ComfyUI-Kolors-MZ
ComfyUI-Kolors-MZ copied to clipboard
Kolors的ComfyUI原生采样器实现(Kolors ComfyUI Native Sampler Implementation)
Pytorch 升级到l了 2.41 会是这个原因吗 [新建 文本文档.txt](https://github.com/user-attachments/files/17155542/default.txt)
Error occurred when executing MZ_KolorsUNETLoaderV2: ERROR: Could not detect model type of: C:\Software\ComfyUI_FK_202406\ComfyUI\models\unet\Kolors\diffusion_pytorch_model.fp16.safetensors unet模型是在https://huggingface.co/Kwai-Kolors/Kolors/blob/main/unet/diffusion_pytorch_model.fp16.safetensors这里下载的 有大佬知道报错原因吗
does this node support kolors lora or not ? as you see, the glm3 output a chatglm3 model, but the lora loader want a clip. so there is no text...
We need a GGUF loader for the ChatGLM3. https://huggingface.co/mradermacher/chatglm3-6b-GGUF/tree/main
我的comfyui已经变更了extra_model_paths.yaml,内容如下: base_path: E:/ComfyUI-aki-v1.3/ checkpoints: E:/comfyui_models/checkpoints/ clip: E:/comfyui_models/clip/ clip_vision: E:/comfyui_models/clip_vision/ configs: E:/comfyui_models/configs/ controlnet: E:/comfyui_models/controlnet/ embeddings: E:/comfyui_models/embeddings/ loras: E:/comfyui_models/loras/ upscale_models: E:/comfyui_models/upscale_models/ vae: E:/comfyui_models/vae/ 我的模型是放在这里的。 在我的示例工作流里面找不到模型。 如下图:  

What comes up when you are using the official ControlNet model: Traceback (most recent call last): File "D:\ComfyUI\execution.py", line 152, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\execution.py",...
clip-vit-large-patch14-336/pytorch_model.bin 老师给的存放目录是clip_vision,这里有错,大家注意,是放在clip目录下
内存泄漏
 走到这个节点内存泄漏了
cpm_kernels库已经正确安装,但还是会出下如下错误,求解! Load TEXT_ENCODER... !!! Exception during processing !!! Library cudart is not initialized Traceback (most recent call last): File "D:\ComfyUI-aki-v1.2\execution.py", line 317, in execute output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all,...