Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

为什么采样出来的视频是倒放的? #568

Open
jimmysue opened this issue Jan 7, 2025 · 0 comments
Open

为什么采样出来的视频是倒放的? #568

jimmysue opened this issue Jan 7, 2025 · 0 comments

Comments

@jimmysue
Copy link

jimmysue commented Jan 7, 2025

下载了 1.3 版本的模型,使用 opensora/sample/sample.py 进行采样, 出来的结果是倒放的为什么?

下面是一个生成的例子:

EulerAncestralDiscrete_1_gs7.5_s100.mp4

下面是我运行的参数配置:

 "--master_port", "29514",
                "--nnode", "1",
                "--nproc_per_node", "1", 
                "opensora/sample/sample.py",
                "--model_path", "/root/sjz/github/Open-Sora-Plan/ckpts/any93x640x640",
                "--version", "v1_3",
                "--num_frames", "93",
                "--height", "352",
                "--width", "640",
                "--cache_dir", "/root/sjz/github/Open-Sora-Plan/ckpts",
                "--text_encoder_name_1", "/root/sjz/github/Open-Sora-Plan/ckpts/mt5-xxl",
                "--text_prompt", "examples/sora.txt",
                "--ae", "WFVAEModel_D8_4x8x8",
                "--ae_path", "/root/sjz/github/Open-Sora-Plan/ckpts/vae",
                "--save_img_path", "./train_1_3_nomotion_fps18",
                "--fps", "18",
                "--guidance_scale", "7.5",
                "--num_sampling_steps", "100",
                "--max_sequence_length", "512",
                "--sample_method", "EulerAncestralDiscrete",
                "--seed", "1234",
                "--num_samples_per_prompt", "1",
                "--rescale_betas_zero_snr",
                "--prediction_type", "v_prediction"
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant