I am trying to run inference via L4 instance on colab and I am coming across this error of ImportError: cannot import name 'Cache' from 'transformers' (/usr/local/lib/python3.11/dist-packages/transformers/__init__.py)
The cache for model files in Transformers v4.22.0 has been updated. Migrating your old cache. This is a one-time only operation. You can interrupt this and resume the migration later on by calling `transformers.utils.move_cache()`.
0it [00:00, ?it/s]
2025-02-04 16:04:06.676396: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:477] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1738685046.999070 16881 cuda_dnn.cc:8310] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1738685047.079683 16881 cuda_blas.cc:1418] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
WARNING[XFORMERS]: xFormers can't load C++/CUDA extensions. xFormers was built for:
PyTorch 2.0.1+cu118 with CUDA 1108 (you have 2.1.0+cu121)
Python 3.11.4 (you have 3.11.11)
Please reinstall xformers (see https://github.com/facebookresearch/xformers#installing-xformers)
Memory-efficient attention, SwiGLU, sparse and more won't be available.
Set XFORMERS_MORE_DETAILS=1 for more details
error: XDG_RUNTIME_DIR not set in the environment.
ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
args
{'add_static_video_prompt': False,
'context_batch_size': 1,
'context_frames': 12,
'context_overlap': 4,
'context_schedule': 'uniform_v2',
'context_stride': 1,
'cross_attention_dim': 768,
'face_image_path': None,
'facein_model_cfg_path': '/content/MuseV/scripts/inference/../.././configs/model/facein.py',
'facein_model_name': None,
'facein_scale': 1.0,
'fix_condition_images': False,
'fixed_ip_adapter_image': True,
'fixed_refer_face_image': True,
'fixed_refer_image': True,
'fps': 12,
'guidance_scale': 7.5,
'height': None,
'img_length_ratio': 1.0,
'img_weight': 0.001,
'interpolation_factor': 1,
'ip_adapter_face_model_cfg_path': '/content/MuseV/scripts/inference/../.././configs/model/ip_adapter.py',
'ip_adapter_face_model_name': None,
'ip_adapter_face_scale': 1.0,
'ip_adapter_model_cfg_path': '/content/MuseV/scripts/inference/../.././configs/model/ip_adapter.py',
'ip_adapter_model_name': None,
'ip_adapter_scale': 1.0,
'ipadapter_image_path': None,
'lcm_model_cfg_path': '/content/MuseV/scripts/inference/../.././configs/model/lcm_model.py',
'lcm_model_name': None,
'log_level': 'INFO',
'motion_speed': 8.0,
'n_batch': 1,
'n_cols': 3,
'n_repeat': 1,
'n_vision_condition': 1,
'need_hist_match': False,
'need_img_based_video_noise': True,
'negative_prompt': 'V2',
'negprompt_cfg_path': '/content/MuseV/scripts/inference/../../configs/model/negative_prompt.py',
'noise_type': 'video_fusion',
'num_inference_steps': 30,
'output_dir': '/content/output',
'overwrite': False,
'prompt_only_use_image_prompt': False,
'record_mid_video_latents': False,
'record_mid_video_noises': False,
'redraw_condition_image': False,
'redraw_condition_image_with_facein': True,
'redraw_condition_image_with_ip_adapter_face': True,
'redraw_condition_image_with_ipdapter': True,
'redraw_condition_image_with_referencenet': True,
'referencenet_image_path': None,
'referencenet_model_cfg_path': '/content/MuseV/scripts/inference/../.././configs/model/referencenet.py',
'referencenet_model_name': None,
'save_filetype': 'mp4',
'save_images': False,
'sd_model_cfg_path': '/content/MuseV/scripts/inference/../../configs/model/T2I_all_model.py',
'sd_model_name': 'majicmixRealv6Fp16',
'seed': None,
'strength': 0.8,
'target_datas': 'all',
'test_data_path': '/content/MuseV/configs/tasks/vegeta_task.yaml',
'time_size': 12,
'unet_model_cfg_path': '/content/MuseV/scripts/inference/../.././configs/model/motion_model.py',
'unet_model_name': 'musev',
'use_condition_image': True,
'vae_model_path': '/content/MuseV/checkpoints/vae/sd-vae-ft-mse',
'video_guidance_scale': 3.5,
'video_guidance_scale_end': None,
'video_guidance_scale_method': 'linear',
'video_negative_prompt': 'V2',
'video_num_inference_steps': 10,
'video_overlap': 1,
'vision_clip_extractor_class_name': None,
'vision_clip_model_path': './checkpoints/ip_adapter/models/image_encoder',
'w_ind_noise': 0.5,
'width': None,
'write_info': False}
running model, T2I SD
{'majicmixRealv6Fp16': {'sd': '/content/MuseV/configs/model/../../checkpoints/t2i/sd1.5/majicmixRealv6Fp16'}}
lcm: None None
unet_model_params_dict_src dict_keys(['musev', 'musev_referencenet', 'musev_referencenet_pose'])
unet: musev /content/MuseV/configs/model/../../checkpoints/motion/musev
referencenet: None None
ip_adapter: None None
facein: None None
ip_adapter_face: None None
video_negprompt V2 badhandv4, ng_deepnegative_v1_75t, (((multiple heads))), (((bad body))), (((two people))), ((extra arms)), ((deformed body)), (((sexy))), paintings,(((two heads))), ((big head)),sketches, (worst quality:2), (low quality:2), (normal quality:2), lowres, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, age spot, glans, (((nsfw))), nipples, extra fingers, (extra legs), (long neck), mutated hands, (fused fingers), (too many fingers)
negprompt V2 badhandv4, ng_deepnegative_v1_75t, (((multiple heads))), (((bad body))), (((two people))), ((extra arms)), ((deformed body)), (((sexy))), paintings,(((two heads))), ((big head)),sketches, (worst quality:2), (low quality:2), (normal quality:2), lowres, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, age spot, glans, (((nsfw))), nipples, extra fingers, (extra legs), (long neck), mutated hands, (fused fingers), (too many fingers)
n_test_datas 1
2025-02-04 16:04:17,597- musev:887- INFO- vision_clip_extractor, None
test_model_vae_model_path /content/MuseV/checkpoints/vae/sd-vae-ft-mse
Keyword arguments {'torch_device': 'cuda'} are not expected by MusevControlNetPipeline and will be ignored.
Loading pipeline components...: 17% 1/6 [00:00<00:03, 1.47it/s]
Traceback (most recent call last):
File "/content/MuseV/scripts/inference/text2video.py", line 977, in <module>
sd_predictor = DiffusersPipelinePredictor(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/content/MuseV/musev/pipelines/pipeline_controlnet_predictor.py", line 243, in __init__
pipeline = MusevControlNetPipeline.from_pretrained(**params)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/content/MuseV/diffusers/src/diffusers/pipelines/pipeline_utils.py", line 1258, in from_pretrained
maybe_raise_or_warn(
File "/content/MuseV/diffusers/src/diffusers/pipelines/pipeline_utils.py", line 305, in maybe_raise_or_warn
unwrapped_sub_model = _unwrap_model(sub_model)
^^^^^^^^^^^^^^^^^^^^^^^^
File "/content/MuseV/diffusers/src/diffusers/pipelines/pipeline_utils.py", line 280, in _unwrap_model
from peft import PeftModel
File "/usr/local/lib/python3.11/dist-packages/peft/__init__.py", line 22, in <module>
from .auto import (
File "/usr/local/lib/python3.11/dist-packages/peft/auto.py", line 32, in <module>
from .mapping import MODEL_TYPE_TO_PEFT_MODEL_MAPPING
File "/usr/local/lib/python3.11/dist-packages/peft/mapping.py", line 25, in <module>
from .mixed_model import PeftMixedModel
File "/usr/local/lib/python3.11/dist-packages/peft/mixed_model.py", line 29, in <module>
from .peft_model import PeftModel
File "/usr/local/lib/python3.11/dist-packages/peft/peft_model.py", line 37, in <module>
from transformers import Cache, DynamicCache, EncoderDecoderCache, PreTrainedModel
ImportError: cannot import name 'Cache' from 'transformers' (/usr/local/lib/python3.11/dist-packages/transformers/__init__.py)
These are the libraries i installed, i tinkered with by trial and error to get them all installed. I faced alot of issues directly installing versions as mentioned in requirements.txt
Please let me know if anyone's found a way to set it up on colab, or got to install Musev without docker.
I am trying to run inference via L4 instance on colab and I am coming across this error of
ImportError: cannot import name 'Cache' from 'transformers' (/usr/local/lib/python3.11/dist-packages/transformers/__init__.py)Getting this error
These are the libraries i installed, i tinkered with by trial and error to get them all installed. I faced alot of issues directly installing versions as mentioned in requirements.txt
Please let me know if anyone's found a way to set it up on colab, or got to install Musev without docker.