How to install ComfyUI

66,996 views
Updated Categorized as Tutorial Tagged , 66 Comments on How to install ComfyUI
Install comfyUI on a laptop.

ComfyUI is a node-based user interface for Stable Diffusion. It’s gaining popularity among Stable Diffusion users. Developers and artists widely use it because it is extremely configurable.

It is a great alternative to more traditional Stable Diffusion GUIs like AUTOMATIC1111 and SD.Next.

This guide covers installing ComfyUI on Windows and Mac.

See the Beginner’s Guide for using ComfyUI.

Benefits of ComfyUI

Why using ComfyUI? It’s a different experience from other GUIs. ComfyUI stands out in the following areas.

1. Lightweight

Unlike other full-feature GUIs such as AUTOMATIC1111, ComfyUI only loads what is necessary. This results in lower memory usage and faster generations.

2. Flexible

ComfyUI is very configurable. You can easily generate two images with different CFG scales in a single workflow and compare the results.

3. You know what it is doing

If you have a good knowledge of how Stable Diffusion works, ComfyUI shows you exactly what it does. No more guessworks.

4. Easy to share workflows

Instead of writing a description of what buttons to click, you can save a workflow and share with someone else.

5. Good for prototyping

It’s a godsend for developers because you can prototype a workflow before coding it for production.

6. Cutting-edge workflows

AUTOMATIC1111 used to be the first GUI to implement the latest tools coming out from the research labs. But now the software team is taking a more cautious approach in pushing out new features.

ComfyUI has the benefit of being agile. Their node-based system allows many more users to wire up and share workflows. You can count on ComfyUI to use the latest goodies.

Structured Stable Diffusion courses
Become a Stable Diffusion Pro step-by-step.

Alternative to local installation

Installing and maintaining ComfyUI locally is not easy. After a successful installation, you still need to keep the software and custom nodes up to date.

Check out Think Diffusion for a fully managed ComfyUI online service. They offer 20% extra credits to our readers. (and a small commission to support this site if you sign up)

Installing ComfyUI on Windows

Two options to install ComfyUI on Windows:

  1. Standalone zip
  2. Manual installation

If you are not a developer of ComfyUI, you should use option 1. Option 2 is for folks who like to tinker with codes.

I will only go over option 1 here. Consult this guide for option 2.

Step 1: Install 7-Zip

You need the 7-zip software to uncompress ComfyUI’s zip file.

Download 7-zip on this page or use this direct download link.

Double-click to run the downloaded exe file. Click Install to install 7-zip on your PC.

Step 2: Download the standalone version of ComfyUI

Download ComfyUI with this direct download link.

When it is done, right-click on the file ComfyUI_windows_portable_nvidia_cu118_or_cpu.7z, select Show More Options > 7-Zip > Extract Here.

Extracting comfyUI with 7-zip

Your PC should be working hard for a while. When it is done, there should be a new folder called ComfyUI_windows_portable.

Feel free to move this folder to a location you like.

Step 3: Download a checkpoint model

You need a checkpoint model to start using ComfyUI.

You have two options: (1) download a model, or (2) share models with other Stable Diffusion GUI such as AUTOMATIC1111.

Feel free to download any model. Here’s the download link for the DreamShaper 8 model.

Put the model in the folder

ComfyUI_windows_portable\ComfyUI\models\checkpoints

Step 4: Start ComfyUI

If you have an Nvidia GPU: Double-click run_nvidia_gpu.bat to start ComfyUI.

If you don’t: Double-click run_cpu.bat to run ComfyUI slooowly…

ComfyUI should automatically start on your browser.

Updating ComfyUI on Windows

To update ComfyUI, double-click to run the file ComfyUI_windows_portable > update > update_comfyui.bat.

Installing ComfyUI on Mac M1/M2

Installing ComfyUI on Mac is a bit more involved. You will need MacOS 12.3 or higher for MPS acceleration support.

Click on the Apple icon at the top left corner and select About this Mac to check.

The following steps install ComfyUI in a virtual environment.

Step 1: Install HomeBrew

 Homebrew is a package manager for Mac. Open the Terminal app, paste the following command, and press return.

/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"

Step 2: Install a few required packages

Open a new terminal and run the following command

brew install cmake protobuf rust [email protected] git wget

Step 3: Clone ComfyUI

Clone the ComfyUI code on your local storage by running the following in Terminal.

git clone https://github.com/comfyanonymous/ComfyUI

Step 3: Install ComfyUI

Now go into ComfyUI’s directory.

cd ComfyUI

Create a virtual environment.

python -m venv venv

Install PyTorch in the virtual environment.

./venv/bin/pip install torch torchvision torchaudio

Install the required packages for CompfyUI.

./venv/bin/pip install -r requirements.txt

Step 4. Download a stable diffusion model

You will need a model to run Stable Diffusion. Use the following link to download the v1.5 model.

Download link

Put the checkpoint model in the folder models/checkpoints.

Alternatively, run the following command to download the model.

 wget -P models/checkpoints https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.ckpt

Step 5: Start ComfyUI

Start ComfyUI by running the following command.

./venv/bin/python main.py

Updating ComfyUI on Mac

Run the following command in the comfyUI folder to update ComfyUI:

git pull

Generating an image

After starting ComfyUI for the very first time, you should see the default text-to-image workflow. It should look like this:

If this is not what you see, click Load Default on the right panel to return this default text-to-image workflow.

1. Selecting a model

First, select a Stable Diffusion Checkpoint model in the Load Checkpoint node. Click on the model name to show a list of available models.

If the node is too small, you can use the mouse wheel or pinch with two fingers on the touchpad to zoom in and out.

If clicking the model name does nothing, you may not have installed a model or configured it to use your existing models in A1111. Go back to the installation section to fix it first.

2. Enter a prompt and a negative prompt

You should see two nodes with the label CLIP Text Encode (Prompt). Enter your prompt in the top one and your negative prompt in the bottom one.

3. Generate an image

Click Queue Prompt to run the workflow. After a short wait, you should see the first image generated.

Sharing models between AUTOMATIC1111 and ComfyUI

If you have AUTOMATIC1111 Stable Diffusiion WebUI installed on your PC, you should share the model files between AUTOMATIC1111 and ComfyUI. Otherwise, you will have a very full hard drive…

Rename the file ComfyUI_windows_portable > ComfyUI > extra_model_paths.yaml.example to extra_model_paths.yaml.

Change this line:

base_path: path/to/stable-diffusion-webui/

Replace path/to/stable-diffusion-webui/ to your actual path to it. E.g.

base_path: C:\Users\USERNAME\stable-diffusion-webui

Restart ComfyUI completely. If the configuration is correct, you should see the full list of your model by clicking the ckpt_name field in the Load Checkpoint node.

You can use this technique to share LoRA, textual inversions, etc between AUTOMATIC1111 and ComfyUI.

Avatar

By Andrew

Andrew is an experienced engineer with a specialization in Machine Learning and Artificial Intelligence. He is passionate about programming, art, photography, and education. He has a Ph.D. in engineering.

66 comments

  1. I cant seem to extract this file, convert_trajectory_transformer_original_pytorch_checkpoint_to_pytorch.py no matter how many times I try. download fresh copy same thing

    1. sorted. if I want to remove Automatic111 can i just place the models in Confy Dir? if so what changes do I make?

    2. This might not be your problem, but, be mindful that Windows has a very dumb file path limit of 256 characters. Sometimes extracting files will fail if they cross this limit. In the age of node_modules and the like, it’s really annoying. The solution would be to put it closer to the root of the drive so the path isn’t too long.

  2. i have got this error when i try to generate my first image, default one. i use m1 mac.

    Error occurred when executing KSampler:

    “upsample_nearest2d_channels_last” not implemented for ‘Half’

    File “/Users/serkancolak/ComfyUI/execution.py”, line 151, in recursive_execute
    output_data, output_ui = get_output_data(obj, input_data_all)
    File “/Users/serkancolak/ComfyUI/execution.py”, line 81, in get_output_data
    return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
    File “/Users/serkancolak/ComfyUI/execution.py”, line 74, in map_node_over_list
    results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
    File “/Users/serkancolak/ComfyUI/nodes.py”, line 1369, in sample
    return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
    File “/Users/serkancolak/ComfyUI/nodes.py”, line 1339, in common_ksampler
    samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
    File “/Users/serkancolak/ComfyUI/comfy/sample.py”, line 100, in sample
    samples = sampler.sample(noise, positive_copy, negative_copy, cfg=cfg, latent_image=latent_image, start_step=start_step, last_step=last_step, force_full_denoise=force_full_denoise, denoise_mask=noise_mask, sigmas=sigmas, callback=callback, disable_pbar=disable_pbar, seed=seed)
    File “/Users/serkancolak/ComfyUI/comfy/samplers.py”, line 702, in sample
    return sample(self.model, noise, positive, negative, cfg, self.device, sampler, sigmas, self.model_options, latent_image=latent_image, denoise_mask=denoise_mask, callback=callback, disable_pbar=disable_pbar, seed=seed)
    File “/Users/serkancolak/ComfyUI/comfy/samplers.py”, line 607, in sample
    samples = sampler.sample(model_wrap, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
    File “/Users/serkancolak/ComfyUI/comfy/samplers.py”, line 545, in sample
    samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **self.extra_options)
    File “/Users/serkancolak/ComfyUI/venv/lib/python3.10/site-packages/torch/utils/_contextlib.py”, line 115, in decorate_context
    return func(*args, **kwargs)
    File “/Users/serkancolak/ComfyUI/comfy/k_diffusion/sampling.py”, line 137, in sample_euler
    denoised = model(x, sigma_hat * s_in, **extra_args)
    File “/Users/serkancolak/ComfyUI/venv/lib/python3.10/site-packages/torch/nn/modules/module.py”, line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
    File “/Users/serkancolak/ComfyUI/venv/lib/python3.10/site-packages/torch/nn/modules/module.py”, line 1520, in _call_impl
    return forward_call(*args, **kwargs)
    File “/Users/serkancolak/ComfyUI/comfy/samplers.py”, line 283, in forward
    out = self.inner_model(x, sigma, cond=cond, uncond=uncond, cond_scale=cond_scale, model_options=model_options, seed=seed)
    File “/Users/serkancolak/ComfyUI/venv/lib/python3.10/site-packages/torch/nn/modules/module.py”, line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
    File “/Users/serkancolak/ComfyUI/venv/lib/python3.10/site-packages/torch/nn/modules/module.py”, line 1520, in _call_impl
    return forward_call(*args, **kwargs)
    File “/Users/serkancolak/ComfyUI/comfy/samplers.py”, line 270, in forward
    return self.apply_model(*args, **kwargs)
    File “/Users/serkancolak/ComfyUI/comfy/samplers.py”, line 267, in apply_model
    out = sampling_function(self.inner_model, x, timestep, uncond, cond, cond_scale, model_options=model_options, seed=seed)
    File “/Users/serkancolak/ComfyUI/comfy/samplers.py”, line 244, in sampling_function
    out = calc_cond_batch(model, conds, x, timestep, model_options)
    File “/Users/serkancolak/ComfyUI/comfy/samplers.py”, line 217, in calc_cond_batch
    output = model.apply_model(input_x, timestep_, **c).chunk(batch_chunks)
    File “/Users/serkancolak/ComfyUI/comfy/model_base.py”, line 97, in apply_model
    model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds).float()
    File “/Users/serkancolak/ComfyUI/venv/lib/python3.10/site-packages/torch/nn/modules/module.py”, line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
    File “/Users/serkancolak/ComfyUI/venv/lib/python3.10/site-packages/torch/nn/modules/module.py”, line 1520, in _call_impl
    return forward_call(*args, **kwargs)
    File “/Users/serkancolak/ComfyUI/comfy/ldm/modules/diffusionmodules/openaimodel.py”, line 885, in forward
    h = forward_timestep_embed(module, h, emb, context, transformer_options, output_shape, time_context=time_context, num_video_frames=num_video_frames, image_only_indicator=image_only_indicator)
    File “/Users/serkancolak/ComfyUI/comfy/ldm/modules/diffusionmodules/openaimodel.py”, line 48, in forward_timestep_embed
    x = layer(x, output_shape=output_shape)
    File “/Users/serkancolak/ComfyUI/venv/lib/python3.10/site-packages/torch/nn/modules/module.py”, line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
    File “/Users/serkancolak/ComfyUI/venv/lib/python3.10/site-packages/torch/nn/modules/module.py”, line 1520, in _call_impl
    return forward_call(*args, **kwargs)
    File “/Users/serkancolak/ComfyUI/comfy/ldm/modules/diffusionmodules/openaimodel.py”, line 93, in forward
    x = F.interpolate(x, size=shape, mode=”nearest”)
    File “/Users/serkancolak/ComfyUI/venv/lib/python3.10/site-packages/torch/nn/functional.py”, line 4001, in interpolate
    return torch._C._nn.upsample_nearest2d(input, output_size, scale_factors)

  3. Hi there,
    I am at stage 3, I am in the correct folder I believe .
    When I enter “python -m venv venv” I get this error:
    h-MBP-sl-dnyl:ComfyUI daniel$ python -m venv venv
    -bash: python: command not found

    Do you know what have gone wrong?

  4. Hey, when I get to step 5 and try and run

    ./venv/bin/python main.py

    i get ‘No such file or directory’

    so i hit cd ComfyUI and then retype and I get a message, after a load of terminal jargon AssertionError: Torch not compiled with CUDA enabled

    Where have I gone wrong? Can’t see anybody else having this issue!

    Thanks.

  5. “C:\Users\Izaan\Downloads\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\.ci\windows_base_files>.\python_embeded\python.exe -s ComfyUI\main.py –cpu –windows-standalone-build
    The system cannot find the path specified.

    C:\Users\Izaan\Downloads\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\.ci\windows_base_files>pause
    Press any key to continue . . .”

    This issue pops up when i try to open anything. Even “run_cpu.bat” and even the “update_comfyui.bat”

  6. Thank you for everything here, this content is priceless !

    I have issues updating ComfyUI within the virtual environnement on MAC M2 (ventura).
    Error message :
    —–
    Your ComfyUI is too OUTDATED!!!

    Keywords: PhotoMaker

    Feature News:

    [PhotoMaker] Built-in nodes supporting PhotoMaker have been added to ComfyUI. (_for_testing/photomaker)

    Issue News:

    ComfyUI: Unknown[-](1900-01-01)
    Manager: V2.6
    ——
    “Failed to update ComfyUI” within comfyUI manager

  7. Help! I got it installed, and added a few models to sample. Ran the sample according to the guide above, and no matter which model I use, I get errors when executing the Ksampler:

    Error occurred when executing KSampler:

    CUDA error: invalid argument
    CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
    For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
    Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.

    File “C:\Users\troy\Downloads\ComfyUI_windows_portable\ComfyUI\execution.py”, line 152, in recursive_execute
    output_data, output_ui = get_output_data(obj, input_data_all)
    File “C:\Users\troy\Downloads\ComfyUI_windows_portable\ComfyUI\execution.py”, line 82, in get_output_data
    return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
    File “C:\Users\troy\Downloads\ComfyUI_windows_portable\ComfyUI\execution.py”, line 75, in map_node_over_list
    results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
    File “C:\Users\troy\Downloads\ComfyUI_windows_portable\ComfyUI\nodes.py”, line 1236, in sample
    return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
    File “C:\Users\troy\Downloads\ComfyUI_windows_portable\ComfyUI\nodes.py”, line 1206, in common_ksampler
    samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
    File “C:\Users\troy\Downloads\ComfyUI_windows_portable\ComfyUI\comfy\sample.py”, line 97, in sample
    samples = sampler.sample(noise, positive_copy, negative_copy, cfg=cfg, latent_image=latent_image, start_step=start_step, last_step=last_step, force_full_denoise=force_full_denoise, denoise_mask=noise_mask, sigmas=sigmas, callback=callback, disable_pbar=disable_pbar, seed=seed)
    File “C:\Users\troy\Downloads\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py”, line 785, in sample
    return sample(self.model, noise, positive, negative, cfg, self.device, sampler(), sigmas, self.model_options, latent_image=latent_image, denoise_mask=denoise_mask, callback=callback, disable_pbar=disable_pbar, seed=seed)
    File “C:\Users\troy\Downloads\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py”, line 690, in sample
    samples = sampler.sample(model_wrap, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
    File “C:\Users\troy\Downloads\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py”, line 630, in sample
    samples = getattr(k_diffusion_sampling, “sample_{}”.format(sampler_name))(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **extra_options)
    File “C:\Users\troy\Downloads\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\utils\_contextlib.py”, line 115, in decorate_context
    return func(*args, **kwargs)
    File “C:\Users\troy\Downloads\ComfyUI_windows_portable\ComfyUI\comfy\k_diffusion\sampling.py”, line 137, in sample_euler
    denoised = model(x, sigma_hat * s_in, **extra_args)
    File “C:\Users\troy\Downloads\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\nn\modules\module.py”, line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
    File “C:\Users\troy\Downloads\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\nn\modules\module.py”, line 1527, in _call_impl
    return forward_call(*args, **kwargs)
    File “C:\Users\troy\Downloads\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py”, line 323, in forward
    out = self.inner_model(x, sigma, cond=cond, uncond=uncond, cond_scale=cond_scale, cond_concat=cond_concat, model_options=model_options, seed=seed)
    File “C:\Users\troy\Downloads\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\nn\modules\module.py”, line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
    File “C:\Users\troy\Downloads\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\nn\modules\module.py”, line 1527, in _call_impl
    return forward_call(*args, **kwargs)
    File “C:\Users\troy\Downloads\ComfyUI_windows_portable\ComfyUI\comfy\k_diffusion\external.py”, line 125, in forward
    eps = self.get_eps(input * c_in, self.sigma_to_t(sigma), **kwargs)
    File “C:\Users\troy\Downloads\ComfyUI_windows_portable\ComfyUI\comfy\k_diffusion\external.py”, line 151, in get_eps
    return self.inner_model.apply_model(*args, **kwargs)
    File “C:\Users\troy\Downloads\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py”, line 311, in apply_model
    out = sampling_function(self.inner_model.apply_model, x, timestep, uncond, cond, cond_scale, cond_concat, model_options=model_options, seed=seed)
    File “C:\Users\troy\Downloads\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py”, line 285, in sampling_function
    max_total_area = model_management.maximum_batch_area()
    File “C:\Users\troy\Downloads\ComfyUI_windows_portable\ComfyUI\comfy\model_management.py”, line 579, in maximum_batch_area
    memory_free = get_free_memory() / (1024 * 1024)
    File “C:\Users\troy\Downloads\ComfyUI_windows_portable\ComfyUI\comfy\model_management.py”, line 555, in get_free_memory
    stats = torch.cuda.memory_stats(dev)
    File “C:\Users\troy\Downloads\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\cuda\memory.py”, line 256, in memory_stats
    stats = memory_stats_as_nested_dict(device=device)
    File “C:\Users\troy\Downloads\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\cuda\memory.py”, line 268, in memory_stats_as_nested_dict
    return torch._C._cuda_memoryStats(device)

    1. what gpu do you have? It seems to have serious issue using the gpu. You can
      – reboot
      – reinstall and run the default workflow without installing any custom nodes.

  8. On M2 Macbook Pro, I followed all the directions above. When I got to Create a virtual environment. python -m venv venv,
    I got the error “Command Python not found.”
    Searched my hard drive, and Python doesn’t exist.
    How do I install Python? Was it supposed to have been installed by the first few commands?

        1. FYI: as long as you do not try and us ComfyUI Manager you are OK. If you do find that you want to use Manager then you have to perform all the pip installs over again using the embedded python that comes with ComfyUI.
          The execution path for the embedded python on a windows installation is ComfyUI_windows_portable\python_embeded

          to execute the pip command use:

          ComfyUI_windows_portable\python_embeded\python -m pip (your pip command goes here)

          for Mac and Linux the backslash is replaced with a forward slash.

  9. Hi, after clicking “Queue Prompt” in ComfyUI I get error message as bellow. I haven’t found any solution so far. Has anybody an idea what’s wrong? MacBook Air M1, OS Sonoma 14.1.1.

    Error occurred when executing CheckpointLoaderSimple:
    the STRING opcode argument must be quoted
    File “/Users/tomaszdajczak/ComfyUI/execution.py”, line 154, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File “/Users/tomaszdajczak/ComfyUI/execution.py”, line 84, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) File “/Users/tomaszdajczak/ComfyUI/execution.py”, line 77, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) File “/Users/tomaszdajczak/ComfyUI/nodes.py”, line 476, in load_checkpoint out = comfy.sd.load_checkpoint_guess_config(ckpt_path, output_vae=True, output_clip=True, embedding_directory=folder_paths.get_folder_paths(“embeddings”)) File “/Users/tomaszdajczak/ComfyUI/comfy/sd.py”, line 434, in load_checkpoint_guess_config sd = comfy.utils.load_torch_file(ckpt_path) File “/Users/tomaszdajczak/ComfyUI/comfy/utils.py”, line 22, in load_torch_file pl_sd = torch.load(ckpt, map_location=device, pickle_module=comfy.checkpoint_pickle) File “/Users/tomaszdajczak/ComfyUI/venv/lib/python3.9/site-packages/torch/serialization.py”, line 1028, in load return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args) File “/Users/tomaszdajczak/ComfyUI/venv/lib/python3.9/site-packages/torch/serialization.py”, line 1246, in _legacy_load magic_number = pickle_module.load(f, **pickle_load_args)

  10. when running ComfyUI (python3 main.py –cpu, as mine iMac 27′ Late 2013), I got message:

    Total VRAM 24576 MB, total RAM 24576 MB

    Set vram state to: DISABLED

    Device: cpu

    VAE dtype: torch.float32

    Using split optimization for cross attention

    Starting server

    where I see other is his video says: Set vram state to: SHARED.

    is there a possibility to set mine to SHARED ? Any help is appreciated.

  11. I was given a workflow I want to try out. Shouldn’t I be able to simple drag/drop it on top of whatever existing workflow to use it? Not working for me. I still get the existing workflow every time.

    1. This should work with the latest comfyui. You can also use the load button. If it is a png file, read the metadata to confirm the workflow json is written there.

  12. I’ve installed comfyUI per your instructions, but it seems it’s not able to access my Nvidia GPU. My laptop has an RTX 4060. Would that be able to be used?

    C:\Users\anujs\AI\stable-diffusion-comfyui\ComfyUI_windows_portable>.\python_embeded\python.exe -s ComfyUI\main.py –windows-standalone-build
    Traceback (most recent call last):
    File “C:\Users\anujs\AI\stable-diffusion-comfyui\ComfyUI_windows_portable\ComfyUI\main.py”, line 72, in
    import execution
    File “C:\Users\anujs\AI\stable-diffusion-comfyui\ComfyUI_windows_portable\ComfyUI\execution.py”, line 11, in
    import nodes
    File “C:\Users\anujs\AI\stable-diffusion-comfyui\ComfyUI_windows_portable\ComfyUI\nodes.py”, line 20, in
    import comfy.diffusers_load
    File “C:\Users\anujs\AI\stable-diffusion-comfyui\ComfyUI_windows_portable\ComfyUI\comfy\diffusers_load.py”, line 4, in
    import comfy.sd
    File “C:\Users\anujs\AI\stable-diffusion-comfyui\ComfyUI_windows_portable\ComfyUI\comfy\sd.py”, line 5, in
    from comfy import model_management
    File “C:\Users\anujs\AI\stable-diffusion-comfyui\ComfyUI_windows_portable\ComfyUI\comfy\model_management.py”, line 114, in
    total_vram = get_total_memory(get_torch_device()) / (1024 * 1024)
    File “C:\Users\anujs\AI\stable-diffusion-comfyui\ComfyUI_windows_portable\ComfyUI\comfy\model_management.py”, line 83, in get_torch_device
    return torch.device(torch.cuda.current_device())
    File “C:\Users\anujs\AI\stable-diffusion-comfyui\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\cuda\__init__.py”, line 769, in current_device
    _lazy_init()
    File “C:\Users\anujs\AI\stable-diffusion-comfyui\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\cuda\__init__.py”, line 298, in _lazy_init
    torch._C._cuda_init()
    RuntimeError: No CUDA GPUs are available

    C:\Users\anujs\AI\stable-diffusion-comfyui\ComfyUI_windows_portable>pause

    1. It works out of the box in my case. You can try cloning the repro and installing manually, or get help from the comfyui repro.

    2. 1. make sure that you have already installed CUDA (from NVIDIA)
      2. this version is compatiblle with CUDA version 11.8

      The latest version of CUDA when I wrote this is 12.1
      but I prefer like this version. because I don’t want to update my CUDA version
      However Thanks to Admin.

  13. I downloaded the zip file and began extracting it, but I keep getting error messages during extraction that say, “Error 0x80070003: The system cannot find the path specified.” followed by things like “test_current_flow_betweenness_centrality_subset… Type: PYC File”, “_data_sparstity_utils.cpython-311.pyc … Type: PYC File”, _fake_quantize_per_tensor_affine_cachemask_tens… Type: H File”… and many more. How do I help ensure the system can find these specified paths?

  14. Mac User here:

    When I’m running the “python -m venv venv” command , I’m getting this error “zsh: command not found: python”.

    What am I doing wrong? I have followed every other step before it with no hassle.

  15. hey, I downloaded everything, I seems fine, but with when I generate it just happen to appear only a colourful noise picture? Nothing concrete visible! do I do anything wrong?

    1. Quite a few people have reported this already. Unfortunately, I am not able to reproduce. Can you or anyone post a screenshot with all parameters visible? Messages on the terminal app would also be helpful.

  16. I’m a noob dork so the sharing code thing took me a hot few minutes to realize you meant to open it up in notepad and change the line in there but I got it! Thanks as always for your super awesome instructions, you make me feel like I know what I’m doing lol

    1. Hi, that step is for installing requiring packages that the requirements.txt file does not install, like python itself.

      The requirements.txt file is in the comfyUI directory.

  17. Hi I am installing ComfyUI on mac mini m2, when I input the command “/venv/bin/python main.py” in macOS Terminal, en error message appears saying file not find. How to resolved it? Many thanks.

        1. looks like you don’t have the python file. go to venv > bin folder and make sure it is there. it is created with the python -m venv venv command.

          1. Same problem here. I’ve checked bin folder, there is python, python3 and python3.10 file there.

Leave a comment

Your email address will not be published. Required fields are marked *