TypeError: StableDiffusionXLReferencePipeline.__call__.<locals>.hacked_DownBlock2D_forward() got an unexpected keyword argument 'scale' #5028
Description
Describe the bug
TypeError Traceback (most recent call last)
Cell In[1], line 18
16 pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
17 seed = torch.manual_seed(10240)
---> 18 result_img = pipe(ref_image=style_image,
19 prompt="1girl",
20 generator=seed,
21 num_inference_steps=20,
22 reference_attn=True,
23 reference_adain=True).images[0]
24 result_img
File /usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py:115, in context_decorator..decorate_context(*args, **kwargs)
112 @functools.wraps(func)
113 def decorate_context(*args, **kwargs):
114 with ctx_factory():
--> 115 return func(*args, **kwargs)
File ~/.cache/huggingface/modules/diffusers_modules/git/stable_diffusion_xl_reference.py:738, in StableDiffusionXLReferencePipeline.call(self, prompt, prompt_2, ref_image, 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, attention_auto_machine_weight, gn_auto_machine_weight, style_fidelity, reference_attn, reference_adain)
734 ref_xt = self.scheduler.scale_model_input(ref_xt, t)
736 MODE = "write"
--> 738 self.unet(
739 ref_xt,
740 t,
741 encoder_hidden_states=prompt_embeds,
742 cross_attention_kwargs=cross_attention_kwargs,
743 added_cond_kwargs=added_cond_kwargs,
744 return_dict=False,
745 )
747 # predict the noise residual
748 MODE = "read"
File /usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py:1501, in Module._call_impl(self, *args, **kwargs)
1496 # If we don't have any hooks, we want to skip the rest of the logic in
1497 # this function, and just call forward.
1498 if not (self._backward_hooks or self._backward_pre_hooks or self._forward_hooks or self._forward_pre_hooks
1499 or _global_backward_pre_hooks or _global_backward_hooks
1500 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1501 return forward_call(*args, **kwargs)
1502 # Do not call functions when jit is used
1503 full_backward_hooks, non_full_backward_hooks = [], []
File /usr/local/lib/python3.10/dist-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 /usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py:1501, in Module._call_impl(self, *args, **kwargs)
1496 # If we don't have any hooks, we want to skip the rest of the logic in
1497 # this function, and just call forward.
1498 if not (self._backward_hooks or self._backward_pre_hooks or self._forward_hooks or self._forward_pre_hooks
1499 or _global_backward_pre_hooks or _global_backward_hooks
1500 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1501 return forward_call(*args, **kwargs)
1502 # Do not call functions when jit is used
1503 full_backward_hooks, non_full_backward_hooks = [], []
TypeError: StableDiffusionXLReferencePipeline.call..hacked_DownBlock2D_forward() got an unexpected keyword argument 'scale'
Reproduction
import torch
from PIL import Image
from diffusers.utils import load_image
from diffusers import DiffusionPipeline, AutoencoderTiny
from diffusers.schedulers import UniPCMultistepScheduler
style_image = load_image("imgs/沙滩动漫.png").convert("RGB")
pipe = DiffusionPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-base-1.0",
custom_pipeline="stable_diffusion_xl_reference",
torch_dtype=torch.float16,
use_safetensors=True,
variant="fp16", safety_checker=None, local_files_only=True,).to('cuda:0')
pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
seed = torch.manual_seed(10240)
result_img = pipe(ref_image=style_image,
prompt="1girl",
generator=seed,
num_inference_steps=20,
reference_attn=True,
reference_adain=True).images[0]
result_img
Logs
No response
System Info
diffusersversion: 0.21.0- Platform: Linux-5.4.0-155-generic-x86_64-with-glibc2.31
- Python version: 3.10.12
- PyTorch version (GPU?): 2.0.1+cu117 (True)
- Huggingface_hub version: 0.16.4
- Transformers version: 4.33.1
- Accelerate version: 0.21.0
- xFormers version: 0.0.20
- Using GPU in script?:
- Using distributed or parallel set-up in script?:
Who can help?
No response