【高端操作】一张图扩增全角度表情光影素材

seraisimmortal

一周速成SD在WEB UI跑通了InstanID批处理pipeline，只能说DFL是什么东西，真不熟

youngcoTop

这个好啊，不用费心费力找多角度素材了。就是不知道人脸一致性有多好

whl716694

等一个傻瓜安装包

w102602

为啥在安装列表里能看到已安装了“AIGODLIKE-ComfyUI"的，怎么进设置里面就找不到翻译呢····卸载又重新安装了两次，还是这样，难道不能用翻译了么就？？？

网络家园

好像很厉害的样子啊，感谢大佬分享

国际狄拉克

ktis321 发表于 2024-3-29 14:35
Error occurred when executing PreviewImage:

'NoneType' object is not subscriptable

就是批量路径的问题

huangjing00238

老大，报错Error occurred when executing KSampler: 'UNetModel' object has no attribute 'default_image_only_indicator'这个怎么解决呢？

寒星玺

大神求助，我这问题请问怎么解决
Error occurred when executing CheckpointLoaderSimple:

Allocation on device 0 would exceed allowed memory. (out of memory)
Currently allocated : 3.12 GiB
Requested : 28.12 MiB
Device limit : 12.00 GiB
Free (according to CUDA): 7.85 GiB
PyTorch limit (set by user-supplied memory fraction)
: 17179869184.00 GiB

File "E:\AI\comfyUI\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\AI\comfyUI\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 "E:\AI\comfyUI\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\AI\comfyUI\ComfyUI\nodes.py", line 541, 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 "E:\AI\comfyUI\ComfyUI\comfy\sd.py", line 522, in load_checkpoint_guess_config
model = model_config.get_model(sd, "model.diffusion_model.", device=inital_load_device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\AI\comfyUI\ComfyUI\comfy\supported_models.py", line 188, in get_model
out = model_base.SDXL(self, model_type=self.model_type(state_dict, prefix), device=device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\AI\comfyUI\ComfyUI\comfy\model_base.py", line 313, in __init__
super().__init__(model_config, model_type, device=device)
File "E:\AI\comfyUI\ComfyUI\comfy\model_base.py", line 62, in __init__
self.diffusion_model = unet_model(**unet_config, device=device, operations=operations)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\AI\comfyUI\ComfyUI\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 742, in __init__
get_resblock(
File "E:\AI\comfyUI\ComfyUI\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 598, in get_resblock
return ResBlock(
^^^^^^^^^
File "E:\AI\comfyUI\ComfyUI\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 210, in __init__
operations.conv_nd(dims, self.out_channels, self.out_channels, kernel_size, padding=padding, dtype=dtype, device=device)
File "E:\AI\comfyUI\ComfyUI\comfy\ops.py", line 139, in conv_nd
return s.Conv2d(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\AI\comfyUI\python_embeded\Lib\site-packages\torch\nn\modules\conv.py", line 447, in __init__
super().__init__(
File "E:\AI\comfyUI\python_embeded\Lib\site-packages\torch\nn\modules\conv.py", line 134, in __init__
self.weight = Parameter(torch.empty(
^^^^^^^^^^^^

Close

滚石

寒星玺 发表于 2024-4-15 21:34
大神求助，我这问题请问怎么解决
Error occurred when executing CheckpointLoaderSimple:

显存不够

ive瑛

天光脑震荡 发表于 2024-3-30 21:08
告诉你一个一步到位的方法：花点钱租滚石的云主机，把里面的ComfyUI整个文件一共50多G复制出来或者传到网 ...

兄弟上传的有网盘链接吗？有的话可以麻烦你发一份吗？