[X] I have searched the existing issues and checked the recent builds/commits of both this extension and the webui
Are you using the latest version of the extension?
[X] I have the modelscope text2video extension updated to the lastest version and I still have the issue.
What happened?
When trying to render anything with the ModelScope Model I get this error:
Traceback (most recent call last):
File "/Users/konsti/stable-diffusion-webui/extensions/sd-webui-text2video/scripts/t2v_helpers/render.py", line 24, in run
vids_pack = process_modelscope(args_dict)
File "/Users/konsti/stable-diffusion-webui/extensions/sd-webui-text2video/scripts/modelscope/process_modelscope.py", line 45, in process_modelscope
del shared.sd_model
AttributeError: can't delete attribute 'sd_model'
Exception occurred: can't delete attribute 'sd_model'
And with the VideoCrafter one I get this:
AssertionError: Torch not compiled with CUDA enabled
Exception occurred: Torch not compiled with CUDA enabled
Steps to reproduce the problem
Go to ....
Press ....
...
What should have happened?
No response
WebUI and Deforum extension Commit IDs
webui commit id - Newest of Vlad and Auto1111
txt2vid commit id - 2a7b60d6
Torch version
2.0.0
What GPU were you using for launching?
None
On which platform are you launching the webui backend with the extension?
Local PC setup (Mac)
Settings
Default
Console logs
(base) XXXX@XXXXs-MBP automatic % ./webui.sh --reinstall
Create and activate python venv
Launching launch.py...
12:53:04-449220 INFO Starting SD.Next
12:53:04-451156 INFO Python 3.10.9 on Darwin
12:53:04-468476 INFO Version: f6f1a73b Wed May 17 06:15:18 2023 -0400
12:53:04-749875 INFO Setting environment tuning
12:53:04-752418 INFO Forcing reinstall of all packages
12:53:04-754338 INFO Installing package: torch==2.0.0 torchvision==0.15.1
12:53:06-191356 INFO Torch 2.0.0
12:53:06-191949 INFO Installing package: tensorflow==2.12.0
12:53:06-507584 INFO Verifying requirements
12:53:06-508616 INFO Installing package: addict
12:53:07-377685 INFO Installing package: aenum
12:53:08-246553 INFO Installing package: aiohttp
12:53:09-248412 INFO Installing package: anyio
12:53:10-141952 INFO Installing package: appdirs
12:53:11-008352 INFO Installing package: astunparse
12:53:11-919323 INFO Installing package: bitsandbytes
12:53:12-786659 INFO Installing package: blendmodes
12:53:13-686273 INFO Installing package: clean-fid
12:53:14-638800 INFO Installing package: easydev
12:53:15-502344 INFO Installing package: extcolors
12:53:16-513044 INFO Installing package: facexlib
12:53:17-437827 INFO Installing package: filetype
12:53:18-359715 INFO Installing package: font-roboto
12:53:19-317207 INFO Installing package: fonts
12:53:20-305564 INFO Installing package: future
12:53:21-256779 INFO Installing package: gdown
12:53:22-212188 INFO Installing package: gfpgan
12:53:23-530162 INFO Installing package: GitPython
12:53:24-456717 INFO Installing package: httpcore
12:53:25-403444 INFO Installing package: inflection
12:53:26-316645 INFO Installing package: jsonmerge
12:53:27-240454 INFO Installing package: kornia
12:53:28-144962 INFO Installing package: lark
12:53:29-042952 INFO Installing package: lmdb
12:53:30-047543 INFO Installing package: lpips
12:53:31-019472 INFO Installing package: numpy
12:53:32-095276 INFO Installing package: omegaconf
12:53:33-054192 INFO Installing package: open-clip-torch
12:53:34-112277 INFO Installing package: opencv-contrib-python
12:53:35-103674 INFO Installing package: piexif
12:53:36-024377 INFO Installing package: Pillow
12:53:37-034706 INFO Installing package: psutil
12:53:37-976073 INFO Installing package: pyyaml
12:53:38-886677 INFO Installing package: realesrgan
12:53:39-883528 INFO Installing package: resize-right
12:53:40-766812 INFO Installing package: rich
12:53:41-663009 INFO Installing package: safetensors
12:53:42-553817 INFO Installing package: scipy
12:53:43-505396 INFO Installing package: tb_nightly
12:53:44-614549 INFO Installing package: toml
12:53:45-498309 INFO Installing package: torchdiffeq
12:53:46-394764 INFO Installing package: torchsde
12:53:47-281672 INFO Installing package: voluptuous
12:53:48-152699 INFO Installing package: yapf
12:53:49-052852 INFO Installing package: scikit-image
12:53:49-977595 INFO Installing package: basicsr
12:53:50-931572 INFO Installing package: requests==2.30.0
12:53:51-858669 INFO Installing package: tqdm==4.65.0
12:53:52-771686 INFO Installing package: accelerate==0.18.0
12:53:53-668161 INFO Installing package: opencv-python==4.7.0.72
12:53:54-605164 INFO Installing package: diffusers==0.16.1
12:53:55-500291 INFO Installing package: einops==0.4.1
12:53:56-396814 INFO Installing package: gradio==3.29.0
12:53:57-423657 INFO Installing package: numexpr==2.8.4
12:53:58-325016 INFO Installing package: pandas==1.5.3
12:53:59-301579 INFO Installing package: protobuf==3.20.3
12:54:00-312280 INFO Installing package: pytorch_lightning==1.9.4
12:54:01-315234 INFO Installing package: transformers==4.26.1
12:54:02-258341 INFO Installing package: timm==0.6.13
12:54:03-163333 INFO Installing package: tomesd==0.1.2
12:54:04-178592 INFO Installing package: urllib3==1.26.15
12:54:05-100358 INFO Installing package: onnxruntime==1.14.0
12:54:05-404617 ERROR Error running pip: install --upgrade onnxruntime==1.14.0
12:54:05-405805 INFO Installing packages
12:54:05-406173 INFO Installing package:
git+https://github.com/openai/CLIP.git@d50d76daa670286dd6cacf3bcd80b5e4823fc8e1
12:54:08-851905 INFO Running setup
12:54:08-852902 INFO Installing repositories
12:54:08-896559 INFO Installing submodules
12:54:09-282876 INFO Updating submodules
12:54:33-603454 INFO Extensions enabled: ['SwinIR', 'clip-interrogator-ext', 'sd-dynamic-thresholding',
'prompt-bracket-checker', 'sd-webui-controlnet', 'ScuNET', 'stable-diffusion-webui-rembg',
'sd-webui-model-converter', 'Lora', 'sd-extension-system-info',
'stable-diffusion-webui-images-browser', 'LDSR', 'multidiffusion-upscaler-for-automatic1111',
'a1111-sd-webui-lycoris', 'sd-webui-text2video']
12:54:33-604843 INFO Updating Wiki
12:54:34-081012 WARNING Setup complete with errors: 1
12:54:34-082477 WARNING See log file for more details: setup.log
12:54:34-083368 INFO Running extension preloading
12:54:34-085714 INFO Server arguments: ['--reinstall']
No module 'xformers'. Proceeding without it.
12:54:35-932570 INFO Libraries loaded
12:54:36-033919 INFO Available models: /Users/XXXX/automatic/models/Stable-diffusion 26
ControlNet v1.1.173
ControlNet v1.1.173
Image Browser: ImageReward is not installed, cannot be used.
OMP: Info #276: omp_set_nested routine deprecated, please use omp_set_max_active_levels instead.
12:54:36-935629 INFO Libraries loaded
12:54:37-050755 INFO Loading UI theme: black-orange
Running on local URL: http://127.0.0.1:7860
To create a public link, set `share=True` in `launch()`.
12:54:37-898947 INFO Local URL: http://127.0.0.1:7860/
12:54:37-899586 INFO API Docs: http://127.0.0.1:7860/docs
12:54:37-899916 INFO Initializing middleware
12:54:38-173929 INFO CUDA FP16 test passed but desired mode is set to FP32
12:54:38-174556 INFO Setting Torch parameters: dtype=torch.float32 vae=torch.float32 unet=torch.float32
Loading weights: /Users/XXXX/automatic/models/Stable-diffusion/2.1-Based/Artius/artiusV21_v21.safetensors ━━━ 0.… -:-…
GB
LatentDiffusion: Running in v-prediction mode
DiffusionWrapper has 865.91 M params.
12:54:38-457877 INFO Model created from config:
/Users/XXXX/automatic/models/Stable-diffusion/2.1-Based/Artius/artiusV21_v21.yaml
12:54:39-676854 INFO Applying scaled dot product cross attention optimization
12:54:39-692781 INFO Embeddings loaded: 17 ['DrD_PNTE768', 'KittyPic', 'XXXX-Embedding-2000',
'XXXX-Embedding-2500', 'XXXX-Embedding-3000', 'XXXX-Embedding-3500',
'XXXX-Embedding-4000', 'XXXX-Embedding-4500', 'XXXX-Embedding-5000',
'XXXX-Embedding-5500', 'XXXX-Embedding-6000', 'XXXX-Embedding-6500',
'XXXX-Embedding-7000', 'XXXX-Embedding-7500', 'XXXX-Embedding-8000',
'XXXX-Embedding-8500', 'XXXX-Embedding-9000']
12:54:39-693593 INFO Textual inversion embeddings skipped(1): RFKTR_bontrex-150
12:54:39-696862 INFO Model loaded in 1.5s (load=0.2s create=0.1s apply=0.4s vae=0.3s move=0.5s)
12:54:39-813643 INFO Model load finished: {'ram': {'used': 5.17, 'total': 64.0}}
12:54:39-934451 INFO Startup time: 5.8s (torch=0.6s gradio=0.9s libraries=0.4s models=0.1s scripts=0.9s opts
onchange=0.1s ui=0.8s start=0.1s scripts app_started_callback=0.2s checkpoint=1.9s)
12:54:39-935514 INFO Memory used: 2.74 total: 64.0
text2video — The model selected is: ModelScope
text2video extension for auto1111 webui
Git commit: <p>2a7b60d6</p><p>Sun May14 2023 18:36</p>
Starting text2video
Pipeline setup
config namespace(framework='pytorch', task='text-to-video-synthesis', model={'type': 'latent-text-to-video-synthesis', 'model_args': {'ckpt_clip': 'open_clip_pytorch_model.bin', 'ckpt_unet': 'text2video_pytorch_model.pth', 'ckpt_autoencoder': 'VQGAN_autoencoder.pth', 'max_frames': 16, 'tiny_gpu': 1}, 'model_cfg': {'unet_in_dim': 4, 'unet_dim': 320, 'unet_y_dim': 768, 'unet_context_dim': 1024, 'unet_out_dim': 4, 'unet_dim_mult': [1, 2, 4, 4], 'unet_num_heads': 8, 'unet_head_dim': 64, 'unet_res_blocks': 2, 'unet_attn_scales': [1, 0.5, 0.25], 'unet_dropout': 0.1, 'temporal_attention': 'True', 'num_timesteps': 1000, 'mean_type': 'eps', 'var_type': 'fixed_small', 'loss_type': 'mse'}}, pipeline={'type': 'latent-text-to-video-synthesis'})
device mps
Working in txt2vid mode
Traceback (most recent call last):
File "/Users/XXXX/automatic/extensions/sd-webui-text2video/scripts/t2v_helpers/render.py", line 24, in run
vids_pack = process_modelscope(args_dict)
File "/Users/XXXX/automatic/extensions/sd-webui-text2video/scripts/modelscope/process_modelscope.py", line 136, in process_modelscope
pbar = tqdm(range(args.batch_count), leave=False)
File "/Users/XXXX/automatic/venv/lib/python3.10/site-packages/tqdm/_tqdm.py", line 383, in __new__
File "/Users/XXXX/automatic/venv/lib/python3.10/site-packages/tqdm/_tqdm.py", line 68, in __init__
AttributeError: module 'sys' has no attribute 'setcheckinterval'
Exception occurred: module 'sys' has no attribute 'setcheckinterval'
Exception ignored in: <function tqdm.__del__ at 0x1076667a0>
Traceback (most recent call last):
File "/Users/XXXX/automatic/venv/lib/python3.10/site-packages/tqdm/_tqdm.py", line 764, in __del__
File "/Users/XXXX/automatic/venv/lib/python3.10/site-packages/tqdm/_tqdm.py", line 994, in close
AttributeError: 'tqdm' object has no attribute 'disable'
text2video — The model selected is: VideoCrafter (WIP)
text2video extension for auto1111 webui
Git commit: <p>2a7b60d6</p><p>Sun May14 2023 18:36</p>
VideoCrafter config:
{'model': {'target': 'lvdm.models.ddpm3d.LatentDiffusion', 'params': {'linear_start': 0.00085, 'linear_end': 0.012, 'num_timesteps_cond': 1, 'log_every_t': 200, 'timesteps': 1000, 'first_stage_key': 'video', 'cond_stage_key': 'caption', 'image_size': [32, 32], 'video_length': 16, 'channels': 4, 'cond_stage_trainable': False, 'conditioning_key': 'crossattn', 'scale_by_std': False, 'scale_factor': 0.18215, 'unet_config': {'target': 'lvdm.models.modules.openaimodel3d.UNetModel', 'params': {'image_size': 32, 'in_channels': 4, 'out_channels': 4, 'model_channels': 320, 'attention_resolutions': [4, 2, 1], 'num_res_blocks': 2, 'channel_mult': [1, 2, 4, 4], 'num_heads': 8, 'transformer_depth': 1, 'context_dim': 768, 'use_checkpoint': True, 'legacy': False, 'kernel_size_t': 1, 'padding_t': 0, 'temporal_length': 16, 'use_relative_position': True}}, 'first_stage_config': {'target': 'lvdm.models.autoencoder.AutoencoderKL', 'params': {'embed_dim': 4, 'monitor': 'val/rec_loss', 'ddconfig': {'double_z': True, 'z_channels': 4, 'resolution': 256, 'in_channels': 3, 'out_ch': 3, 'ch': 128, 'ch_mult': [1, 2, 4, 4], 'num_res_blocks': 2, 'attn_resolutions': [], 'dropout': 0.0}, 'lossconfig': {'target': 'torch.nn.Identity'}}}, 'cond_stage_config': {'target': 'lvdm.models.modules.condition_modules.FrozenCLIPEmbedder'}}}}
Loading model from /Users/XXXX/automatic/models/VideoCrafter/model.ckpt
LatentDiffusion: Running in eps-prediction mode
Successfully initialize the diffusion model !
DiffusionWrapper has 958.92 M params.
making attention of type 'vanilla' with 512 in_channels
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
making attention of type 'vanilla' with 512 in_channels
Traceback (most recent call last):
File "/Users/XXXX/automatic/extensions/sd-webui-text2video/scripts/t2v_helpers/render.py", line 26, in run
vids_pack = process_videocrafter(args_dict)
File "/Users/XXXX/automatic/extensions/sd-webui-text2video/scripts/videocrafter/process_videocrafter.py", line 41, in process_videocrafter
model, _, _ = load_model(config, ph.models_path+'/VideoCrafter/model.ckpt', #TODO: support safetensors and stuff
File "/Users/XXXX/automatic/extensions/sd-webui-text2video/scripts/videocrafter/sample_utils.py", line 37, in load_model
model.cuda()
File "/Users/XXXX/automatic/venv/lib/python3.10/site-packages/lightning_fabric/utilities/device_dtype_mixin.py", line 69, in cuda
device = torch.device("cuda", torch.cuda.current_device())
File "/Users/XXXX/automatic/venv/lib/python3.10/site-packages/torch/cuda/__init__.py", line 674, in current_device
_lazy_init()
File "/Users/XXXX/automatic/venv/lib/python3.10/site-packages/torch/cuda/__init__.py", line 239, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled
Exception occurred: Torch not compiled with CUDA enabled
Is there an existing issue for this?
Are you using the latest version of the extension?
What happened?
When trying to render anything with the ModelScope Model I get this error:
Traceback (most recent call last): File "/Users/konsti/stable-diffusion-webui/extensions/sd-webui-text2video/scripts/t2v_helpers/render.py", line 24, in run vids_pack = process_modelscope(args_dict) File "/Users/konsti/stable-diffusion-webui/extensions/sd-webui-text2video/scripts/modelscope/process_modelscope.py", line 45, in process_modelscope del shared.sd_model AttributeError: can't delete attribute 'sd_model' Exception occurred: can't delete attribute 'sd_model'
And with the VideoCrafter one I get this: AssertionError: Torch not compiled with CUDA enabled Exception occurred: Torch not compiled with CUDA enabled
Steps to reproduce the problem
What should have happened?
No response
WebUI and Deforum extension Commit IDs
webui commit id - Newest of Vlad and Auto1111 txt2vid commit id - 2a7b60d6
Torch version
2.0.0
What GPU were you using for launching?
None
On which platform are you launching the webui backend with the extension?
Local PC setup (Mac)
Settings
Default
Console logs
Additional information
No response