: Delay import of mmpose (AUTOMATIC1111#1866) :memo: v1.1.237 (AUTOMATIC1111#1868) :bug: Fix all keypoints invalid issue (AUTOMATIC1111#1871) :bug: lazy import * :construction: update test expectation * :construction: Switch to onnx * :construction: solve onnx package issue * :wrench: Check cuda in more efficient way * :art: Format code
This reverts commit e141d33.
no such file |
have you found out any solution for this ? In facing the same issue. |
works for me, thx |
Describe the bug
When attempting to generate an image batch, I get this error:
Batch 1 out of 4: 0%| | 0/30 [00:00<?, ?it/s]loc("mps_add"("(mpsFileLoc): /AppleInternal/Library/BuildRoots/20d6c351-ee94-11ec-bcaf-7247572f23b4/Library/Caches/com.apple.xbs/Sources/MetalPerformanceShadersGraph/mpsgraph/MetalPerformanceShadersGraph/Core/Files/MPSGraphUtilities.mm":219:0)): error: input types 'tensor<2x1280xf32>' and 'tensor<*xf16>' are not broadcast compatible LLVM ERROR: Failed to infer result type(s). zsh: abort python webui.py (web-ui) karsten@MacBook-Pro-2020 stable-diffusion-webui % /Users/karsten/miniconda3/envs/web-ui/lib/python3.10/multiprocessing/resource_tracker.py:224: UserWarning: resource_tracker: There appear to be 1 leaked semaphore objects to clean up at shutdown warnings.warn('resource_tracker: There appear to be %d '
This happens whenever I try and generate a batch of images.
Expected behavior
I'd expect it to run smoothly?
Screenshots
If applicable, add screenshots to help explain your problem.
Desktop (please complete the following information):
The text was updated successfully, but these errors were encountered: