Text-to-Video
MLX
Diffusers
Safetensors
apple-silicon
video-generation
audio-generation
fasth3-omni
int4
8-step
Instructions to use Disrupt-linus/FastH3-Omni-MLX-INT4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Disrupt-linus/FastH3-Omni-MLX-INT4 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download Disrupt-linus/FastH3-Omni-MLX-INT4 --local-dir FastH3-Omni-MLX-INT4
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Add complete Qwen-VL text encoder weights and tokenizers for 1-shot self-contained inference
7b4e9b0 verified Download root/text_encoder/video_preprocessor_config.json from Disrupt-linus/FastH3-Omni-MLX-INT4: direct link, hf CLI and curl.
- Browser
- Download file 385 Bytes
-
https://huggingface.co/Disrupt-linus/FastH3-Omni-MLX-INT4/resolve/main/root/text_encoder/video_preprocessor_config.json
- Command line
-
hf download hf://Disrupt-linus/FastH3-Omni-MLX-INT4/root/text_encoder/video_preprocessor_config.json
-
curl -L -o video_preprocessor_config.json https://huggingface.co/Disrupt-linus/FastH3-Omni-MLX-INT4/resolve/main/root/text_encoder/video_preprocessor_config.json
385 Bytes
| { | |
| "size": { | |
| "longest_edge": 25165824, | |
| "shortest_edge": 4096 | |
| }, | |
| "patch_size": 16, | |
| "temporal_patch_size": 2, | |
| "merge_size": 2, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "processor_class": "Qwen3VLProcessor", | |
| "video_processor_type": "Qwen3VLVideoProcessor" | |
| } |