序言

由于stable diffusion web ui无法做到对流程进行控制，只是点击个生成按钮后，一切都交给AI来处理。但是用于生产生活是需要精细化对各个流程都要进行控制的。

故也就有个今天的猪脚：Comfyui

步骤

1. 下载comfyui项目
2. 配置大模型和vae
3. 下载依赖组件
4. 启动

下载comfyUI

官网地址：https://github.com/comfyanonymous/ComfyUI

将项目下载到自己喜欢的目录下，下面是我的：

yutao@yutao MINGW64 /e/openai/project$ git clone https://github.com/comfyanonymous/ComfyUI.git

配置大模型和vae

1. 在ComfyUI/models/checkpoints中放大模型文件
2. 在ComfyUI/models/vae中放vae文件。

但是，我们学stable diffusion基本都是从stable diffusion webui开始的，所以我们其实不需要再额外的下载，checkpoint和vae，而是共用他们。

ComfyUI的作者提供了配置方法：

1. 修改extra_model_paths.yaml.example文件重命名为：extra_model_paths.yaml
2. 打开文件，将里面的base_path进行修改：
   以下是我的stable-diffusion-webui的路径

a111:    base_path: E:/openai/project/stable-diffusion-webui

保存退出。

下载依赖组件

在ComfyUI中调出命令行(将文件夹路径上敲cmd，回车即可)中执行：

E:/openai/project/ComfyUI>pip install -r requirements.txt

就会开始下载所需的依赖组件。

启动

命令：python main.py

E:/openai/project/ComfyUI>python main.py

浏览器访问地址：http://127.0.0.1:8188

最左边，因为我之前玩stable diffusion时候已经下载好了guofeng3大模型。所以load checkpoint 里面我显示的是guofeng3.

大模型，我下载的是guofeng3。
放到models/checkpoints文件夹里，例如：E:/openai/project/ComfyUI/models/checkpoints。

生成图片

因为默认参数就可以生成一个花瓶，点击右上角的Queue Prompt。

但是我的电脑总是不是那么顺利。

详细描述文章：【ComfyUI】RuntimeError: CUDA error: operation not supported

报了如下错误：

got promptmodel_type EPSadm 0making attention of type 'vanilla-pytorch' with 512 in_channelsWorking with z of shape (1, 4, 32, 32) = 4096 dimensions.making attention of type 'vanilla-pytorch' with 512 in_channelsmissing {'cond_stage_model.text_projection', 'cond_stage_model.logit_scale'}left over keys: dict_keys(['cond_stage_model.transformer.text_model.embeddings.position_ids', 'model_ema.decay', 'model_ema.num_updates'])loading newloading newloading in lowvram mode 1842.6899042129517!!! Exception during processing !!!Traceback (most recent call last):  File "E:/openai/project/ComfyUI/execution.py", line 152, in recursive_execute    output_data, output_ui = get_output_data(obj, input_data_all)                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^  File "E:/openai/project/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 "E:/openai/project/ComfyUI/execution.py", line 75, in map_node_over_list    results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^  File "E:/openai/project/ComfyUI/nodes.py", line 1236, in sample    return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^  File "E:/openai/project/ComfyUI/nodes.py", line 1206, in common_ksampler    samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^  File "E:/openai/project/ComfyUI/comfy/sample.py", line 81, in sample    comfy.model_management.load_models_gpu([model] + models, comfy.model_management.batch_area_memory(noise.shape[0] * noise.shape[2] * noise.shape[3]) + inference_memory)  File "E:/openai/project/ComfyUI/comfy/model_management.py", line 394, in load_models_gpu    cur_loaded_model = loaded_model.model_load(lowvram_model_memory)                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^  File "E:/openai/project/ComfyUI/comfy/model_management.py", line 288, in model_load    accelerate.dispatch_model(self.real_model, device_map=device_map, main_device=self.device)  File "D:/Program Files/Python/Lib/site-packages/accelerate/big_modeling.py", line 391, in dispatch_model    attach_align_device_hook_on_blocks(  File "D:/Program Files/Python/Lib/site-packages/accelerate/hooks.py", line 532, in attach_align_device_hook_on_blocks    add_hook_to_module(module, hook)  File "D:/Program Files/Python/Lib/site-packages/accelerate/hooks.py", line 155, in add_hook_to_module    module = hook.init_hook(module)             ^^^^^^^^^^^^^^^^^^^^^^  File "D:/Program Files/Python/Lib/site-packages/accelerate/hooks.py", line 253, in init_hook    set_module_tensor_to_device(module, name, self.execution_device)  File "D:/Program Files/Python/Lib/site-packages/accelerate/utils/modeling.py", line 307, in set_module_tensor_to_device    new_value = old_value.to(device)                ^^^^^^^^^^^^^^^^^^^^RuntimeError: CUDA error: operation not supportedCUDA 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.

其实就是说，我当前电脑的GPU或硬件，并不支持当前CUDA中的某些操作。

解决办法

官方提供了两种解决策略。

方式一：黑名单策略

加完后，再重启。发现还是不行。

方式二：启动时添加–disable-cuda-malloc

# 注意--disable-cuda-mallocE:/openai/project/ComfyUI>python main.py --disable-cuda-malloc

最后，通过方式二，得以解决。

参考地址：

https://github.com/comfyanonymous/ComfyUI#manual-install-windows-linux

Stable Diffusion ComfyUI 入门感受