Instructions to use ali-vilab/MS-Image2Video with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- OpenCLIP
How to use ali-vilab/MS-Image2Video with OpenCLIP:
import open_clip model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms('hf-hub:ali-vilab/MS-Image2Video') tokenizer = open_clip.get_tokenizer('hf-hub:ali-vilab/MS-Image2Video') - Notebooks
- Google Colab
- Kaggle
Example code reports error.
I just follow the example codefrom modelscope.pipelines import pipelinefrom modelscope.outputs import OutputKeyspipe = pipeline(task='image-to-video', model='damo/Image-to-Video', model_revision='v1.1.0')img = './image.png'output_video_path = pipe(img, output_video='./output.mp4')[OutputKeys.OUTPUT_VIDEO]
and it fails to save the video with the error as:
2023-09-05 16:43:30,202 - modelscope - WARNING - task image-to-video input definition is missing
2023-09-05 16:44:23,675 - modelscope - ERROR - Save Video Error with
2023-09-05 16:44:23,901 - modelscope - WARNING - task image-to-video output keys are missing
What else should I do? Can u give me some advice?
In addition, your model is based on the Modelscope, and we use the pipeline method to call your model. How can I directly use your model for potential modification (as the from_pretrained interface used in conventional hugging face model hub)?
same here...
same here...
I have resolved the issue. You need to reinstall the ffmpeg and uninstall the original one in the system, after that the example can run normally.