Closed mhussar closed 1 year ago
If you're on Windows, install Windows Terminal and launch your webui-user.bat
inside it. Once the bug occurs, right-click the tab and click save or copy logs
It's hard to get the cause of the error without the traceback
text2video — The model selected is: ModelScope text2video extension for auto1111 webui Git commit: cac54c26 (Thu Apr 6 16:46:13 2023) 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 cuda Working in txt2vid mode 0%| | 0/1 [00:00<?, ?it/s]latents torch.Size([1, 4, 24, 32, 32]) tensor(-0.0051, device='cuda:0') tensor(0.9974, device='cuda:0') Traceback (most recent call last): File "D:\Projects\Personal\AI_ImageCreation\StableDiffusion1111_010723\stable-diffusion-webui\extensions\sd-webui-modelscope-text2video\scripts\text2vid.py", line 92, in process process_modelscope(skip_video_creation, ffmpeg_location, ffmpeg_crf, ffmpeg_preset, fps, add_soundtrack, soundtrack_path, \ File "D:\Projects\Personal\AI_ImageCreation\StableDiffusion1111_010723\stable-diffusion-webui\extensions\sd-webui-modelscope-text2video\scripts\text2vid.py", line 234, in processmodelscope samples, = pipe.infer(prompt, n_prompt, steps, frames, seed + batch if seed != -1 else -1, cfg_scale, File "D:\Projects\Personal\AI_ImageCreation\StableDiffusion1111_010723\stable-diffusion-webui/extensions/sd-webui-text2video/scripts\modelscope\t2v_pipeline.py", line 245, in infer x0 = self.diffusion.ddim_sample_loop( File "D:\Projects\Personal\AI_ImageCreation\StableDiffusion1111_010723\stable-diffusion-webui\venv\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context return func(*args, **kwargs) TypeError: GaussianDiffusion.ddim_sample_loop() got an unexpected keyword argument 'mask' Exception occurred: GaussianDiffusion.ddim_sample_loop() got an unexpected keyword argument 'mask'
This issue has been closed due to incorrect formatting. Please address the following mistakes and reopen the issue:
This issue has been closed due to incorrect formatting. Please address the following mistakes and reopen the issue:
Is there an existing issue for this?
Are you using the latest version of the extension?
What happened?
getting this error just for modelscope: Exception occurred: GaussianDiffusion.ddim_sample_loop() got an unexpected keyword argument 'mask'
Steps to reproduce the problem
What should have happened?
before the recent update modelscope was working fine creating a video
WebUI and Deforum extension Commit IDs
webui commit id - txt2vid commit id -
What GPU were you using for launching?
rtx 3090 24 vram
On which platform are you launching the webui backend with the extension?
Local PC setup (Windows)
Settings
default settings nothing fancy
Console logs
Additional information
No response