How can I fix the error "LoRAModule.forward() takes 2 positional arguments but 3 were given"

[xdfeng07]

0%| | 0/50 [00:00<?, ?it/s]

TypeError Traceback (most recent call last)
Cell In[6], line 54
52 for scale in scales:
53 generator = torch.manual_seed(seed)
---> 54 images = pipe(prompt, num_images_per_prompt=1, num_inference_steps=50, generator=generator, network=network, start_noise=start_noise, scale=scale, unet=unet).images[0]
55 image_list.append(images)
56 del unet, network, pipe

File ~/miniconda3/envs/sd/lib/python3.10/site-packages/torch/autograd/grad_mode.py:27, in _DecoratorContextManager.call..decorate_context(*args, **kwargs)
24 @functools.wraps(func)
25 def decorate_context(*args, **kwargs):
26 with self.clone():
---> 27 return func(*args, **kwargs)

Cell In[2], line 313, in call(self, prompt, prompt_2, height, width, num_inference_steps, denoising_end, guidance_scale, negative_prompt, negative_prompt_2, num_images_per_prompt, eta, generator, latents, prompt_embeds, negative_prompt_embeds, pooled_prompt_embeds, negative_pooled_prompt_embeds, output_type, return_dict, callback, callback_steps, cross_attention_kwargs, guidance_rescale, original_size, crops_coords_top_left, target_size, negative_original_size, negative_crops_coords_top_left, negative_target_size, network, start_noise, scale, unet)
311 added_cond_kwargs = {"text_embeds": add_text_embeds, "time_ids": add_time_ids}
312 with network:
--> 313 noise_pred = unet(
314 latent_model_input,
315 t,
316 encoder_hidden_states=prompt_embeds,
317 cross_attention_kwargs=cross_attention_kwargs,
318 added_cond_kwargs=added_cond_kwargs,
319 return_dict=False,
320 )[0]
322 # perform guidance
323 if do_classifier_free_guidance:

File ~/miniconda3/envs/sd/lib/python3.10/site-packages/torch/nn/modules/module.py:1194, in Module._call_impl(self, *input, **kwargs)
1190 # If we don't have any hooks, we want to skip the rest of the logic in
1191 # this function, and just call forward.
1192 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
1193 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1194 return forward_call(*input, **kwargs)
1195 # Do not call functions when jit is used
1196 full_backward_hooks, non_full_backward_hooks = [], []

File ~/miniconda3/envs/sd/lib/python3.10/site-packages/diffusers/models/unet_2d_condition.py:966, in UNet2DConditionModel.forward(self, sample, timestep, encoder_hidden_states, class_labels, timestep_cond, attention_mask, cross_attention_kwargs, added_cond_kwargs, down_block_additional_residuals, mid_block_additional_residual, encoder_attention_mask, return_dict)
956 sample, res_samples = downsample_block(
957 hidden_states=sample,
958 temb=emb,
(...)
963 **additional_residuals,
964 )
965 else:
--> 966 sample, res_samples = downsample_block(hidden_states=sample, temb=emb, scale=lora_scale)
968 if is_adapter and len(down_block_additional_residuals) > 0:
969 sample += down_block_additional_residuals.pop(0)

File ~/miniconda3/envs/sd/lib/python3.10/site-packages/torch/nn/modules/module.py:1194, in Module._call_impl(self, *input, **kwargs)
1190 # If we don't have any hooks, we want to skip the rest of the logic in
1191 # this function, and just call forward.
1192 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
1193 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1194 return forward_call(*input, **kwargs)
1195 # Do not call functions when jit is used
1196 full_backward_hooks, non_full_backward_hooks = [], []

File ~/miniconda3/envs/sd/lib/python3.10/site-packages/diffusers/models/unet_2d_blocks.py:1183, in DownBlock2D.forward(self, hidden_states, temb, scale)
1179 hidden_states = torch.utils.checkpoint.checkpoint(
1180 create_custom_forward(resnet), hidden_states, temb
1181 )
1182 else:
-> 1183 hidden_states = resnet(hidden_states, temb, scale=scale)
1185 output_states = output_states + (hidden_states,)
1187 if self.downsamplers is not None:

File ~/miniconda3/envs/sd/lib/python3.10/site-packages/torch/nn/modules/module.py:1194, in Module._call_impl(self, *input, **kwargs)
1190 # If we don't have any hooks, we want to skip the rest of the logic in
1191 # this function, and just call forward.
1192 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
1193 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1194 return forward_call(*input, **kwargs)
1195 # Do not call functions when jit is used
1196 full_backward_hooks, non_full_backward_hooks = [], []

File ~/miniconda3/envs/sd/lib/python3.10/site-packages/diffusers/models/resnet.py:637, in ResnetBlock2D.forward(self, input_tensor, temb, scale)
626 input_tensor = (
627 self.downsample(input_tensor, scale=scale)
628 if isinstance(self.downsample, Downsample2D)
629 else self.downsample(input_tensor)
630 )
631 hidden_states = (
632 self.downsample(hidden_states, scale=scale)
633 if isinstance(self.downsample, Downsample2D)
634 else self.downsample(hidden_states)
635 )
--> 637 hidden_states = self.conv1(hidden_states, scale)
639 if self.time_emb_proj is not None:
640 if not self.skip_time_act:

File ~/miniconda3/envs/sd/lib/python3.10/site-packages/torch/nn/modules/module.py:1194, in Module._call_impl(self, *input, **kwargs)
1190 # If we don't have any hooks, we want to skip the rest of the logic in
1191 # this function, and just call forward.
1192 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
1193 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1194 return forward_call(*input, **kwargs)
1195 # Do not call functions when jit is used
1196 full_backward_hooks, non_full_backward_hooks = [], []

TypeError: LoRAModule.forward() takes 2 positional arguments but 3 were given

[rohitgandikota]

did you use the installation guide we provided in README.md ? I suspect it could be some diffusers version issue?

[manzonif]

Yes, with diffusers v0.24.0 I've got that error.

I finally got it working on Windows:

python -m pip install bitsandbytes==0.41.0 --prefer-binary --extra-index-url=https://jllllll.github.io/bitsandbytes-windows-webui

pip install torch==2.0.1 torchvision==0.15.2 --index-url https://download.pytorch.org/whl/cu118

pip install -r requirements.txt

Then I tried to run train_lora_XL with a custom checkpoint from Civitai, (newrealityxl_v11.safetensors")
And it comes out with the error: Unexpected key(s) in state_dict: "text_model.embeddings.position_ids"
I found this issue on diffusers's repository
So I installed:

 pip install accelerate
 pip install omegaconf

And seems to work fine.

[rohitgandikota]

closing this issue - feel free to reopen if the issue persists

[sdbds]

https://github.com/sdbds/sliders-for-windows/tree/qinglong
windows version for autoinstall and run with powershell scripts.

[lixida123]

是的，使用扩散器 v0.24.0 我遇到了这个错误。

我终于让它在 Windows 上运行了：

python -m pip install bitsandbytes==0.41.0 --prefer-binary --extra-index-url=https://jllllll.github.io/bitsandbytes-windows-webui

pip install torch==2.0.1 torchvision==0.15.2 --index-url https://download.pytorch.org/whl/cu118

pip install -r requirements.txt

然后我尝试使用Civitai的自定义检查点（newrealityxl_v11.safetensors）运行train_lora_XL，并出现错误： state_dict中意外的键：“text_model.embeddings.position_ids” 我在扩散器的存储库中发现了这个问题 所以我安装了：

 pip install accelerate
 pip install omegaconf

而且似乎工作正常。
Thank you for your answer, I have been reporting errors when calling the Sd local model for a long time, I run your: pip install accelerate in git
pip install omegaconf successfully solves the problem of calling the local model