rhymes-ai
/

Allegro-TI2V

AllegroPipeline

Model card Files Files and versions Community

RhymesAI commited on Nov 25, 2024

Commit

5de6e57

•

1 Parent(s): 84a6333

Update README.md

Files changed (1) hide show

README.md +0 -1

README.md CHANGED Viewed

@@ -117,7 +117,6 @@ library_name: diffusers
     | `--first_frame`      | [Required] First-frame image input for image-to-video generation.                                  |
     | `--last_frame`       | [Optional] If provided, the model will generate intermediate video content based on the specified first and last frame images. |
     | `--enable_cpu_offload` | [Optional] Offload the model into CPU for less GPU memory cost (about 9.3G, compared to 27.5G if CPU offload is not enabled), but the inference time will increase significantly. |
 5. **(Optional) Interpolate the video to 30 FPS**
 - It is recommended to use [EMA-VFI](https://github.com/MCG-NJU/EMAVFI) to interpolate the video from 15 FPS to 30 FPS.

     | `--first_frame`      | [Required] First-frame image input for image-to-video generation.                                  |
     | `--last_frame`       | [Optional] If provided, the model will generate intermediate video content based on the specified first and last frame images. |
     | `--enable_cpu_offload` | [Optional] Offload the model into CPU for less GPU memory cost (about 9.3G, compared to 27.5G if CPU offload is not enabled), but the inference time will increase significantly. |
 5. **(Optional) Interpolate the video to 30 FPS**
 - It is recommended to use [EMA-VFI](https://github.com/MCG-NJU/EMAVFI) to interpolate the video from 15 FPS to 30 FPS.