Description
Describe the bug
I fine-tuned Stable Diffusion using the LoRA method on my own dataset. However, during the inference process, I encountered the error: TypeError: init() got an unexpected keyword argument 'lora_bias'.
Reproduction
CUDA_VISIBLE_DEVICES=1 accelerate launch train_text_to_image_lora.py
--mixed_precision="fp16"
--pretrained_model_name_or_path=$MODEL_NAME
--train_data_dir=$TRAIN_DATA_DIR --caption_column="additional_feature"
--resolution=512 --random_flip
--train_batch_size=1
--num_train_epochs=100 --checkpointing_steps=5000
--learning_rate=1e-04 --lr_scheduler="constant" --lr_warmup_steps=0
--seed=42
--output_dir=$OUTPUT_DIR
--validation_prompt=None
export MODEL_PATH="/home/new_project/prohibit/model"
export SAVE_PATH="./data_generated/" \
CUDA_VISIBLE_DEVICES=0 python generate.py --model_path $MODEL_PATH --save_path $SAVE_PATH
generate.py:
model_path = args.model_path
pipe = StableDiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", torch_dtype=torch.float16)
pipe.safety_checker = None
pipe.requires_safety_checker = False
print("加载参数")
pipe.unet.load_attn_procs(model_path)
pipe.to("cuda")
normal_image = pipe("a drawing of a cartoon character laying on the ground", num_inference_steps=30, guidance_scale=7.5).images[0]
Logs
/home/miniconda3/envs/new/lib/python3.9/site-packages/diffusers/loaders/unet.py:215: FutureWarning: `load_attn_procs` is deprecated and will be removed in version 0.40.0. Using the `load_attn_procs()` method has been deprecated and will be removed in a future version. Please use `load_lora_adapter()`.
deprecate("load_attn_procs", "0.40.0", deprecation_message)
Traceback (most recent call last):
File "/home/new_project/prohibit/generate.py", line 29, in <module>
pipe.unet.load_attn_procs(model_path)
File "/home/miniconda3/envs/new/lib/python3.9/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
return fn(*args, **kwargs)
File "/home/miniconda3/envs/new/lib/python3.9/site-packages/diffusers/loaders/unet.py", line 220, in load_attn_procs
is_model_cpu_offload, is_sequential_cpu_offload = self._process_lora(
File "/home/miniconda3/envs/new/lib/python3.9/site-packages/diffusers/loaders/unet.py", line 346, in _process_lora
lora_config = LoraConfig(**lora_config_kwargs)
TypeError: __init__() got an unexpected keyword argument 'lora_bias'System Info
- 🤗 Diffusers version: 0.33.0.dev0
- Platform: Linux-6.8.0-48-generic-x86_64-with-glibc2.39
- Running on Google Colab?: No
- Python version: 3.9.21
- PyTorch version (GPU?): 2.5.1+cu124 (True)
- Flax version (CPU?/GPU?/TPU?): not installed (NA)
- Jax version: not installed
- JaxLib version: not installed
- Huggingface_hub version: 0.27.0
- Transformers version: 4.47.1
- Accelerate version: 1.2.1
- PEFT version: 0.7.0
- Bitsandbytes version: not installed
- Safetensors version: 0.5.0
- xFormers version: not installed
- Accelerator: NVIDIA GeForce RTX 3090 Ti, 24564 MiB
NVIDIA GeForce RTX 3090 Ti, 24564 MiB - Using GPU in script?: yes
- Using distributed or parallel set-up in script?: <no
Who can help?
No response