Instructions to use stabilityai/stable-video-diffusion-img2vid-xt-1-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use stabilityai/stable-video-diffusion-img2vid-xt-1-1 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image, export_to_video # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-video-diffusion-img2vid-xt-1-1", dtype=torch.bfloat16, device_map="cuda") pipe.to("cuda") prompt = "A man with short gray hair plays a red electric guitar." image = load_image( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png" ) output = pipe(image=image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Notebooks
- Google Colab
- Kaggle
About Sora
This is a topic about Sora.
Now that we have sora from openai, this one seems obsolete though
Now that we have sora from openai, this one seems obsolete though
Oh? We actually "have" sora, now? How many super computers do you have in your garage that are ready to crank out videos for you?
Now that we have sora from openai, this one seems obsolete though
Sure but to run something like SORA localy you will need rtx 6090 titan with 80 gb vram
@Yhyu13 Also currently only a very few amount of people can test sora.
even when its out, its 99% going to be closed source like gpt 3.5
We do not have sora, this is always how they roll, they kept dall-e limited to beta for a long time as well.
测试:生成视频视频,请问该如何解决报错如下:
Sampling with EulerEDMSampler for 26 steps: 96%|████████████████████████████████████████████████████▉ | 25/26 [00:56<00:02, 2.27s/it]
2024-03-25 09:18:24.440 Uncaught app exception
Traceback (most recent call last):
File "/usr/local/lib/python3.10/dist-packages/streamlit/runtime/scriptrunner/script_runner.py", line 542, in _run_script
exec(code, module.__dict__)
File "/home/generative-models/scripts/demo/video_sampling.py", line 280, in
save_video_as_grid_and_mp4(samples, save_path, T, fps=saving_fps)
File "/home/generative-models/scripts/demo/streamlit_helpers.py", line 912, in save_video_as_grid_and_mp4
imageio.mimwrite(video_path, vid, fps=fps)
File "/usr/local/lib/python3.10/dist-packages/imageio/v2.py", line 495, in mimwrite
return file.write(ims, is_batch=True, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/imageio/plugins/tifffile_v3.py", line 224, in write
self._fh.write(image, **kwargs)
TypeError: TiffWriter.write() got an unexpected keyword argument 'fps'