【高级教程】太变态了,FLUX实现超自然换衣服换物品

173593968

需要什么配置才能运行！

liuxu0203

膜拜大佬

tdasts

To see the GUI go to: http://127.0.0.1:8188
got prompt
Using split attention in VAE
Using split attention in VAE
VAE load device: cpu, offload device: cpu, dtype: torch.float32
Requested to load FluxClipModel_
loaded completely 9.5367431640625e+25 4777.53759765625 True
CLIP/text encoder model load device: cpu, offload device: cpu, current: cpu, dtype: torch.float16
clip missing: ['text_projection.weight']
Requested to load CLIPVisionModelProjection
loaded completely 9.5367431640625e+25 787.7150573730469 True
怎么报错了哎？是版本太新了还是啥？  clip missing: ['text_projection.weight']

28337

感谢                        

a18367774619

Sizes of tensors must match except in dimension 1. Expected size 4096 but got size 768 for tensor number 1 in the list.

这个报错是啥原因大佬们

lknet

搞定了，太牛了

28337

感谢分享                     

statipue

谢谢大佬

syluxin

!!! Exception during processing!!! Error(s) in loading state_dict for Flux:
        size mismatch for img_in.weight: copying a param with shape torch.Size([3072, 384]) from checkpoint, the shape in current model is torch.Size([3072, 64]).
Traceback (most recent call last):
  File "D:\comfyui_old\ComfyUI\execution.py", line 152, in recursive_execute
    output_data, output_ui = get_output_data(obj, input_data_all)
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\comfyui_old\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 "D:\comfyui_old\ComfyUI\execution.py", line 75, in map_node_over_list
    results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\comfyui_old\ComfyUI\nodes.py", line 836, in load_unet
    model = comfy.sd.load_unet(unet_path, dtype=dtype)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\comfyui_old\ComfyUI\comfy\sd.py", line 627, in load_unet
    model = load_unet_state_dict(sd, dtype=dtype)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\comfyui_old\ComfyUI\comfy\sd.py", line 619, in load_unet_state_dict
    model.load_model_weights(new_sd, "")
  File "D:\comfyui_old\ComfyUI\comfy\model_base.py", line 204, in load_model_weights
    m, u = self.diffusion_model.load_state_dict(to_load, strict=False)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\comfyui_old\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 2189, in load_state_dict
    raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for Flux:
        size mismatch for img_in.weight: copying a param with shape torch.Size([3072, 384]) from checkpoint, the shape in current model is torch.Size([3072, 64]).

Prompt executed in 78.49 seconds

报故了，哪位大佬能解惑一下

2280470710

好强，能动起来吗