search

nateraw / stable-diffusion-videos

Create 🔥 videos with Stable Diffusion by exploring the latent space and morphing between text prompts
Apache License 2.0
4.36k stars 417 forks source link

run make_music_video.py prompt error at stable_diffusion_pipeline #108

Open eu09 opened 1 year ago

eu09 commented 1 year ago

python3 make_music_video.py Fetching 15 files: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 15/15 [00:00<00:00, 69750.07it/s] You have passed None for safety_checker to disable its functionality in <class 'stable_diffusion_videos.stable_diffusion_pipeline.StableDiffusionWalkPipeline'>. Note that this might lead to problems when using <class 'stable_diffusion_videos.stable_diffusion_pipeline.StableDiffusionWalkPipeline'> and is not recommended. You have disabled the safety checker for <class 'stable_diffusion_videos.stable_diffusion_pipeline.StableDiffusionWalkPipeline'> by passing safety_checker=None. Ensure that you abide to the conditions of the Stable Diffusion license and do not expose unfiltered results in services or applications open to the public. Both the diffusers team and Hugging Face strongly recommend to keep the safety filter enabled in all public facing circumstances, disabling it only for use-cases that involve analyzing network behavior or auditing its results. For more information, please have a look at https://github.com/huggingface/diffusers/pull/254 . Traceback (most recent call last): File "/home/elohlinux/stable-diffusion-videos/examples/make_music_video.py", line 45, in pipe.walk( File "/home/elohlinux/.local/lib/python3.10/site-packages/stable_diffusion_videos/stable_diffusion_pipeline.py", line 797, in walk return make_video_pyav( File "/home/elohlinux/.local/lib/python3.10/site-packages/stable_diffusion_videos/stable_diffusion_pipeline.py", line 115, in make_video_pyav frames = frames.permute(0, 2, 3, 1) AttributeError: 'NoneType' object has no attribute 'permute'

nateraw commented 1 year ago

Not able to reproduce this error. (see colab here). In the colab the only thing I changed is fps=5 so it would generate faster and batch_size=12 which is the highest batch size my Colab Pro+ machine allowed for.

This error looks like something went wrong with finding the frame files themselves.

Double check you're on the latest version of the code pip install --upgrade stable-diffusion-videos[realesrgan] and try again I guess?

Shlok-Bhakta commented 1 year ago

I'm not sure if this will help, I ran into the same issue as I was generating images. My issue was that the amount of interpolation frames was 0 at some point. I was programmatically generating numbers and would sometimes get an array that looked like this [7, 8, 15, 0, 6, 3, 5]. It would always error when generating because of that 0 in index 3. Hope that helps!