Revise README for text-to-video generation example

Updated example prompt and parameters for video generation.
This commit is contained in:
Prince Canuma
2026-01-12 17:21:54 +01:00
committed by GitHub
parent 535dd9a066
commit 61b003ff2c

View File

@@ -36,9 +36,11 @@ Supported models:
### Text-to-Video Generation
```bash
uv run mlx_video.generate --prompt "A cat walking on grass"
uv run mlx_video.generate --prompt "Two dogs of the poodle breed wearing sunglasses, close up, cinematic, sunset" -n 100 --width 768
```
<img src="https://github.com/Blaizzy/mlx-video/raw/main/examples/poodles.gif" width="512" alt="Poodles demo">
With custom settings:
```bash
@@ -58,7 +60,7 @@ python -m mlx_video.generate \
| `--prompt`, `-p` | (required) | Text description of the video |
| `--height`, `-H` | 512 | Output height (must be divisible by 64) |
| `--width`, `-W` | 512 | Output width (must be divisible by 64) |
| `--num-frames`, `-n` | 33 | Number of frames (must be 1 + 8*k) |
| `--num-frames`, `-n` | 100 | Number of frames |
| `--seed`, `-s` | 42 | Random seed for reproducibility |
| `--fps` | 24 | Frames per second |
| `--output`, `-o` | output.mp4 | Output video path |
@@ -106,16 +108,6 @@ mlx_video/
└── video_vae/ # VAE encoder/decoder
```
# Examples
Here's an example result generated by MLX-Video:
```sh
uv run mlx_video.generate --prompt "Two dogs of the poodle breed wearing sunglasses, close up, cinematic, sunset" -n 100 --width 768
```
<img src="https://github.com/Blaizzy/mlx-video/raw/main/examples/poodles.gif" width="512" alt="Poodles demo">
## License
MIT