Add the usage snippet, taken from the inference project's own README

split_model.json

@@ -17,5 +17,6 @@
   "extra_links": [
     "q8 variant: https://huggingface.co/dgrauet/void-model-mlx-q8",
     "q4 variant: https://huggingface.co/dgrauet/void-model-mlx-q4"
-  ]
+  ],
+  "cli_snippet": "git clone https://github.com/dgrauet/VideoX-Fun-mlx.git\nexport VIDEOX_FUN_MLX_PATH=/path/to/VideoX-Fun-mlx\npip install mlx opencv-python-headless pillow numpy sentencepiece\n\npython -m void_mlx.infer \\\n    --sample sample/BigBen \\\n    --pass1 weights/void_pass1.safetensors \\\n    --pass2 weights/void_pass2.safetensors \\\n    --base-model /path/to/CogVideoX-Fun-V1.5-5b-InP-mlx-q8 \\\n    --steps 30 --max-frames 13 --height 352 --width 624 \\\n    --low-ram --output result.gif"
 }