SEINE icon indicating copy to clipboard operation
SEINE copied to clipboard

[ICLR 2024] SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction

Results 24 SEINE issues
Sort by recently updated
recently updated
newest added

raise NotImplementedError(msg) NotImplementedError: No operator found for `memory_efficient_attention_forward` with inputs: query : shape=(1, 2, 1, 40) (torch.float32) key : shape=(1, 2, 1, 40) (torch.float32) value : shape=(1, 2, 1, 40)...

File "/data/SEINE/sample_scripts/with_mask_sample.py", line 258, in main(omega_conf) File "/data/SEINE/sample_scripts/with_mask_sample.py", line 247, in main torchvision.io.write_video(save_video_path, video_, fps=8) File "/root/anaconda3/envs/seine/lib/python3.9/site-packages/torchvision/io/video.py", line 91, in write_video stream = container.add_stream(video_codec, rate=fps) File "av/container/output.pyx", line 67, in...

![img_v3_025r_d23a3324-3119-4455-8367-e671a17a74dg](https://github.com/Vchitect/SEINE/assets/23116994/1d7419d0-2fb1-46ec-9149-d2316b4c147e) After I installed according to the instructions, I executed the I2V instructions, reported the error, and the model was placed in the specified position. How to address it?

I am getting an error when running the inference . can anyone help me with this? python sample_scripts/with_mask_sample.py --config configs/sample_i2v.yaml loading model Traceback (most recent call last): File "/home/ubuntu/PycharmProjects/pythonProject/SEINE/sample_scripts/with_mask_sample.py", line...

Thanks for your interesting work! Can you tell me the batch size, learning rate and iterations during training?

Dear SEINE Contributors, I hope this message finds you well. I am reaching out to discuss an aspect of the SEINE model that I believe holds potential for further refinement,...

Hi, I have a question that in `Transformer3DModel.forward()`, you split the input `encoder_hidden_states` into two parts, `encoder_hidden_states_video` and `encoder_hidden_states_image`, before send it to `BasicTransformerBlock`. I would like to ask you...

Hello 我在Mac M1上面运行项目一直报错这个错误 提示无法加载CUDA的内容 麻烦看下如何解决 WARNING[XFORMERS]: xFormers can't load C++/CUDA extensions. xFormers was built for: PyTorch 2.0.1 with CUDA 1106 (you have 2.0.1) Python 3.9.16 (you have 3.9.16) Please reinstall...

作者您好,抱歉又来打扰您,对于论文中流程图有一些疑问?在流程图钟没看到文本 c 输入,在哪里体现了呢? ![image](https://github.com/Vchitect/SEINE/assets/56951874/2e2d1d80-b414-4b01-b7d4-761ce100702e)